The DOI matches its Crossref record; 117 of the 130 references it cites were found in a registry or an index; 30 of the 45 sources its claims cite were checked for support.
Federated Learning for Healthcare Informatics
Open accessAbstract
With the rapid development of computer software and hardware technologies, more and more healthcare data are becoming readily available from clinical institutions, patients, insurance companies, and pharmaceutical industries, among others. This access provides an unprecedented opportunity for data science technologies to derive data-driven insights and improve the quality of care delivery. Healthcare data, however, are usually fragmented and private making it difficult to generate robust results across populations. For example, different hospitals own the electronic health records (EHR) of different patient populations and these records are difficult to share across hospitals because of their sensitive nature. This creates a big barrier for developing effective analytical approaches that are generalizable, which need diverse, "big data." Federated learning, a mechanism of training a shared global model with a central server while keeping all the sensitive data in local institutions where the data belong, provides great promise to connect the fragmented healthcare data sources with privacy-preservation. The goal of this survey is to provide a review for federated learning technologies, particularly within the biomedical space. In particular, we summarize the general solutions to the statistical challenges, system challenges, and privacy issues in federated learning, and point out the implications and potentials in healthcare.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
14 No basis given · 10 Own interpretation · 9 Supported · 8 Partly supported · 3 Sources not found · 3 No full text of the sources · 1 Couldn’t confirm · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Another commonly used method is globally sharing a small portion of data between all the clients [75, 111]. The shared subset is required containing a uniform distribution over classes from the central server to the clients.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Could not verifycites [75] Nishio T, Yonetani R (2018) Client selection for federated learning with heterogeneous resources in mobile edge. arXiv:1804.08333 sourceExperimental — accuracy not yet measured
The Experimental Setup (p. 5) describes IID and non-IID data assignments, but not sharing a small, class-balanced subset among clients. The Results (p. 7) discuss increasing client participation or using model compression to alleviate non-IID effects. Searches for shared data and uniform class distribution found no passage addressing the claimed method. (LLM, conf=0.76)
- Supportedcites [111] Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V (2018) Federated learning with non-iid data. arXiv:1806.00582 source
Section 4.2 (p. 7) proposes a small, globally shared dataset with a uniform distribution over classes, distributed from the cloud to clients to improve federated learning with non-IID data. Section 4.2 (p. 8) reports improved accuracy using this strategy. (LLM, conf=0.93)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“When the component distributions are actually different, pluralism can outperform the “ideal” IID baseline.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Supportedcites [28] Eichner H, Koren T, McMahan HB, Srebro N, Talwar K (2019) Semi-cyclic stochastic gradient descent. arXiv:1904.10120 source
The Summary (p. 8) states the claim directly, adding that the paper's experiments illustrate it. Section 4 (p. 4) explains that separate predictors can benefit when component subproblems conflict. (LLM, conf=0.95)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“It is demonstrated can work with certain non independent identical distribution (non-IID) data by requiring all the clients to share the same model.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Supportedcites [69] McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, pp 1273–1282 source
The Experimental Results (p. 6) report that FedAvg achieved substantial speedups on pathologically non-IID MNIST data and worked on non-IID Shakespeare data. The FederatedAveraging Algorithm (p. 4) describes clients updating a shared starting model and the server averaging their models. The paper does not establish that sharing a model alone is sufficient for every non-IID setting, but the claim is limited to certain data. (LLM, conf=0.88)
boostedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Most centralized models are trained on the aggregated training samples obtained from the samples drawn from the local clients [96, 111]. Intrinsically, the centralized model is trained to minimize the loss with respect to the uniform distribution [73]”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Not matchedcites [96] Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. In: Advances in neural information processing systems, pp 4424–4434
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Partly supportedcites [111] Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V (2018) Federated learning with non-iid data. arXiv:1806.00582 sourceExperimental — accuracy not yet measured
Section 3.1 (p. 4) describes centralized training as optimizing population loss, but it does not say the population distribution is uniform. Sections 4.1–4.2 (p. 7) specify a uniform distribution over classes only for a separate, globally shared dataset used in the authors’ data-sharing strategy. That does not establish that centralized models generally minimize loss with respect to a uniform distribution. (LLM, conf=0.84)
- Not matchedcites [73] Mohri M, Sivek G, Suresh AT (2019) Agnostic federated learning. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International conference on machine learning, proceedings of machine learning research, vol 97. PMLR, Long Beach, pp 4615–4625
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
Every source the paper cites for this claim was checked and supports it.
In the paper
“The performance of convolutional neural networks trained with FedAvg algorithm can reduce significantly due to the weight divergence [111].”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Supportedcites [111] Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V (2018) Federated learning with non-iid data. arXiv:1806.00582 source
The Introduction (p. 1) reports substantial accuracy reductions for CNNs trained with FedAvg on highly skewed non-IID data. The Introduction (p. 2) attributes that reduction to weight divergence, directly supporting the claim's explanation. (LLM, conf=0.94)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“For example, Obermeyer et al. [76] found that a commonly used algorithm to determine enrollment in specific health programs was biased against African Americans, assigning the same level of risk to healthier Caucasian patients.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
What the sources say
- Supportedcites [76] Obermeyer Z, Powers B, Vogeli C, Mullainathan S (2019) Dissecting racial bias in an algorithm used to manage the health of populations. Science 366(6464):447–453 source
The paper’s opening section says the widely used algorithm helps identify patients for additional care and that, at a given risk score, Black patients are considerably sicker than White patients. The “Health disparities conditional on risk score” section likewise reports that Black patients are less healthy than White patients at any level of algorithm prediction. Page numbers are not provided in our copy. (LLM, conf=0.94)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Thus, some researchers combine DP with SMC to reduce the growth of noise injection as the number of parties increases without sacrificing privacy while preserving provable privacy guarantees, protecting against extraction attacks and collusion threats [18, 100].”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- Could not verifycites [18] Cheng K, Fan T, Jin Y, Liu Y, Chen T, Yang Q (2019) Secureboost: a lossless federated learning framework. arXiv:1901.08755 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes noise injection in differential privacy, and the Security Discussion (p. 5) mentions secure multi-party computation as a way to limit information leakage. Neither passage says the methods are combined or that combining them reduces noise growth as the number of parties increases. Searches for that combination, noise growth, and party count found no supporting passage. (LLM, conf=0.76)
- Not checked — no full text of the sourcecites [100] Truex S, Baracaldo N, Anwar A, Steinke T, Ludwig H, Zhang R (2018) A hybrid approach to privacy-preserving federated learning. arXiv:1812.03224 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“Therefore, federated learning has a promising application in NLP like virtual keyboard prediction [7, 39, 70].”
§ Federated Learning for Healthcare Informatics > Applications > Others
What the sources say
- Supportedcites [7] Bonawitz K, Eichner H, Grieskamp W, Huba D, Ingerman A, Ivanov V, Kiddon C, Konecny J, Mazzocchi S, McMahan HB, et al. (2019) Towards federated learning at scale: System design. arXiv:1902.01046 source
The Applications section (p. 8) describes Gboard using federated learning for keyboard content suggestions and next-word prediction. It also reports that the federated next-word model outperformed comparison models in live experiments, supporting the characterization of keyboard prediction as a promising application. (LLM, conf=0.94)
- Supportedcites [39] Hard A, Rao K, Mathews R, Beaufays F, Augenstein S, Eichner H, Kiddon C, Ramage D (2018) Federated learning for mobile keyboard prediction. arXiv:1811.03604 source
The Abstract (p. 1) describes training a language model with federated learning for next-word prediction in a smartphone virtual keyboard and reports better prediction recall than server-based training. The Conclusion (p. 6) says the federated model outperformed the comparison models on that task, supporting the claim that this is a promising NLP application. (LLM, conf=0.94)
- Supportedcites [70] McMahan HB, Ramage D, Talwar K, Zhang L (2017) Learning differentially private recurrent language models. arXiv:1710.06963 source
The Introduction (p. 1) identifies next-word prediction on a mobile keyboard as the paper’s motivating application. The Experimental Results (p. 6) evaluate federated training of a language model tuned for that setting, and the Conclusions (p. 9) describe its promise for real-world applications. The experiments used a public dataset, so this supports the claim of a promising application, not a deployed keyboard system. (LLM, conf=0.92)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Their results show that training the model in the federated learning framework leads to comparable performance to the traditional centralized learning setting.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
What the sources say
- Supportedcites [90] Sharma P, Shamout FE, Clifton DA (2019) Preserving patient privacy while training a predictive model of in-hospital mortality. arXiv:1912.00354 source
The Abstract (p. 1) states that federated training achieved performance comparable to traditional centralized training. The Problem Formulation (p. 2) identifies the task as predicting in-hospital mortality for ICU patients, and the Summary (p. 4) repeats the performance comparison. (LLM, conf=0.95)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, this specific uniform distribution is not an adequate solution in most scenarios.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 19
- Probably not a substantial claim. 13
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Privacy and Security: Additional privacy protections are needed for unreliable participating clients. It is impossible to ensure all clients are equally reliable.”
§ Federated Learning for Healthcare Informatics > Federated Learning
What the sources say
- Partly supportedcites [13] Caldas S, Wu P, Li T, Konečnỳ J, McMahan HB, Smith V, Talwalkar A (2018) Leaf: a benchmark for federated settings. arXiv:1812.01097 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says federated methods must address privacy and security concerns because personally generated data is sensitive. It does not say that participating clients are unreliable, that their reliability cannot be ensured, or that unreliability calls for additional privacy protections. (LLM, conf=0.83)
- Not matchedcites [96] Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. In: Advances in neural information processing systems, pp 4424–4434
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of participating clients in federated learning is large, potentially thousands or millions.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Federated dropout not only reduces the downlink communication but also reduces the size of uplink updates. Moreover, the local computational costs is correspondingly reduced since the local training procedure dealing with parameters with smaller dimensions.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Communication Efficiency of Federated Learning
What the sources say
- Supportedcites [12] Caldas S, Konečny J, McMahan HB, Talwalkar A (2018) Expanding the reach of federated learning by reducing client resource requirements. arXiv:1812.07210 source
Section 3.2 (p. 4) says federated dropout transmits only the coefficients needed for a smaller sub-model, reducing server-to-client communication. It explicitly states that client-to-server updates are smaller and that local training requires fewer FLOPS. (LLM, conf=0.95)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Communication Efficiency: The number of clients K is large and can be much bigger than the average number of training sample stored in the activated clients, i.e., K ≫ (n/K).”
§ Federated Learning for Healthcare Informatics > Federated Learning
What the sources say
- Supportedcites [13] Caldas S, Wu P, Li T, Konečnỳ J, McMahan HB, Smith V, Talwalkar A (2018) Leaf: a benchmark for federated settings. arXiv:1812.01097 source
Table 1 (Section 2 LEAF, p. 3) reports thousands to millions of devices for several datasets, with far fewer mean samples per device—for example, 660,120 devices and 2.42 samples per device in Sent140. The Introduction (p. 1) also describes federated settings as having very large numbers of devices. These passages support the claim that client count can greatly exceed average samples per client, though not for every dataset listed. (LLM, conf=0.91)
- Not matchedcites [96] Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. In: Advances in neural information processing systems, pp 4424–4434
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Therefore, some researches began to study fully decentralized framework where the central server is not required [41, 60, 85, 91]. The local clients are distributed over the graph/network where they only communicate with their one-hop neighbors.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Communication Efficiency of Federated Learning
What the sources say
- Supportedcites [41] He C, Tan C, Tang H, Qiu S, Liu J (2019) Central server free federated learning over single-sided trust social networks. arXiv:1910.04956 source
The Introduction (p. 1) describes a decentralized architecture in which the central node is removed and each node communicates only with its neighbors. It also presents the paper’s federated-learning setting as one without a central server; graph neighbors correspond to the citing sentence’s one-hop neighbors. (LLM, conf=0.94)
- Supportedcites [60] Lalitha A, Kilinc OC, Javidi T, Koushanfar F (2019) Peer-to-peer federated learning on graphs. arXiv:1901.11173 source
The Introduction (p. 1) explicitly describes a fully decentralized framework with no centralized controller and nodes that communicate only with their one-hop neighbors. The Discussion (p. 6) likewise describes learning with no central server. (LLM, conf=0.95)
- Partly supportedcites [85] Roy AG, Siddiqui S, Pölsterl S, Navab N, Wachinger C (2019) Braintorrent: a peer-to-peer environment for decentralized federated learning. arXiv:1905.06731 sourceExperimental — accuracy not yet measured
The Introduction (p. 2) and Conclusion (p. 8) describe BrainTorrent as server-less, with clients communicating directly rather than through a central server. The one-hop-neighbor restriction is not supported as a general network rule: Section 2.2 (p. 4) says every client is directly connected to every other client, and an initiating client pings all the others. (LLM, conf=0.86)
- Partly supportedcites [91] Shayan M, Fung C, Yoon CJ, Beschastnikh I (2018) Biscotti: a ledger for private and secure peer-to-peer machine learning. arXiv:1811.09904 sourceExperimental — accuracy not yet measured
The Abstract (p. 1) describes Biscotti as a fully decentralized peer-to-peer approach, supporting the claim that it does not require a central server. The Noising protocol (p. 7) says a peer contacts selected noising peers, but our copy does not establish that clients communicate only with one-hop neighbors. (LLM, conf=0.87)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Compared to AFL, Li et al. [64] proposed q-Fair Federated Learning (q-FFL), assigning higher weight to devices with poor performance, so that the distribution of accuracy in the network reduces in variance.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Supportedcites [64] Li T, Sanjabi M, Smith V (2019) Fair resource allocation in federated learning. arXiv:1905.10497 source
The Introduction (p. 1) says q-FFL gives higher relative weight to devices with higher loss. Section 4.2 (p. 7) reports that q-FFL with q > 0 reduces the variance of testing accuracies across devices. (LLM, conf=0.94)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Statistical Challenge: The data distribution among all clients differ greatly, i.e., , we have . It is such that any data points available locally are far from being a representative sample of the overall distribution, i.e., .”
§ Federated Learning for Healthcare Informatics > Federated Learning
What the sources say
- Partly supportedcites [13] Caldas S, Wu P, Li T, Konečnỳ J, McMahan HB, Smith V, Talwalkar A (2018) Leaf: a benchmark for federated settings. arXiv:1812.01097 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says devices have different, though perhaps related, data-generating distributions, supporting the claim of heterogeneous client data. It does not establish that every client's local samples are far from representative of the overall distribution; that absolute formulation goes beyond the passage. (LLM, conf=0.84)
- Not matchedcites [96] Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. In: Advances in neural information processing systems, pp 4424–4434
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, DP only protects users from data leakage to a certain extent and may reduce performance in prediction accuracy because it is a lossy method [18].”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- Supportedcites [18] Cheng K, Fan T, Jin Y, Liu Y, Chen T, Yang Q (2019) Secureboost: a lossless federated learning framework. arXiv:1901.08755 source
The Introduction (p. 1) says differential privacy prevents user-data leakage only to a certain degree. It also says that adding noise makes the method lossy in machine learning and may result in unsatisfactory prediction accuracy. (LLM, conf=0.95)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Federated learning has also enabled predictive modeling based on diverse sources, which can provide clinicians with additional insights into the risks and benefits of treating patients earlier [9, 10, 90].”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
What the sources say
- Partly supportedcites [9] Boughorbel S, Jarray F, Venugopal N, Moosa S, Elhadi H, Makhlouf M (2019) Federated uncertainty-aware learning for distributed hospital ehr data. arXiv:1910.12191 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says federated learning enables predictive models trained jointly from different EHR sources. The Clinical Application section (p. 2) describes predicting preterm-birth risk three months before delivery, but does not say the model gives clinicians insight into the risks and benefits of treating patients earlier. (LLM, conf=0.88)
- Partly supportedcites [10] Brisimi TS, Chen R, Mela T, Olshevsky A, Paschalidis IC, Shi W (2018) Federated learning of predictive models from federated electronic health records. Int J Med Inform 112:59–67 sourceExperimental — accuracy not yet measured
The Abstract (Objective) and Conclusions describe a federated model that uses distributed EHR data to predict future hospitalizations. The Introduction (Health application) links prediction and early prevention, but the paper does not assess the risks and benefits of treating patients earlier or show that its model gives clinicians insight into that trade-off. Page numbers are unavailable in our copy. (LLM, conf=0.86)
- Partly supportedcites [90] Sharma P, Shamout FE, Clifton DA (2019) Preserving patient privacy while training a predictive model of in-hospital mortality. arXiv:1912.00354 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes federated training of an in-hospital mortality model using data distributed across hospitals, and the Summary (p. 4) discusses the potential value of larger, more diverse datasets. The paper does not say that its model gives clinicians insight into the risks and benefits of treating patients earlier. Its evaluation used one database distributed among virtual workers, rather than data collected from multiple hospitals (Dataset, p. 3). (LLM, conf=0.86)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Federated learning is a viable method to connect EHR data from medical institutions, allowing them to share their experiences, and not their data, with a guarantee of privacy [9, 25, 34, 45, 65, 82].”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
What the sources say
- Partly supportedcites [9] Boughorbel S, Jarray F, Venugopal N, Moosa S, Elhadi H, Makhlouf M (2019) Federated uncertainty-aware learning for distributed hospital ehr data. arXiv:1910.12191 sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says federated learning jointly trains models from different EHR sources without sharing data, and §3.2 (p. 3) says the proposed algorithm preserves data privacy by sending model updates to the data location. Those passages support the paraphrase, but not the citing sentence’s stronger claim of a privacy guarantee; the Introduction also identifies privacy as an ongoing challenge. (LLM, conf=0.82)
- Partly supportedcites [25] Duan R, Boland MR, Liu Z, Liu Y, Chang HH, Xu H, Chu H, Schmid CH, Forrest CB, Holmes JH, et al. (2020) Learning from electronic health records across multiple sites: a communication-efficient and privacy-preserving distributed algorithm. J Am Med Inform Assoc 27(3):376–385 sourceExperimental — accuracy not yet measured
The Conclusion (page not provided) says ODAL enables analysis across multiple clinical datasets without transferring patient-level data, supporting the claim that institutions can learn from EHR data without sharing those records. It defines privacy preservation in that limited sense; it does not establish the citing sentence’s broader “guarantee of privacy.” (LLM, conf=0.87)
- Partly supportedcites [34] Gruendner J, Schwachhofer T, Sippl P, Wolf N, Erpenbeck M, Gulden C, Kapsner LA, Zierk J, Mate S, Stürzl M, et al. (2019) KETOS: Clinical decision support and machine learning as a service–A training and deployment platform based on Docker, OMOP-CDM, and FHIR Web Services. PloS one 14(10):1–16 sourceExperimental — accuracy not yet measured
The Results section (Example model 3; page unavailable) describes training models across a federated hospital network while only aggregated statistics leave each institution. The Discussion likewise says patient data need not leave hospitals. These passages support privacy-preserving cross-institutional training, but they do not establish the claimed guarantee of privacy. (LLM, conf=0.86)
- Partly supportedcites [45] Huang L, Liu D (2019) Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. arXiv:1903.09296 sourceExperimental — accuracy not yet measured
The Introduction (page unavailable) says federated learning keeps EMR data local and aggregates locally computed results, allowing institutions to learn together without sharing the records. The Conclusions (page unavailable) describe the authors’ clustering method as avoiding a privacy breach. Neither passage establishes the citing sentence’s stronger claim of a guarantee of privacy. (LLM, conf=0.84)
- Partly supportedcites [65] Li Z, Roberts K, Jiang X, Long Q (2019) Distributed learning from multiple ehr databases: Contextual embedding models for medical events. J Biomed Inform 92:103138 sourceExperimental — accuracy not yet measured
The Distributed Noise Contrastive Estimation and Privacy Protection sections describe building a model from multiple EHR databases without sharing patient data; sites share a differentially private count table instead. But the Conclusion and Discussion says the experiment used two EHR systems at one institution, not different hospitals, and calls for evaluation across hospitals. The paper describes privacy protection, not an unqualified guarantee of privacy. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [82] Raja PV, Sivasankar E (2014) Modern framework for distributed healthcare data analytics based on hadoop. In: Information and communication technology-EurAsia conference. Springer, pp 348–355 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Federated learning, a mechanism of training a shared global model with a central server while keeping all the sensitive data in local institutions where the data belong, provides great promise to connect the fragmented healthcare data sources with privacy-preservation.”
§ Federated Learning for Healthcare Informatics > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Mohri et al. [73] proposed a minimax optimization scheme, i.e., agnostic federated learning (AFL), where the centralized model is optimized for any possible target distribution formed by a mixture of the client distributions.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges of Federated Learning
What the sources say
- Not matchedcites [73] Mohri M, Sivek G, Suresh AT (2019) Agnostic federated learning. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International conference on machine learning, proceedings of machine learning research, vol 97. PMLR, Long Beach, pp 4615–4625
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Apparently, we can consider three ways to reduce the communication cost: (a) reduce the number of clients K, (b) reduce the update size, (c) reduce the number of updates U.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Communication Efficiency of Federated Learning
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Healthcare data, however, are usually fragmented and private making it difficult to generate robust results across populations.”
§ Federated Learning for Healthcare Informatics > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Federated learning holds great promises on healthcare data analytics.”
§ Federated Learning for Healthcare Informatics > Introduction
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Federated learning, a mechanism of training a shared global model with a central server while keeping all the sensitive data in local institutions where the data belong”
§ Federated Learning for Healthcare Informatics > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“Without well-designed incentives, self-interested mobile or other wearable devices will be reluctant to participate in federal learning tasks, which will hinder the adoption of federated learning [53].”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
What the sources say
- Not checked — no full text of the sourcecites [53] Kang J, Xiong Z, Niyato D, Yu H, Liang YC, Kim DI (2019) Incentive design for efficient federated learning in mobile networks: A contract theory approach. arXiv:1905.07479 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Federated tries to make isolated institutions or devices share their experiences, and the performance of machine learning model will be significantly improved by the formed large medical dataset.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Differential privacy (DP) [26] is an alternative theoretical model for protecting the privacy of individual data, which has been widely applied to many areas, not only traditional algorithms, e.g., boosting [27], principal component analysis [15], support vector machine [86], but also deep learning research [1, 70]. It ensures that the addition or removal does not substantially affect the outcome”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- Not checked — no full text of the sourcecites [26] Dwork C, Kenthapadi K, McSherry F, Mironov I, Naor M (2006) Our data, ourselves: Privacy via distributed noise generation. In: Annual international conference on the theory and applications of cryptographic techniques. Springer, pp 486–503 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, most health systems suffer from data clutter and efficiency problems.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This widespread adoption is due in part by the fact that it enables a collaborative modeling mechanism that allows for efficient ML all while ensuring data privacy and legal compliance between multiple parties or multiple computing nodes.”
§ Federated Learning for Healthcare Informatics > Applications
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The analyzed results are apparently worthless when dirty data are accidentally used as samples.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Medical devices in hospitals have incomparable advantages over wearable devices.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Although SMC guarantees that none of the parties shares anything with each other or with any third party, it can not prevent an adversary from learning some individual information”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- Not checked — no full text of the sourcecites [8] Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage D, Segal A, Seth K (2017) Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security. ACM, pp 1175–1191 source
- Not matchedcites [78] Pathak M, Rane S, Raj B (2010) Multiparty differential privacy via aggregation of locally trained classifiers. In: Advances in neural information processing systems, pp 1876–1884
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Federated learning has the potential to connect all the isolated medical institutions, hospitals, or devices to make them share their experiences with privacy guarantee.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, the prediction task is currently restricted and relatively simple.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The quality of data collected from multiple sources is uneven and there is no uniform data standard.”
§ Federated Learning for Healthcare Informatics > Conclusions and Open Questions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“The creation and utility of standardized common data models, such as OMOP [44], allow for more wide-spread replication analyses but it does not overcome the limitations of joint data access.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
What the sources say
- Not matchedcites [44] Hripcsak G, Duke JD, Shah NH, Reich CG, Huser V, Schuemie MJ, Suchard MA, Park RW, Wong ICK, Rijnbeek PR, et al. (2015) Observational health data sciences and informatics (ohdsi): opportunities for observational researchers. Stud Health Technol Inform 216:574
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The authors state this as an assumption.
The number of participating clients in federated learning is large, potentially thousands or millions.
“In federated learning, we usually assume the number of participated clients (e.g., phones, cars, clinical institutions...) is large, potentially in the thousands or millions.”
The authors state this as an assumption.
There are K activated clients where data reside, each with a data distribution and a number of samples.
“Mathematically, assume there are K activated clients where the data reside in (a client could be a mobile phone, a wearable device, or a clinical institution data warehouse, etc.). Let denote the data distribution associated with client k and nk the number of samples available from that client.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Due to the contemporary features, DFL can be integrated with P2Pbased communication technologies such as blockchain [37] to build decentralized FL systems.”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [37]
Experimental — accuracy not yet measuredIn the citing paper
“FL enables healthcare records that are located across different institutions to be connected without revealing personal information [11].”
From A comprehensive survey on federated learning techniques for healthcare informatics (2023) · cites this paper as [11]
In the citing paper
“Xu et al. [11] surveyed the papers that focus FL in the biomedical area to provide a review.”
From A systematic review on federated learning in medical image analysis (2023) · cites this paper as [11]
In the citing paper
“By enabling multiple institutions to collaborate on AI model development without exchanging patient data, FL addresses the most pressing concerns in healthcare AI: privacy and data integrity.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“By enabling multiple institutions to collaborate on AI model development without exchanging patient data, FL addresses the most pressing concerns in healthcare AI: privacy and data integrity.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“As Ref. [19] explains, only the model parameters or gradients-essentially the learned features or updates to the model-are shared with a central server or among participants.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“This ensures that the raw patient data, which may contain personally identifiable information, never leaves the institution's premises where it was collected.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“The authors of [19] highlight the statistical variance in data distribution among clients, communication efficiency, and the potential for malicious clients as operational challenges in FL.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“The core principle of DP is to ensure that the presence or absence of any individual's data do not substantially alter the outcome of an analysis.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“This method is advantageous for sharing insights from health data, such as statistical summaries or AI model parameters, while safeguarding patient confidentiality.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“It functions by introducing a calculated amount of random noise, either to the data itself or to the outputs of algorithms, thereby making it statistically challenging for attackers to deduce sensitive information about any individual in the dataset.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“By creating a secure and tamper-proof ledger for medical data transactions, blockchain technology ensures the integrity and traceability of patient data, which is paramount in clinical settings.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“As privacy protection intensifies with increased noise, the usefulness of the data for research and the accuracy of AI models may be compromised.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“While it excels at enhancing privacy, it can simultaneously lead to reduced accuracy of predictions or analyses due to the added noise.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“For instance, blockchain can be used to securely manage electronic health records (EHRs), providing a reliable source of patient data for healthcare professionals and AI algorithms while preventing unauthorized access and data breaches [19].”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“Blockchain technology stands out for its unique attributes of decentralization, immutability, and transparency, which are particularly beneficial in the context of healthcare AI systems.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“This hybrid approach is designed to control the escalation of noise with the number of participants, thus maintaining both privacy and the practical value of the data.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“DP's application extends to various algorithms, including but not limited to boosting, principal component analysis, support vector machines, and deep learning.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“It is also effectively employed in Federated Learning scenarios involving decentralized data processing across multiple entities, such as hospitals or research institutions, to prevent indirect data leakage-a prevalent issue in collaborative environments [19].”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“By enabling the training of AI models on decentralized data sources, FL ensures that sensitive patient information remains within the confines of the local institution, thereby preserving privacy.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“To counterbalance this, researchers often integrate DP with other methods like Secure Multi-party Computation (SMC) to balance privacy and data utility [19].”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“At the same time, client selection protocols, model compression, and update reduction strategies aim to improve communication efficiency.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“FL's ability to integrate data from various sources without compromising privacy is a testament to its potential to enhance the capabilities of healthcare AI systems.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“Moreover, integrating Secure Multi-party Computation and Differential Privacy within FL frameworks enhances the privacy and security of the data, making FL a powerful tool for healthcare applications [19].”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“Techniques like Agnostic Federated Learning and q-Fair Federated Learning have been proposed to address the issue of data heterogeneity.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“By adopting these technologies, healthcare providers can meet the requirements of laws such as HIPAA in the United States and GDPR in Europe, which mandate strict data privacy and security standards.”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“The ethical considerations of patient data use are also addressed, as these technologies provide mechanisms to ensure that patient consent is obtained and that data are used to respect individual autonomy and dignity [19].”
From Balancing Privacy and Progress: A Review of Privacy Challenges, Systemic Oversight, and Patient Perceptions in AI-Driven Healthcare (2024) · cites this paper as [19]
In the citing paper
“In healthcare, AI performs a vital and crucial role in understanding the human thinking process through the computer using various effective AI-based algorithms to make complex examinations easier for healthcare professionals [83].”
From Federated learning-based AI approaches in smart healthcare: Concepts, taxonomies, challenges and open issues (2023) · cites this paper as [83]
In the citing paper
“To overcome this issue, federated learning is used to train the shared global model using data from several institutions without compromising data privacy [13].”
From A Comprehensive Analysis of Recent Deep and Federated-Learning-Based Methodologies for Brain Tumor Diagnosis (2022) · cites this paper as [13]
In the citing paper
“However, the results of deep learning are less accurate, as the datasets for training and testing are smaller.”
From A Comprehensive Analysis of Recent Deep and Federated-Learning-Based Methodologies for Brain Tumor Diagnosis (2022) · cites this paper as [13]
In the citing paper
“It has been observed that addressing the security issues was primarily focused [11]; however, more attention needs to be paid to the protection of end-user privacy in modern electronic health care systems [12], [13].”
From Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Survey (2023) · cites this paper as [11]
In the citing paper
“Federated machine learning has shown promising results in the healthcare industry, as indicated in [146,147].”
From Smart Wearables for the Detection of Cardiovascular Diseases: A Systematic Literature Review (2023) · cites this paper as [146]
In the citing paper
“Xu et al. performed a survey focusing on the progress of federated learning in healthcare informatics [7].”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [7]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 2×
“The naive way to solve the federated learning problem is through Federated Averaging (FedAvg) [61].”
BackgroundMethodDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“, sparse, low-rank [58], or more specifically, pruning the least useful connections in a network [37, 113], weight quantization [17, 89], and model distillation [43].”
BackgroundMIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141 · cited 1×
“tionbetweenparticipants aboutsomeoftheencryptedresults[70]. Table1:Summaryofrecentworkonfederatedlearningforhealthcare Problem MLMethod #Hospital Data PatientSimilarityLearning[54] Hashing 3 MIMIC-III[42] PatientSimilarityLearning[96] Hashing 20 MIMIC-III Phenotyping[47] *TF 1-5 MIMIC-III,UCSD[92] Phenotyping[59] NLP…”
MethodAdvances and Open Problems in Federated Learning
Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.04977 · Cited by 7,857
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“esearch[64].Whileprovidingahugeamountof patient data for analysis, EHRs contain systemic and random biases overall andspecifictohospitalsthatlimitthegeneralizabilityofresults.Forexample, Obermeyeretal.[68]foundthatacommonlyusedalgorithmtodetermineenrollment in specific health programs were biased against African America…”
BackgroundDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 2×
“, boosting [27], principal component analysis [15], support vector machine [86], but also deep learning research [1, 70].”
BackgroundFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322 · cited 3×
“privacyandlegalcompliancebetweenmultiplepartiesormultiplecomputing nodes. Some promising examples that highlight these capabilities are virtual keyboard prediction [31,62], smart retail [99], finance [97], vehicle-to-vehicle communication[80].Inthissection,wefocusprimarilyonapplicationswithin thehealthcarespace,butalso…”
BackgroundInfluentialHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662 · cited 1×
“, sparse, low-rank [58], or more specifically, pruning the least useful connections in a network [37, 113], weight quantization [17, 89], and model distillation [43].”
Background
Research works printed but not linked: 5
- Kawa D, Punyani S, Nayak P, Karkera A, Jyotinagar V (2019) Credit risk assessment from combined bank records using federated learning. International Research Journal of Engineering and Technology (IRJET) 6(4):1355–1358
- Mohri M, Sivek G, Suresh AT (2019) Agnostic federated learning. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International conference on machine learning, proceedings of machine learning research, vol 97. PMLR, Long Beach, pp 4615–4625
- Pathak M, Rane S, Raj B (2010) Multiparty differential privacy via aggregation of locally trained classifiers. In: Advances in neural information processing systems, pp 1876–1884
- Rehak D, Dodds P, Lannom L (2005) A model and infrastructure for federated learning content repositories. In: Interoperability of web-based educational systems workshop, vol 143. Citeseer
- Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. In: Advances in neural information processing systems, pp 4424–4434
Cited by
Sorted by citations
Items 301–400 of 1,496
Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation
Wu, Z., Sun, S., Wang, Y., Liu, M., Pan, Q., Zhang, J., Li, Z., & Liu, Q. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639369 · Cited by 39
“Owing to the advantages of protecting data privacy and boosting model accuracy, FL has been widely applied to a variety of applications, such as medical treatment [1], [2], financial risk management [3], and recommendation systems [4], [5].”
BackgroundHashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Qiu, P., Zhang, X., Ji, S., Fu, C., Yang, X., & Wang, T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3356164 · Cited by 34
“Vertical federated learning (VFL) [12], [13], [14], [15] is a trending paradigm that addresses a common dilemma faced by companies that share the same user group but differ in the features.”
BackgroundA federated recommendation algorithm based on user clustering and meta-learning
Yu, E., Ye, Z., Zhang, Z., Qian, L., & Xie, M. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111483 · Cited by 32
Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges
Aouedi, O., Sacco, A., Khan, L. U., Nguyen, D. C., & Guizani, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3484228 · Cited by 42
“Reference [15] offers a review of the main structures of FL models and only briefly introduces the application of FL in the field of health informatics.”
Hemdan, E. E., & Sayed, A. (2025) · Algorithms · doi:10.3390/a18070401 · Cited by 45
Almogadwy, B. S., & Alqarafi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-06574-w · Cited by 29
Shah, S. T., Ali, Z., Waqar, M., & Kim, A. (2025) · Healthcare · doi:10.3390/healthcare13212760 · Cited by 41
Current status and future developments in predicting outcomes in radiation oncology
Niraula, D., Cui, S., Pakela, J. M., Wei, L., Luo, Y., Haken, R. K. T., & Naqa, I. E. (2022) · British Journal of Radiology · doi:10.1259/bjr.20220239 · Cited by 29
Nair, D. G., Nair, J. J., Reddy, K. J., & Narayana, C. V. A. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105476 · Cited by 32
An Elderly Fall Detection Method Based on Federated Learning and Extreme Learning Machine (Fed-ELM)
Yu, Z., Liu, J., Yang, M., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3229044 · Cited by 29
“Eduardo et al [26] used Convolutional Neural Network (CNN) to detect falls and analyzed its performance at different sampling frequencies and various locations.”
BackgroundMethodDecentralized Machine Learning Training: A Survey on Synchronization, Consolidation, and Topologies
Khan, Q. W., Khan, A. N., Rizwan, A., Ahmad, R., Khan, S., & Kim, D. (2023) · IEEE Access · doi:10.1109/access.2023.3284976 · Cited by 32
Modeling global distribution for federated learning with label distribution skew
Sheng, T., Shen, C., Liu, Y., Ou, Y., Qu, Z., Liang, Y., & Wang, J. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109724 · Cited by 32
DPFLA: Defending Private Federated Learning Against Poisoning Attacks
Feng, X., Cheng, W., Cao, C., Wang, L., & Sheng, V. S. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3376255 · Cited by 29
“It can be applied to a wide range of applications [1], such as e-health [2], finance [3], autonomous driving [4], smart cities [5] and more.”
BackgroundFederated learning-based natural language processing: a systematic literature review
Khan, Y., Sánchez, D., & Domingo‐Ferrer, J. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10970-5 · Cited by 35
Federated Learning in Healthcare: A Privacy Preserving Approach
Narmadha, K., & Varalakshmi, P. (2022) · Studies in health technology and informatics · doi:10.3233/shti220436 · Cited by 31
Li, W., Hacid, H., Almazrouei, E., & Debbah, M. A. (2023) · AI · doi:10.3390/ai4030039 · Cited by 37
Jindal, V., Kukreja, V., Singh, D. P., et al. (2023) · doi:10.1109/aicera/icis59538.2023.10420360 · Cited by 28
Alzakari, S. A., Sarkar, A., Khan, M. Z., & Alhussan, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3420078 · Cited by 32
“Xu et al. [63] offered an overview of FL techniques, focusing specifically on their applicability in the field of biomedicine.”
BackgroundWang, F., Zhou, S., Hou, B., Santini, F., Yuan, L., Guo, Y., Zhu, J., Hilbert, T., Kober, T., Zhang, Y., et al. (2022) · European Radiology · doi:10.1007/s00330-022-09254-9 · Cited by 28
“However, by using federated learning [20], our MRI bilateral thigh muscle data were stored and analyzed by DL in situ in our medical center, while we only pooled the trained algorithm parameters— not the data— to the central server.”
MethodSelf-citationTyagi, P., & Bargavi, S. K. M. (2023) · International Journal of Data Informatics and Intelligent Computing · doi:10.59461/ijdiic.v2i1.42 · Cited by 28
Federated learning for diagnosis of age-related macular degeneration
Gholami, S., Lim, J. I., Leng, T., Ong, S. S. Y., Thompson, A. C., & Alam, M. N. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1259017 · Cited by 32
“This traditional method accumulates data from diverse sources, collating them in a centralized server or location for the training of a machine learning (ML) model [Xu et al., 2021].”
MethodFedEYE: A scalable and flexible end-to-end federated learning platform for ophthalmology
Yan, B., Cao, D., Jiang, X., Chen, Y., Dai, W., Dong, F., Huang, W., Zhang, T., Gao, C., Chen, Q., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.100928 · Cited by 32
“Many studies have investigated the use of FL in medical sub-fields, 23–25 including lung cancer, 26–28 pneumonia, 29–31 kidney diseases, 32,33 and even intensive care unit mortality rate prediction.”
BackgroundDüsing, C., Cimiano, P., Rehberg, S., Scherer, C., Kaup, O., Köster, C., Hellmich, S., Herrmann, D., Meier, K. L., Claßen, S., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102982 · Cited by 26
B 2 SFL: A Bi-Level Blockchained Architecture for Secure Federated Learning-Based Traffic Prediction
Guo, H., Meese, C., Li, W., Shen, C.-C., & Nejad, M. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3318990 · Cited by 26
“Recently, Federated learning (FL) has shown promise in facilitating privacy-preserving and collaborative machine learning across multiple application domains (e.g., healthcare [2], Internet of Things (IoT) [3], and transportation [4]).”
BackgroundDigital healthcare systems in a federated learning perspective
Shafik, W. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13897-3.00001-1 · Cited by 27
Lovers, A. A. K., Däumer, M., Frasch, M. G., Ugwumadu, A. H. N., Warrick, P. A., Vullings, R., Pini, N., Tolladay, J., Petersen, O. B., Lederer, C., et al. (2025) · BJOG An International Journal of Obstetrics & Gynaecology · doi:10.1111/1471-0528.18097 · Cited by 31
“For example, serious adverse labour outcomes may be subject to litigation and, therefore, hospitals may prefer to withhold or restrict access to data associated with these cases [109, 110].”
Privacy considerations for sharing genomics data
Oestreich, M., Chen, D., Schultze, J. L., Fritz, M., & Becker, M. (2021) · EXCLI journal · doi:10.17179/excli2021-4002 · Cited by 25
“There have been isolated use cases in the health sector, such as FL for predictions based on electronic health records (Brisimi et al., 2018; Xu et al., 2021), medical images (Sheller et al.”
BackgroundMethodArtificial intelligence and imaging for risk prediction of pancreatic cancer: a narrative review
Qureshi, T. A., Javed, S., Sarmadi, T., Pandol, S. J., & Li, D. (2022) · Chinese Clinical Oncology · doi:10.21037/cco-21-117 · Cited by 27
Guo, Y., He, Y., Lyu, J., Zhou, Z., Yang, D., Ma, L., Tan, H., Chen, C., Zhang, W., Hu, J., et al. (2022) · The Lancet Digital Health · doi:10.1016/s2589-7500(22)00090-5 · Cited by 29
Field, M., Thwaites, D., Carolan, M., Delaney, G. P., Lehmann, J., Sykes, J., Vinod, S. K., & Holloway, L. C. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104181 · Cited by 29
FLICU: A Federated Learning Workflow for Intensive Care Unit Mortality Prediction
Mondrejevski, L., Miliou, I., Montanino, A., Pitts, D., Hollmén, J., & Papapetrou, P. (2022) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms55023.2022.00013 · Cited by 31
“An additional advantage of FL is its capability to be seamlessly integrated with existing electronic healthcare systems storing valuable data, like Electronic Health Records (EHRs) [7], [8].”
BackgroundA Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction
Falco, I. D., Cioppa, A. D., Koutný, T., Úbl, M., Krčma, M., Scafuri, U., & Tarantino, E. (2023) · Sensors · doi:10.3390/s23062957 · Cited by 30
Gahlan, N., & Sethia, D. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19467-3 · Cited by 34
Re-Fed+: A Better Replay Strategy for Federated Incremental Learning
Li, Y., Wang, H., Qi, Y., Liu, W., & Li, R. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3551732 · Cited by 30
“Recently,FLhasattracted growingattentionandhasbeenappliedinvariousareassuchas recommendationsystems[4],[5]andsmarthealthcare[6],[7].”
Jatain, D., Sıngh, V., & Dahiya, N. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.05.016 · Cited by 25
“However, many works have focussed on the statistical challenges, system challenges and privacy issues with respect to the application of federated learning to healthcare sector (Xu et al., 2020).”
Federated Reinforcement Learning-Supported IDS for IoT-steered Healthcare Systems
Otoum, S., Guizani, N., & Mouftah, H. T. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500698 · Cited by 25
“Xu [11] et. al. takes on the challenge of reviewing all the ways that federated learning is beneficial when it comes to health care informatics.”
BackgroundFederated Learning via Conditional Mutual Learning for Alzheimer’s Disease Classification on T1w MRI
Huang, Y., Yang, H.-C., & Lee, C.-C. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630382 · Cited by 27
“Federated Learning (FL) is a learning paradigm that holds great promise on distributed learning by training the algorithm collaboratively across sites without exchanging the data itself [3].”
BackgroundBenchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data
Salmeron, J. L., Arévalo, I., & Celma, A. R. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e16925 · Cited by 26
“[30] provide an overview of the common solutions to address statistical challenges, system challenges, and privacy issues in federated learning.”
BackgroundFedLC: Optimizing Federated Learning in Non-IID Data via Label-Wise Clustering
Lee, H., & Seo, D. (2023) · IEEE Access · doi:10.1109/access.2023.3271517 · Cited by 31
“…was suggested as a viable methodology that effectively encompasses the geographically dispersed and independently trained local neural network models, widely being applied in distributed processing fields such as in healthcare [4], [5], IoT [6], [7], [8], security [9], [10], and data mining [11].”
BackgroundBi, X., Gupta, A., & Yang, M. (2023) · Management Science · doi:10.1287/mnsc.2023.00611 · Cited by 25
SR-FDIL: Synergistic Replay for Federated Domain-Incremental Learning
Li, Y., Xu, W., Qi, Y., Wang, H., Li, R., & Guo, S. (2024) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2024.3436874 · Cited by 27
“…at-tracted growing attention and applied to various fields such as collaborative inferring [4] and distributed advertising, smart healthcare [5], [6], etc. Typical FL methods aim to learn highly accurate models by aggregating knowledge from multiple clients with fixed and static data, which…”
BackgroundFedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
Le, H. Q., Nguyen, M. N. H., Thwal, C. M., Qiao, Y., Zhang, C., & Hong, C. S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.107017 · Cited by 32
Landscape of machine learning evolution: privacy-preserving federated learning frameworks and tools
Nguyen, G., Díaz, J. S.-P., Calatrava, A., Berberi, L., Lytvyn, O., Kozlov, V. Y., Tran, V., Moltó, G., & García, Á. L. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-11036-2 · Cited by 32
“The preservation of privacy is almost ubiquitous in various disciplines of information technology, including, but not limited to, financial analysis (Cheng et al. 2020 ), cybersecu - rity (Nguyen et al. 2020 ), and bioinformatics (Xu et al. 2021 ).”
Simon, J., & Kapileswar, N. (2025) · International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) · doi:10.1109/icssas66150.2025.11080854 · Cited by 25
“However, these devices produce huge volumes of data that must be processed using a great deal of power and storage capacity [3].”
A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
Liu, Y., Zhang, L., Ge, N., & Li, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01973 · Cited by 45
“We have collected 11 reviews [3,5–14] related to FL. • The literatures [8–10] is biased towards specific areas, focusing on the statistical challenges, communication effi-ciency/stability issues, device/data heterogeneity issues, privacy and security issues, traceability and accountability in the…”
BackgroundAttention on Personalized Clinical Decision Support System: Federated Learning Approach
Thwal, C. M., Thar, K., Tun, Y. L., & Hong, C. S. (2021) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp51126.2021.00035 · Cited by 25
“Due to the heterogeneous and vulnerable properties, dealing with limited clinical data becomes a huge obstacle for big data analysis to facilitate precision medicine while developing better healthcare infrastructures [11].”
BackgroundMachine Learning for Predicting Rare Clinical Outcomes—Finding Needles in a Haystack
Wang, F. (2021) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.10738 · Cited by 25
Self-citationFedSPL: federated self-paced learning for privacy-preserving disease diagnosis
Wang, Q., & Zhou, Y. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab498 · Cited by 25
Collaborative training of medical artificial intelligence models with non-uniform labels
Arasteh, S. T., Isfort, P., Sähn, M.-J., Müller‐Franzes, G. A., Khader, F., Kather, J. N., Kuhl, C. K., Nebelung, S., & Truhn, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-33303-y · Cited by 26
The value of federated learning during and post-COVID-19
Qian, F., & Zhang, J. A. (2021) · International Journal for Quality in Health Care · doi:10.1093/intqhc/mzab010 · Cited by 22
“3 performance of ML models trained on centrally hosted datasets.(1, 3) It is worth mentioning that training ML models using centralized datasets confronts enormous challenges in healthcare applications due to stringent legal and administrative regulations, technical difficulties, and patient data privacy concerns.”
BackgroundWahab, H., Mehmood, I., Ugail, H., Ser, J. D., & Muhammad, K. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.10.007 · Cited by 23
Federated learning as a smart tool for research on infectious diseases
Zwiers, L. C., Grobbee, D. E., Uijl, A., & Ong, D. S. Y. (2024) · BMC Infectious Diseases · doi:10.1186/s12879-024-10230-5 · Cited by 24
“Healthcare data are therefore often fragmented, such that hospitals may only access the data collected in-house, and population registries cannot be shared across country borders [9].”
Federated learning for Healthcare 5.0: a comprehensive survey, taxonomy, challenges, and solutions
Amin, M., Ahmad, S., & Loh, W.-K. (2025) · Soft Computing · doi:10.1007/s00500-025-10508-z · Cited by 29
“Recently Xu et al. (2021b) rendered a comprehensive examination of FL tools, emphasizing implications in biomedicine.”
Sensitivity-Aware Differential Privacy for Federated Medical Imaging
Zheng, L., Cao, Y., Yoshikawa, M., Shen, Y., Rashed, E. A., Taura, K., Hanaoka, S., & Zhang, T. (2025) · Sensors · doi:10.3390/s25092847 · Cited by 35
“…which enables cross-institutional collaborative model training without the need for centralized storage or the exchange of sensitive data, has been widely applied to various medical tasks such as brain tumor classification [18], breast density classification [19], and COVID-19 detection [20].”
Enhancing healthcare data privacy and interoperability with federated learning
Akhmetov, A., Latif, Z., Tyler, B., & Yazıcı, A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2870 · Cited by 27
“Another article ( Xu et al., 2021 ) explains that FL can be an effective way of linking and analyzing private health data from different sources.”
Federated Learning: Issues in Medical Application
Yoo, J. H., Jeong, H., Lee, J., & Chung, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91387-8_1 · Cited by 26
“While medical experts can provide sufficient information during data preprocessing, such as labeling, segmentation, noise filtering, this cannot happen during the federated learning’s training process [58].”
BackgroundAdaptive Weight Aggregation in Federated Learning for Brain Tumor Segmentation
Khan, M. I., Jafaritadi, M., Alhoniemi, E. J., Kontio, E., & Khan, S. A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09002-8_40 · Cited by 25
Huang, C., Wang, L., & Han, X. G. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583874 · Cited by 25
“FL is a distributed AI paradigm that has been recognized as a promising solution in the field of intelligent healthcare [9, 47, 50].”
BackgroundA call for open data to develop mental health digital biomarkers
Adler, D. A., Wang, F., Mohr, D. C., Estrin, D., Livesey, C., & Choudhury, T. (2022) · BJPsych Open · doi:10.1192/bjo.2022.28 · Cited by 23
Self-citationAdvancing Pandemic Preparedness in Healthcare 5.0: A Survey of Federated Learning Applications
Alsamhi, S. H., Hawbani, A., Shvetsov, A. V., & Kumar, S. (2023) · Advances in Human-Computer Interaction · doi:10.1155/2023/9992393 · Cited by 25
Chai, Y., Liu, H., Zhu, H., Pan, Y., Zhou, A., Liu, H., Liu, J., & Qian, Y. (2024) · Information & Management · doi:10.1016/j.im.2024.103922 · Cited by 24
Federated Abnormal Heart Sound Detection with Weak to No Labels
Qiu, W., Quan, C., Yu, Y., Kara, E., Qian, K., Hu, B., Schuller, B. W., & Yamamoto, Y. (2024) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0152 · Cited by 25
Savoia, M., Prezioso, E., Mele, V., & Piccialli, F. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.07.014 · Cited by 27
Li, X., Gao, B., Qin, Q., Yao, P., Li, J., Zhao, H., Liu, C., Zhang, Q., Hao, Z., Li, Y., et al. (2025) · Nature Electronics · doi:10.1038/s41928-025-01390-6 · Cited by 23
Self-citationFeng, G., Weng, F., Lu, W. P., Xu, L., Zhu, W., Tan, M., & Weng, P. (2025) · International Journal of General Medicine · doi:10.2147/ijgm.s516247 · Cited by 31
FED-EHR: A Privacy-Preserving Federated Learning Framework for Decentralized Healthcare Analytics
Wani, R. U. Z., & Can, Ö. (2025) · Electronics · doi:10.3390/electronics14163261 · Cited by 26
Pfohl, S. R., Zhang, H., Xu, Y., Foryciarz, A., Ghassemi, M., & Shah, N. H. (2022) · Scientific Reports · doi:10.1038/s41598-022-07167-7 · Cited by 25
“In cases where it is of interest to increase the sample size, decentralized aggregation techniques [73] as well as large-scale pre-training and transfer learning [54, 55] may be effective.”
MethodMachine learning and deep learning in medicine and neuroimaging
Fernández, I. S., & Peters, J. M. (2023) · Annals of the Child Neurology Society · doi:10.1002/cns3.5 · Cited by 30
“65 Federated learning brings the code to the data rather than the data to the code.”
BackgroundInfluentialDu, J., Qin, N., Huang, D., Jia, X., & Zhang, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3328073 · Cited by 22
“Additionally, the difference in computational power across clients will lead to asynchronous aggregation, which will lessen the efficiency of global model aggregation [10].”
BackgroundFLOAT: Federated Learning Optimizations with Automated Tuning
Khan, A. F., Khan, A. A., Abdelmoniem, A. M., Fountain, S., Butt, A. R., & Anwar, A. (2024) · European Conference on Computer Systems · doi:10.1145/3627703.3650081 · Cited by 25
“Despite the promise of FL in privacy preservation and its successful applications in diverse fields such as consumer devices [24, 78], healthcare [19, 74, 82], finance [6, 47, 63], and manufacturing [31, 55, 88], we are faced with a number of challenges [30, 40] when utilizing FL in practice.”
BackgroundFederated learning for rare disease detection: a survey
Wang, J., & Ma, F. (2023) · Rare Disease and Orphan Drugs Journal · doi:10.20517/rdodj.2023.16 · Cited by 21
Elliptic Crypt With Secured Blockchain Assisted Federated Q-Learning Framework for Smart Healthcare
Gajendran, S., Muthusamy, R., Ravi, K., Chandraumakantham, O., & Marappan, S. (2024) · IEEE Access · doi:10.1109/access.2024.3381528 · Cited by 21
“The use of FL increases the security of the secret transfer through user authentication [14], [15] in SHS.”
BackgroundFederated attention consistent learning models for prostate cancer diagnosis and Gleason grading
Kong, F., Wang, X., Xiang, J., Yang, S., Wang, X., Yue, M., Zhang, J., Zhao, J., Han, X., Dong, Y., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.03.028 · Cited by 36
“The divergence between the training and test data distributions can substantially negatively impact model robustness [56].”
Self-citationA Comprehensive Survey on Federated Learning Applications in Computational Mental Healthcare
Vajrobol, V., Singh, S., Saxena, G. J., Pundir, A., Gaurav, A., Bansal, S., Attar, R. W., Rahman, M., & Gupta, B. B. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.056500 · Cited by 26
Decentralized big data mining: federated learning for clustering youth tobacco use in India
Haripriya, R., Khare, N., Pandey, M., & Biswas, S. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-01042-0 · Cited by 21
Haripriya, R., Khare, N., Pandey, M., & Biswas, S. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01169-8 · Cited by 32
Ryu, H., Lee, M., Kim, S.-H., Kim, J. H., & Yang, H.-J. (2025) · Healthcare · doi:10.3390/healthcare13212811 · Cited by 25
“Biosignals (e.g., electrocardiogram, ECG; photoplethysmography, PPG; phonocardiogram, PCG) and electronic health records (EHRs) often contain personally identifiable information (PII), underscoring the need for secure analytical frameworks [1,2].”
Decentralized Federated Learning Over Slotted ALOHA Wireless Mesh Networking
Salama, A., Stergioulis, A., Hayajneh, A. M., Zaidi, S. A. R., McLernon, D., & Robertson, I. D. (2023) · IEEE Access · doi:10.1109/access.2023.3246924 · Cited by 24
Low-Overhead Clustered Federated Learning for Personalized Stress Monitoring
Jiang, S., Firouzi, F., & Chakrabarty, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3299736 · Cited by 26
“Nowadays, the FL algorithm is essential in the biomedical field, especially in facilitating data sharing between hospitals [18].”
BackgroundMullie, L., Afilalo, J., Archambault, P. M., Bouchakri, R., Brown, K., Buckeridge, D. L., Cavayas, Y. A., Turgeon, A. F., Martineau, D., Lamontagne, F., et al. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad235 · Cited by 25
Saidi, R., Rahmany, I., Dhahri, S., & Moulahi, T. (2024) · IEEE Access · doi:10.1109/access.2024.3419084 · Cited by 24
“This approach ensures data privacy and security by keeping sensitive information on local devices and sharing only model updates for aggregation, addressing concerns about data confidentiality, especially in healthcare settings [41].”
Zhu, M.-Y., Zecchin, M., Park, S., Guo, C., Feng, C., & Simeone, O. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3358615 · Cited by 29
“Federated inference has applications in fields as diverse as distributed healthcare platforms [7], Internet-of-Things systems [8], and autonomous vehicle networks [9].”
BackgroundAdvanced Optimization Techniques for Federated Learning on Non-IID Data
Efthymiadis, F., Karras, A., Karras, C., & Sioutas, S. (2024) · Future Internet · doi:10.3390/fi16100370 · Cited by 20
“This method is particularly important in domains such as autonomous vehicles [8], traffic prediction and monitoring [9,10], healthcare [11–13], telecommunications [14,15], the Internet of Things (IoT), smart cities [16–18], industrial management [19–21], blockchain [22–24], and medical artificial…”
A vertical federation recommendation method based on clustering and latent factor model
Zhang, J., & Jiang, Y. (2021) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs53707.2021.9587935 · Cited by 20
Methods and Impact for Using Federated Learning to Collaborate on Clinical Research
Cheung, A. T. M., Nasir-Moin, M., Kwon, Y. J., Guan, J., Liu, C., Jiang, L. Y., Raimondo, C. D., Chotai, S., Chambless, L. B., Ahmad, H. S., et al. (2022) · Neurosurgery · doi:10.1227/neu.0000000000002198 · Cited by 22
Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients
Zaccone, R., Rizzardi, A., Caldarola, D., Ciccone, M., & Barbara Caputo, B. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956084 · Cited by 23
“Recent years have seen a growing interest in Federated Learning [14], [21], [40].”
BackgroundSTFL:Spatio-temporal Federated Learning for Vehicle Trajectory Prediction
Zhou, X., Ke, R., Cui, Z., Liu, Q., & Qian, W. (2022) · 2022 IEEE 2nd International Conference on Digital Twins and Parallel Intelligence (DTPI) · doi:10.1109/dtpi55838.2022.9998967 · Cited by 20
“At present, FL has been used in many fields, such as mobile keyboard prediction[2], Healthcare[3].etc. Feng et al.[4] proposed PMF and Li et al.[5] proposed STSAN using FL to predict human mobility.”
MethodFederated Learning for Medical Imaging Segmentation via Dynamic Aggregation on Non-IID Data Silos
Yang, L., He, J., Fu, Y., & Luo, Z. (2023) · Electronics · doi:10.3390/electronics12071687 · Cited by 24
Lam, S. C., Wynes, M. W., Connolly, C., Ashizawa, K., Atkar-Khattra, S., Belani, C. P., DiNatale, D., Henschke, C. I., Hochhegger, B., Jacomelli, C., et al. (2023) · Journal of Thoracic Oncology · doi:10.1016/j.jtho.2023.08.016 · Cited by 21
Automatic Layer Freezing for Communication Efficiency in Cross-Device Federated Learning
Malan, E., Peluso, V., Calimera, A., Macii, E., & Montuschi, P. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3309691 · Cited by 20
“In cross-silo FL, the participating clients are geo-distributed data centers belonging to multiple institutions or organizations (e.g., hospitals of the national health systems [6]).”
BackgroundA federated pedestrian trajectory prediction model with data privacy protection
Ni, R., Lu, Y., Yang, B., Yang, C., & Liu, X. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01239-5 · Cited by 22
“Federated learning has been applied in many fields [13], especially in medicine [20] for protecting patients’ privacy.”
zPROBE: Zero Peek Robustness Checks for Federated Learning
Ghodsi, Z., Javaheripi, M., Sheybani, N., Zhang, X., Huang, K., & Koushanfar, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00448 · Cited by 26
“This lack of privacy prohibits the use of FL in many machine learning applications that involve sensitive data such as healthcare information [31, 44] or financial transactions [45].”
BackgroundAdaptive Federated Learning via New Entropy Approach
Zheng, S., Yuan, W., Wang, X., & Duan, L. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3402080 · Cited by 22
“…Xuehe Wang , Member, IEEE , and Lingjie Duan , Senior Member, IEEE Abstract —Federated Learning (FL) has emerged as a prominent distributed machine learning framework that enables geographically discrete clients to train a global model collaboratively while preserving their privacy-sensitive data.”
BackgroundYin, Z., Wang, H., Chen, B., Zhang, X., Lin, X. S., Sun, H., Li, A., & Zhou, C. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112208 · Cited by 23
Mankowski, M. A., Bae, S., Strauss, A. T., Lonze, B. E., Orandi, B. J., Stewart, D. E., Massie, A. B., McAdams‐DeMarco, M., Oermann, E. K., Habal, M. V., et al. (2024) · American Journal of Transplantation · doi:10.1016/j.ajt.2024.11.008 · Cited by 19
Artificial intelligence, medications, pharmacogenomics, and ethics
Haga, S. B. (2024) · Pharmacogenomics · doi:10.1080/14622416.2024.2428587 · Cited by 25
Generative Artificial Intelligence in Medicine
Shanmugam, D., Agrawal, M., Movva, R., Chen, I. Y., Ghassemi, M., Jacobs, M. L., & Pierson, E. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095332 · Cited by 40
Federated learning model with dynamic scoring-based client selection for diabetes diagnosis
Ahmed, S., Kaiser, M. S., Chaki, S., Aloteibi, S., & Moni, M. A. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113662 · Cited by 23
A Comprehensive Review of EEG-Based Seizure Detection Techniques
Jebaraj, G. S., & Konguvel, E. (2025) · IEEE Access · doi:10.1109/access.2025.3578991 · Cited by 19
Mir, B. A., Abbas, S. R., & Lee, S. W. (2026) · Healthcare · doi:10.3390/healthcare14030306 · Cited by 42
“Changing from data centralization to model propagation, this architecture radically changes the data governance structure, improving privacy protection while still allowing the creation of reliable, a widely applicable AI models trained on variety of datasets [21].”
Metadata
- Authors
- Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F.
- Affiliations
- Weill Cornell Medicine (US)
- Icahn School of Medicine at Mount Sinai (US)
- United States Department of Defense (US)
- University of Florida (US)
- Corresponding author
- Wang, Fei
- Venue
- Journal of Healthcare Informatics Research
- Published
- 2020-11-12
- Volume
- 5
- Issue
- 1
- Pages
- 1-19
- ISSN
- 2509-4971 (ISSN-L)
- 2509-498X
- PMC
- PMC7659898
- OpenAlex
- W3100779497
- Cited by
- 1,542
- References
- 130
- Citations by year
- 2026: 239 · 2025: 366 · 2024: 314 · 2023: 278 · 2022: 204 · 2021: 111 · 2020: 29
- FWCI
- 61.09
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Journal of Healthcare Informatics Research (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1750326)
- National Institute on Aging (P30AG028740)
- Office of Naval Research (N00014-18-1-2585, N00014-18, N00014)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- federated learning, healthcare data privacy, electronic health records, data fragmentation, privacy-preserving machine learning, biomedical applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
