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.
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
“Multi-task learning (MTL) is a natural way to deal with the data drawn from different distributions. It directly captures relationships among non-IID and unbalanced data by leveraging the relatedness between them in comparison to learn a single global model.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Statistical Challenges 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.
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, FedAvg does not address the statistical challenge of strongly skewed data distributions.”
§ 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: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“Unfortunately, due to a myriad of reasons such as discrepant data schemes and privacy concerns, it is unlikely that data will eve be connected together in a single database to learn from all at once.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
hedgedconditional- 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.
In the paper
“Moreover, SMC protocols are usually computationally expensive even for the simplest problems, requiring iterated encryption/decryption and repeated communication between participants about some of the encrypted results [78].”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- 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: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
“In these scenarios, the performance of ML model will be significantly improved by the iterative improvements of learning from large and diverse medical data sets.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
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.
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, during federated model training process, the clients suffer from considerable overhead in communication and computation.”
§ 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: unclear — It is unclear why the paper says 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
“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, e.g., which clients’ absence might change the decision boundary of a classifier, etc.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
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.
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
“These improperly calibrated algorithms can arise due to a variety of reasons, such as differences in underlying access to care or low representation in training data.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
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.
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
“The setting of federated learning, where the model is trained locally without revealing the input data or the model’s output to any clients, prevents direct leakage while training or using the model.”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
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.
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
“While providing a huge amount of patient data for analysis, EHRs contain systemic and random biases overall and specific to hospitals that limit the generalizability of results.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
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.
In the paper
“However, the clients may infer some information about another client’s private dataset given the execution of f(w), or over the shared predictive model w [100].”
§ Federated Learning for Healthcare Informatics > Federated Learning > Privacy and Security
What the sources say
- 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
hedgedconditional- 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.
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
“It is clear that one way to alleviate the risk for such biased algorithms is the ability to learn from EHR data that is more representative of the global population and which goes beyond a single hospital or site.”
§ Federated Learning for Healthcare Informatics > Applications > Healthcare
boosteddirect- 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
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503
Federated learning on non-IID data: A survey
Zhu, H., Xu, J., Liu, S., & Jin, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.098 · Cited by 1,062
“Overviews of FL applications to IoT and edge devices [73, 56, 117], wireless networks [53], mobile devices [85], and healthcare [143] have also been reported.”
BackgroundSelf-citationFederated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. (2021) · Deakin Research Online (Deakin University) · Cited by 889
Federated learning for smart healthcare: A survey
Nguyen, D. C., Pham, Q.-V., Pathirana, P. N., Ding, M., Seneviratne, A., Lin, Z., Dobre, O., & Hwang, W.-J. (2023) · ACM Computing Surveys · doi:10.1145/3501296 · Cited by 827
“The work in [17] mainly discusses the FL architectures and models with a very brief introduction to the roles of FL in healthcare informatics.”
Background
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
