International Journal of Analog Integrated Circuits Review Article
Privacy-Preserving AI Framework for Secure Healthcare Data Sharing and Disease Prediction
Abstract
Healthcare organizations need to share knowledge across hospitals, laboratories, connected medical devices, and research systems, but direct pooling of patient records creates significant privacy, security, and governance concerns. This review presents a practical privacy-preserving artificial intelligence framework for collaborative healthcare data analysis and disease prediction without requiring routine transfer of raw patient records to a central repository. The framework combines local data preprocessing, distributed model training, protected model updates, secure aggregation, controlled model distribution, access management, and human-reviewed prediction. Privacy techniques such as differential privacy, homomorphic encryption, secure aggregation, and secure multiparty computation are discussed at a conceptual level, with emphasis on their different roles and trade-offs. The paper also highlights risks that remain even when data are decentralized, including information leakage from model updates, unauthorized access, poor device security, data imbalance, and inappropriate use of prediction outputs. Electrical and electronics engineering is connected to the framework through medical sensors, wearable devices, signal acquisition, edge controllers, secure hardware identity, encrypted gateways, and reliable communication of physiological measurements. A phased deployment process is proposed so that institutions can begin with local validation and privacy controls before moving to collaborative training and clinical decision support. The review concludes that privacy-preserving healthcare artificial intelligence should be treated as a layered system in which data minimization, cryptographic protection, trustworthy electronics, model validation, auditability, and human oversight work together.
Keywords
References (15)
- Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, Bakas S, Galtier MN, Landman BA, Maier-Hein K, Ourselin S. The future of digital health with federated learning. NPJ digital medicine. 2020 Sep 14;3(1):119.
- Kaissis GA, Makowski MR, Rückert D, Braren RF. Secure, privacy-preserving and federated machine learning in medical imaging. Nature machine intelligence. 2020 Jun;2(6):305-11.
- Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR, Bakas S. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Scientific reports. 2020 Jul 28;10(1):12598.
- Brisimi TS, Chen R, Mela T, Olshevsky A, Paschalidis IC, Shi W. Federated learning of predictive models from federated electronic health records. International journal of medical informatics. 2018 Apr 1;112:59-67.
- McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA. Communication-efficient learning of deep networks from decentralized data. InArtificial intelligence and statistics 2017 Apr 10 (pp. 1273-1282). Pmlr.
- Kairouz P, McMahan HB. Advances and open problems in federated learning. Foundations and trends in machine learning. 2021 Jun 23;14(1-2):1-210.
- Dwork C. Differential privacy. InInternational colloquium on automata, languages, and programming 2006 Jul 10 (pp. 1-12). Berlin, Heidelberg: Springer Berlin Heidelberg.
- Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L. Deep learning with differential privacy. InProceedings of the 2016 ACM SIGSAC conference on computer and communications security 2016 Oct 24 (pp. 308-318).
- Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage D, Segal A, Seth K. Practical secure aggregation for privacy-preserving machine learning. Inproceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security 2017 Oct 30 (pp. 1175-1191).
- Gilad-Bachrach R, Dowlin N, Laine K, Lauter K, Naehrig M, Wernsing J. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. InInternational conference on machine learning 2016 Jun 11 (pp. 201-210). PMLR.
- Shokri R, Stronati M, Song C, Shmatikov V. Membership inference attacks against machine learning models. In2017 IEEE symposium on security and privacy (SP) 2017 May 22 (pp. 3-18). IEEE.
- Zhu L, Liu Z, Han S. Deep leakage from gradients. Advances in neural information processing systems. 2019;32.
- Li T, Sahu AK, Talwalkar A, Smith V. Federated learning: Challenges, methods, and future directions. IEEE signal processing magazine. 2020 May 1;37(3):50-60..
- Gu X, Sabrina F, Fan Z, Sohail S. A review of privacy enhancement methods for federated learning in healthcare systems. International Journal of Environmental Research and Public Health. 2023 Aug 7;20(15):6539.
- Gentry C. Fully homomorphic encryption using ideal lattices. InProceedings of the forty-first annual ACM symposium on Theory of computing 2009 May 31 (pp. 169-178).