The DOI matches its Crossref record; 123 of the 127 references it cites were found in a registry or an index; 53 of the 137 sources its claims cite were checked for support.
Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration
Open accessAbstract
Federated learning (FL) is revolutionizing healthcare by enabling collaborative machine learning across institutions while preserving patient privacy and meeting regulatory standards. This review delves into FL’s applications within smart health systems, particularly its integration with IoT devices, wearables, and remote monitoring, which empower real-time, decentralized data processing for predictive analytics and personalized care. It addresses key challenges, including security risks like adversarial attacks, data poisoning, and model inversion. Additionally, it covers issues related to data heterogeneity, scalability, and system interoperability. Alongside these, the review highlights emerging privacy-preserving solutions, such as differential privacy and secure multiparty computation, as critical to overcoming FL’s limitations. Successfully addressing these hurdles is essential for enhancing FL’s efficiency, accuracy, and broader adoption in healthcare. Ultimately, FL offers transformative potential for secure, data-driven healthcare systems, promising improved patient outcomes, operational efficiency, and data sovereignty across the healthcare ecosystem.
Overview
CoChat Summary
## TL;DR
This is a systematic review of federated learning (FL) in smart healthcare, focusing on privacy, security, predictive analytics, and IoT integration. It argues that FL enables collaborative model training without sharing raw patient data, but adoption is constrained by heterogeneity, communication costs, and security threats such as poisoning and model inversion.
## Key findings
- FL is presented as a way to train models across hospitals, clinics, IoT devices, and wearables without centralizing raw data, supporting privacy and regulatory compliance with HIPAA and GDPR.
- The review highlights reported improvements from FL use cases, including a multi-hospital diabetes study where FL reportedly reduced data breach risk by 40% and improved predicted outcomes by 15% in EHR analysis, and disease prediction collaborations that improved model generalizability by 20%.
- In the text’s examples, FL-enabled remote monitoring with wearables reached 90% precision in detecting chronic diseases, and one cited breast tumor prediction approach improved local model precision by up to 20%.
- Security threats emphasized include adversarial attacks, data poisoning, and model inversion; the paper points to mitigation tools such as differential privacy, secure multiparty computation, homomorphic encryption, robust aggregation, and blockchain.
## Methods
- This is a systematic review covering studies published from 2023 to 2024 on FL in healthcare.
- The authors searched SpringerLink, PubMed, ScienceDirect, ACM Digital Library, and IEEE Xplore using healthcare/FL/IOT/privacy/security keyword combinations, then screened studies with title/abstract review followed by full-text review.
- Inclusion focused on peer-reviewed journal or conference papers on FL in smart health/healthcare and privacy/security techniques; analysis combined qualitative theme synthesis and a quantitative summary of metrics such as privacy loss, model accuracy, and computational cost.
## Limitations
- The paper states an English-only restriction and notes that this can cause selection bias and reduce the global scope of included studies.
- It also states that the fast-moving FL literature means some recent publications may not yet have been indexed, limiting comprehensiveness.
- Evident from the text: the review’s evidence base is limited to 2023–2024 studies, so older foundational work is largely outside scope.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures












Verification
Claims the paper makes
45 Valid · 8 Not valid · 75 Not checked · 46 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“The approach is also bandwidth-efficient, as only model updates need to be communicated, reducing the need for large data transfers [13].”
§ Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration > 1. Introduction > 1.2. Federated Learning
What the sources say
- Supportedcites [13] Zhang, 2022, Federated learning for the Internet of Things: Applications, challenges, and opportunities, IEEE Internet Things Mag. source
Section II (p. 1) says raw data stay on devices and only model updates are sent to the central server. Section II (p. 2) adds that avoiding transmission of raw IoT data reduces communication costs, especially on low-bandwidth networks. (LLM, conf=0.93)
plainstates a cause- 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
“For example, using sophisticated privacy-preserving techniques like differential privacy, a memory-aware curriculum FL strategy increased the precision of local models in breast tumor prediction by up to 20% while protecting patient information confidentiality [4].”
§ Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration > 1. Introduction > 1.1. Background and Motivation
What the sources say
- Partly supportedcites [4] Jiménez-Sánchez, A., Tardy, M., Ballester, M.A.G., Mateus, D., and Piella, G. (2023). Memory-aware curriculum federated learning for breast cancer classification. Comput. Methods Programs Biomed., 229. sourceExperimental — accuracy not yet measured
The paper says it uses differential privacy for data protection (section B), and Table III reports improved average precision–recall AUC for its federated method, from 0.77 to 0.82. It does not report a 20% increase in local-model precision. The Discussion also cautions that patient reidentification or information leakage cannot be ruled out, so the confidentiality claim is too strong. (LLM, conf=0.89)
plainstates a cause- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Early cancer diagnosis accuracy has been shown to significantly improve with FL.”
§ Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration > 1. Introduction > 1.1. Background and Motivation
What the sources say
- Partly supportedcites [4] Jiménez-Sánchez, A., Tardy, M., Ballester, M.A.G., Mateus, D., and Piella, G. (2023). Memory-aware curriculum federated learning for breast cancer classification. Comput. Methods Programs Biomed., 229. sourceExperimental — accuracy not yet measured
The Abstract reports improved breast-cancer classification metrics for the proposed method, and the results section (‘a)’, page not provided) says its improvement over other federated approaches was statistically significant. The source does not establish that federated learning generally improves early cancer diagnosis accuracy: it tests a specific breast-cancer classification method, primarily against other federated methods. (LLM, conf=0.88)
- Partly supportedcites [5] Hossain, M.M., Islam, M.R., Ahamed, M.F., Ahsan, M., and Haider, J. (2024). A Collaborative Federated Learning Framework for Lung and Colon Cancer Classifications. Technologies, 12. sourceExperimental — accuracy not yet measured
The Abstract reports high accuracy for federated classification of lung and colon cancer images and says the framework performed better than other approaches. It does not show that federated learning significantly improved the accuracy of early-stage cancer diagnosis; early diagnosis is discussed as a potential benefit in the Introduction, not evaluated as an outcome. (LLM, conf=0.86)
plainstates a cause- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“FL has seen notable applications in disease prediction and early diagnosis, particularly for situations requiring large, different datasets to train perfect models [41].”
§ Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration > 3. Overview of Federated Learning in Healthcare > 3.1. Key Applications of Federated Learning in Healthcare
What the sources say
- Partly supportedcites [41] Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., and Raad, A. (2023). Reviewing federated machine learning and its use in diseases prediction. Sensors, 23. sourceExperimental — accuracy not yet measured
Section 3.3 (Discussion) says FL can train disease-diagnosis models on large, distributed patient datasets from different facilities, and section 3.2 describes its use in disease prediction and detection. The citing sentence’s claim about training “perfect models” goes beyond the paper: section 3.3.1 says FL’s results are not yet sufficient to establish a performance advantage over conventional ML in disease prediction. (LLM, conf=0.88)
plainstates an association- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Using a variety of patient data from several institutions, FL has developed more broadly applicable models for predicting diseases like sepsis and acute kidney damage (AKI) in precision medicine.”
§ Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration > 3. Overview of Federated Learning in Healthcare > 3.4. Case Studies in Federated Learning for Healthcare
What the sources say
- Partly supportedcites [64] Rajendran, S., Xu, Z., Pan, W., Ghosh, A., and Wang, F. (2023). Data heterogeneity in federated learning with Electronic Health Records: Case studies of risk prediction for acute kidney injury and sepsis diseases in critical care. PLoS Digit. Health, 2. sourceExperimental — accuracy not yet measured
The Results report federated AKI and sepsis prediction models using patient data from seven hospitals, and the Discussion says they generally outperformed local models. But the Discussion cautions that data heterogeneity makes it difficult to justify a conclusion about generalizability, so the claim overstates how firmly the paper establishes that the models are more broadly applicable. (LLM, conf=0.86)
plainstates a cause- 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.
- Partly supported
64 more claims · 12 with their cited sources checked
Create a free account to see all 174 claims and to verify the 13 references still open.
- It may state two separate claims as one. 91
- Probably not a substantial claim. 27
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 check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Many studies on XAI in healthcare remain in the proof-of-concept stage or are only tested on retrospective datasets [34,35].”
From Explainable AI in Clinical Decision Support Systems: A Meta-Analysis of Methods, Applications, and Usability Challenges (2025) · cites this paper as [34]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Self-check results appear here once an independent check has confirmed them.
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“Sharafaddini, A.M., Esfahani, K.K., and Mansouri, N. (2024). Deep learning approaches to detect breast cancer: A comprehensive review. Multimed. Tools Appl., 1–112.”
Cited work 10.1007/s11042-024-20011-6 · retracted 2026-04-16 · notice 10.1007/s11042-026-21595-x · this paper published 2024-12-22
Citations
Cites
1 retracted
RETRACTED ARTICLE: Deep learning approaches to detect breast cancer: a comprehensive review
Sharafaddini, A. M., Esfahani, K. K., & Mansouri, N. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20011-6 · Cited by 104
RetractedFederated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734
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
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
Wang, J., Liu, Q., Liang, H., Joshi, G., & Poor, H. V. (2020) · arXiv · doi:10.48550/arxiv.2007.07481 · Cited by 927
Federated 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
Fairness in machine learning: A survey
Caton, S., & Haas, C. (2024) · ACM Computing Surveys · doi:10.1145/3616865 · Cited by 646
Fairness in Machine Learning: A Survey
Caton, S., & Haas, C. (2020) · arXiv · doi:10.48550/arxiv.2010.04053 · Cited by 646
Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges
Martínez Beltrán, E. T., Pérez, M. Q., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3315746 · Cited by 625
Research works printed but not linked: 5
- Shiwlani, 2024, Revolutionizing healthcare: The impact of artificial intelligence on patient care, diagnosis, and treatment, JURIHUM J. Inov. Dan Hum., 1, 779
- Thummisetti, 2024, Advancing healthcare informatics for empowering privacy and security through federated learning paradigms, Int. J. Sustain. Dev. Comput. Sci., 6, 1
- Heikkilä, M.A. (2024). On Joint Noise Scaling in Differentially Private Federated Learning with Multiple Local Steps. arXiv.
- Henry, 2024, AI-Driven Optimization in Healthcare: Machine Learning Models for Predictive Diagnostics and Personalized Treatment Strategies, Well Test. J., 33, 10
- Rehan, 2023, AI-Powered Genomic Analysis in the Cloud: Enhancing Precision Medicine and Ensuring Data Security in Biomedical Research, J. Deep Learn. Genom. Data Anal., 3, 37
Cited by
Abbas, Q., Jeong, W., & Lee, S. W. (2025) · Healthcare · doi:10.3390/healthcare13172154 · Cited by 236
“Many studies on XAI in healthcare remain in the proof-of-concept stage or are only tested on retrospective datasets [34,35].”
Self-citationA scoping review of the governance of federated learning in healthcare
Eden, R., Chukwudi, I., Bain, C., Barbieri, S., Callaway, L. K., de Jersey, S., George, Y., Gorse, A., Lawley, M., Marendy, P., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01836-3 · Cited by 112
“FL is revolutionising healthcare by enabling collaborative ML across institutions while preserving patient privacy 5,11,12 .”
Abdelwanis, M., Simsekler, M. C. E., Gabor, A. F., Sleptchenko, A., & Omar, M. (2025) · Safety Science · doi:10.1016/j.ssci.2025.107028 · Cited by 97
Ali, M., Ali, S., Abbas, Q., Abbas, Z., & Lee, S. (2025) · Digital Health · doi:10.1177/20552076251395548 · Cited by 109
“66 Behavioral activity monitoring.”
Self-citationCioboată, R., Bălteanu, M. A., Osman, A., Vlăsceanu, S. G., Zlatian, O. M., Mitroi, D. M., Catană, O. M., Socaci, A., & Țieranu, E. N. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14072154 · Cited by 42
Metadata
- Authors
- Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W.
- Affiliations
- COMSATS University Islamabad (PK)
- Sungkyunkwan University (KR)
- Corresponding author
- Lee, Seung Won
- Venue
- Healthcare
- Publisher
- MDPI AG
- Published
- 2024-12-22
- Volume
- 12
- Issue
- 24
- Pages
- 2587
- ISSN
- 2227-9032 (ISSN-L)
- PMC
- PMC11728217
- OpenAlex
- W4405701133
- Cited by
- 228
- References
- 127
- Citations by year
- 2026: 142 · 2025: 85 · 2024: 1
- FWCI
- 7.79
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Healthcare (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- SungKyunKwan University (NRF[2021-R1-I1A2(059735)], RS[2024-0040(5650)], RS[2024-0044(0881)], RS[2019- II19(0421)])
- Ministry of Education (NRF[2021-R1-I1A2(059735)], RS[2024-0040(5650)], RS[2024-0044(0881)], RS[2019- II19(0421)])
- National Research Foundation of Korea (NRF) (NRF[2021-R1-I1A2(059735)], RS[2024-0040(5650)], RS[2024-0044(0881)], RS[2019- II19(0421)])
- Ministry of Science and ICT (MSIT) (NRF[2021-R1-I1A2(059735)], RS[2024-0040(5650)], RS[2024-0044(0881)], RS[2019- II19(0421)])
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Keywords
- federated learning, smart healthcare, privacy-preserving machine learning, Internet of Medical Things, wearable devices, remote patient monitoring, predictive analytics, adversarial attacks, data poisoning, model inversion attacks, data heterogeneity, scalability, interoperability, differential privacy, secure multi-party computation, data sovereignty
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration. https://app.cochat.ai/papers/10.3390/healthcare12242587
- The paper
- Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W. (2024). Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration. Healthcare. https://doi.org/10.3390/healthcare12242587
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.