The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Federated learning of predictive models from federated Electronic Health Records
Open accessAbstract
Background In an era of "big data," computationally efficient and privacy-aware solutions for large-scale machine learning problems become crucial, especially in the healthcare domain, where large amounts of data are stored in different locations and owned by different entities. Past research has been focused on centralized algorithms, which assume the existence of a central data repository (database) which stores and can process the data from all participants. Such an architecture, however, can be impractical when data are not centrally located, it does not scale well to very large datasets, and introduces single-point of failure risks which could compromise the integrity and privacy of the data. Given scores of data widely spread across hospitals/individuals, a decentralized computationally scalable methodology is very much in need.Objective We aim at solving a binary supervised classification problem to predict hospitalizations for cardiac events using a distributed algorithm. We seek to develop a general decentralized optimization framework enabling multiple data holders to collaborate and converge to a common predictive model, without explicitly exchanging raw data.Methods We focus on the soft-margin l 1-regularized sparse Support Vector Machine (sSVM) classifier. We develop an iterative cluster Primal Dual Splitting (cPDS) algorithm for solving the large-scale sSVM problem in a decentralized fashion. Such a distributed learning scheme is relevant for multi-institutional collaborations or peer-to-peer applications, allowing the data holders to collaborate, while keeping every participant's data private.Results We test cPDS on the problem of predicting hospitalizations due to heart diseases within a calendar year based on information in the patients Electronic Health Records prior to that year. cPDS converges faster than centralized methods at the cost of some communication between agents. It also converges faster and with less communication overhead compared to an alternative distributed algorithm. In both cases, it achieves similar prediction accuracy measured by the Area Under the Receiver Operating Characteristic Curve (AUC) of the classifier. We extract important features discovered by the algorithm that are predictive of future hospitalizations, thus providing a way to interpret the classification results and inform prevention efforts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source doesn’t support the claim as written.
In the citing paper
“A similar scheme is used by Xie et al. [485] to design a variant of local SGD in which clients locally perform Adagrad [335, 161].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [485]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing 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].”
From Federated Learning for Healthcare Informatics (2021) · cites this paper as [10]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In the context of electronic health records (EHR), for example, FL helps to represent and to find clinically similar patients13,47, as well as predicting hospitalisations due to cardiac events14, mortality and ICU stay time19.”
From The future of digital health with federated learning (2020) · cites this paper as [14]
In the citing paper
“Governance of data for FL is maintained locally, alleviating privacy concerns, with only model weights or gradients communicated between the client-sites and the federated server38,39.”
From Federated learning for predicting clinical outcomes in patients with COVID-19 (2021) · cites this paper as [39]
In the citing paper
“For example, FL can be used to improve the perceiving and learning ability of AIoT devices such as connected vehicles for autonomous driving [199] and wearable devices for health monitoring [222], [197].”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [222]
In the citing paper
“The FL algorithm is used to describe and identify physician-related persons and to estimate their hospitalization, deaths, and survival rates based on electronic health records (EHR) [54].”
From A comprehensive survey on federated learning techniques for healthcare informatics (2023) · cites this paper as [54]
In the citing paper
“Deep Leakage from Gradients (DLG) [152] obtained the private training data at the inference phase.”
From Challenges, Applications and Design Aspects of Federated Learning: A Survey (2021) · cites this paper as [152]
In the citing paper
“The theoretical and experimental comparisons show that the proposed model converges faster and with less communication overhead compared to an alternative distributed algorithm.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [35]
In the citing paper
“Furthermore, an FL-based approach is proposed in [81] to predict hospitalizations for patients diagnosed with heart diseases using their historic EHRs.”
From Federated learning for smart healthcare: A survey (2023) · cites this paper as [81]
In the citing paper
“In addition, Brisimi et al., (2018) also use EMRs to evaluate whether a patient with heart disease will be hospitalized based on a FL algorithm called cluster Primal Dual Splitting (cPDS).”
From A review of applications in federated learning (2020) · cites this paper as Brisimi et al., (2018)
In the citing paper
“Brisimi et al. 2018 Predict future hospitalizations for patients Cluster Primal Dual Splitting algorithm Yield classifiers using relatively few features Need more iterations for convergence”
From A review of applications in federated learning (2020) · cites this paper as Brisimi et al. 2018
In the citing paper
“Brisimi et al. 2018 Predict future hospitalizations for patients Cluster Primal Dual Splitting algorithm Yield classifiers using relatively few features Need more iterations for convergence”
From A review of applications in federated learning (2020) · cites this paper as Brisimi et al. 2018
In the citing paper
“Brisimi et al. 2018 Predict future hospitalizations for patients Cluster Primal Dual Splitting algorithm Yield classifiers using relatively few features Need more iterations for convergence”
From A review of applications in federated learning (2020) · cites this paper as Brisimi et al. 2018
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565 · cited 2×
“We consider SVMs because they are effective classifiers [14] and perform well in predicting hospitalizations.”
MethodSmith, D. K., & Bertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 12,385
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571 · cited 1×
“In particular, even though maintaining all data in a central location enables the implementation of anonymization measures (e.g., k-anonymity [13]), it introduces a single point of attack or failure and makes it possible for a data breach to expose identifiable data for many individuals.”
BackgroundGeneral Cardiovascular Risk Profile for Use in Primary Care: The Framingham Heart Study
D’Agostino, R. B., Vasan, R. S., Pencina, M. J., Wolf, P. A., Cobain, M., Massaro, J. M., & Kannel, W. B. (2008) · Circulation · doi:10.1161/circulationaha.107.699579 · Cited by 7,491
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557 · cited 1×
“[ 9–11] Two well-known examples of privacy breaches are the Netflix Prize and the Massachusetts Group Insurance Commission (GIC) medical records database.”
BackgroundA New Initiative on Precision Medicine
Collins, F. S., & Varmus, H. (2015) · New England Journal of Medicine · doi:10.1056/nejmp1500523 · Cited by 5,202
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Weik, M. H. (2000) · Springer eBooks · doi:10.1007/1-4020-0613-6_12436 · Cited by 2,700
Statistical Learning with Sparsity
Hastie, T. J., Tibshirani, R. J., & Wainwright, M. J. (2015) · Chapman & Hall/CRC eBooks · doi:10.1201/b18401 · Cited by 2,529
Research works printed but not linked: 1
- R. Chen, I.C. Paschalidis, Outlier Detection Using Distributionally Robust Optimization under the Wasserstein Metric, ArXiv Prepr. ArXiv170602412 (2017).
Cited by
Sorted by citations
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
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210
“Federated learning methods have been deployed in practice by major companies [5], [41] and play a critical role in supporting privacy-sensitive applications where training data are distributed at the edge [8], [19].”
MethodThe 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 in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565
“, to develop predictive models for diagnosis in health AI [25] and to foster collaboration across multiple hospitals [26] and Government agencies [27].”
BackgroundSheller, M. J., Edwards, B., Reina, G. A., Martin, J., Pati, S., Kotrotsou, A., Milchenko, M., Xu, W., Marcus, D., Colen, R. R., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-69250-1 · Cited by 1,646
“…we acknowledge that the synchronization used in this study (1 epoch per synchronization, i.e., federated round) may be insufficient for data such as electronic health records 28,29 and clinical notes, as well as genomics, where more variance might be present across international institutions.”
Metadata
- Authors
- Brisimi, T. S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I. C., & Shi, W.
- Affiliations
- Boston University (US)
- Massachusetts General Hospital (US)
- Corresponding author
- Paschalidis, Ioannis Ch.
- Venue
- International Journal of Medical Informatics
- Publisher
- Elsevier BV
- Published
- 2018-04
- Volume
- 112
- Pages
- 59-67
- ISSN
- 1386-5056 (ISSN-L)
- PMC
- PMC5836813
- OpenAlex
- W2783522756
- Cited by
- 997
- References
- 24
- Citations by year
- 2026: 118 · 2025: 159 · 2024: 146 · 2023: 167 · 2022: 156 · 2021: 151 · 2020: 74 · 2019: 20 · 2018: 5
- FWCI
- 35.18
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- International Journal of Medical Informatics (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Science Foundation (IIS-1724990, CNS-1645681, CCF-1527292, IIS-1237022)
- Boston University
- Army Research Office (W911NF-12-1-0390)
- National Institutes of Health (1UL1TR001430)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- federated learning, electronic health records, distributed optimization, sparse support vector machines, primal-dual splitting, binary classification, data privacy, multi-institutional collaboration, feature extraction, heart disease prevention
- MeSH terms
- Machine Learning, Algorithms, Hospitalization, Humans, ROC Curve, Databases, Factual, Electronic Health Records, Support Vector Machine
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.
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
