Balancing privacy and performance in healthcare: A federated learning framework for sensitive data

Fatima Tanveer; Faisal Iradat; Waseem Iqbal; Hatoon S. Alsagri; Haya Abdullah A. Alhakbani; Awais Ahmad; Fakhri Alam Khan

doi:10.1177/20552076251381769

Balancing privacy and performance in healthcare: A federated learning framework for sensitive data

Fatima Tanveer, Faisal Iradat, Waseem Iqbal, Hatoon S. Alsagri, Haya Abdullah A. Alhakbani, Awais Ahmad^*, Fakhri Alam Khan

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Objective: To design and evaluate a privacy-preserving federated learning (PPFL) framework for sensitive healthcare data, balancing robust privacy, model performance, and computational efficiency, while promoting user trust. Methods: We integrated differentially private stochastic gradient descent (DPSGD) into a federated learning (FL) pipeline and evaluated the system on the Stroke Prediction Dataset. Experiments measured model utility (accuracy, F1), privacy (ε), resource usage, and trust features, with results compared to recent baselines. Results: The proposed framework achieved 93% accuracy on stroke risk prediction while maintaining a final privacy budget of ε 0.69 and minimal computational overhead. Our approach outperformed existing methods in privacy-utility trade-off, provided real-time privacy feedback, and is compliant with TRIPOD-AI/CLAIM recommendations. Conclusion: This PPFL framework enables effective, trustworthy privacy-preserving ML in healthcare and resource-constrained settings. Future work will extend model architectures, regulatory alignment, and direct user trust assessment.

Original language	English
Article number	20552076251381769
Journal	Digital Health
Volume	11
DOIs	https://doi.org/10.1177/20552076251381769
State	Published - 1 Jan 2025

Bibliographical note

Publisher Copyright:
© The Author(s) 2025. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access page (https://us.sagepub.com/en-us/nam/open-access-at-sage).

Keywords

Federated learning
computational efficiency
decentralized AI
differential privacy
healthcare data
privacy-preserving machine learning
user trust

ASJC Scopus subject areas

Health Policy
Health Informatics
Computer Science Applications
Health Information Management

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1177/20552076251381769

Cite this

@article{b0cd183b633241f78f8d295abf70561b,

title = "Balancing privacy and performance in healthcare: A federated learning framework for sensitive data",

abstract = "Objective: To design and evaluate a privacy-preserving federated learning (PPFL) framework for sensitive healthcare data, balancing robust privacy, model performance, and computational efficiency, while promoting user trust. Methods: We integrated differentially private stochastic gradient descent (DPSGD) into a federated learning (FL) pipeline and evaluated the system on the Stroke Prediction Dataset. Experiments measured model utility (accuracy, F1), privacy (ε), resource usage, and trust features, with results compared to recent baselines. Results: The proposed framework achieved 93\% accuracy on stroke risk prediction while maintaining a final privacy budget of ε 0.69 and minimal computational overhead. Our approach outperformed existing methods in privacy-utility trade-off, provided real-time privacy feedback, and is compliant with TRIPOD-AI/CLAIM recommendations. Conclusion: This PPFL framework enables effective, trustworthy privacy-preserving ML in healthcare and resource-constrained settings. Future work will extend model architectures, regulatory alignment, and direct user trust assessment.",

keywords = "Federated learning, computational efficiency, decentralized AI, differential privacy, healthcare data, privacy-preserving machine learning, user trust",

author = "Fatima Tanveer and Faisal Iradat and Waseem Iqbal and Alsagri, \{Hatoon S.\} and Alhakbani, \{Haya Abdullah A.\} and Awais Ahmad and Khan, \{Fakhri Alam\}",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access page (https://us.sagepub.com/en-us/nam/open-access-at-sage).",

year = "2025",

month = jan,

day = "1",

doi = "10.1177/20552076251381769",

language = "English",

volume = "11",

journal = "Digital Health",

issn = "2055-2076",

publisher = "SAGE Publications Inc.",

}

TY - JOUR

T1 - Balancing privacy and performance in healthcare

T2 - A federated learning framework for sensitive data

AU - Tanveer, Fatima

AU - Iradat, Faisal

AU - Iqbal, Waseem

AU - Alsagri, Hatoon S.

AU - Alhakbani, Haya Abdullah A.

AU - Ahmad, Awais

AU - Khan, Fakhri Alam

N1 - Publisher Copyright: © The Author(s) 2025. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access page (https://us.sagepub.com/en-us/nam/open-access-at-sage).

PY - 2025/1/1

Y1 - 2025/1/1

N2 - Objective: To design and evaluate a privacy-preserving federated learning (PPFL) framework for sensitive healthcare data, balancing robust privacy, model performance, and computational efficiency, while promoting user trust. Methods: We integrated differentially private stochastic gradient descent (DPSGD) into a federated learning (FL) pipeline and evaluated the system on the Stroke Prediction Dataset. Experiments measured model utility (accuracy, F1), privacy (ε), resource usage, and trust features, with results compared to recent baselines. Results: The proposed framework achieved 93% accuracy on stroke risk prediction while maintaining a final privacy budget of ε 0.69 and minimal computational overhead. Our approach outperformed existing methods in privacy-utility trade-off, provided real-time privacy feedback, and is compliant with TRIPOD-AI/CLAIM recommendations. Conclusion: This PPFL framework enables effective, trustworthy privacy-preserving ML in healthcare and resource-constrained settings. Future work will extend model architectures, regulatory alignment, and direct user trust assessment.

AB - Objective: To design and evaluate a privacy-preserving federated learning (PPFL) framework for sensitive healthcare data, balancing robust privacy, model performance, and computational efficiency, while promoting user trust. Methods: We integrated differentially private stochastic gradient descent (DPSGD) into a federated learning (FL) pipeline and evaluated the system on the Stroke Prediction Dataset. Experiments measured model utility (accuracy, F1), privacy (ε), resource usage, and trust features, with results compared to recent baselines. Results: The proposed framework achieved 93% accuracy on stroke risk prediction while maintaining a final privacy budget of ε 0.69 and minimal computational overhead. Our approach outperformed existing methods in privacy-utility trade-off, provided real-time privacy feedback, and is compliant with TRIPOD-AI/CLAIM recommendations. Conclusion: This PPFL framework enables effective, trustworthy privacy-preserving ML in healthcare and resource-constrained settings. Future work will extend model architectures, regulatory alignment, and direct user trust assessment.

KW - Federated learning

KW - computational efficiency

KW - decentralized AI

KW - differential privacy

KW - healthcare data

KW - privacy-preserving machine learning

KW - user trust

UR - https://www.scopus.com/pages/publications/105017314887

U2 - 10.1177/20552076251381769

DO - 10.1177/20552076251381769

M3 - Article

AN - SCOPUS:105017314887

SN - 2055-2076

VL - 11

JO - Digital Health

JF - Digital Health

M1 - 20552076251381769

ER -

Balancing privacy and performance in healthcare: A federated learning framework for sensitive data

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this