{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T14:39:05Z","timestamp":1792507145507,"version":"4.5.0"},"reference-count":71,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The development of robust medical AI for knowledge discovery and decision support commonly necessitates large-scale datasets from multiple institutions. However, such data aggregation is severely constrained by privacy regulations and the inherent risk of sensitive information leakage, making it difficult to navigate the utility-privacy trade-off.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We aimed to design a secure multiparty deep learning system that enables privacy-preserving modeling from distributed medical time-series data without centralizing raw information or exposing model parameters. Our goal was to achieve predictive accuracy comparable to nonsecure models while providing strong security and efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a framework using threshold homomorphic encryption to securely train recurrent neural networks on distributed longitudinal data. To improve the efficiency, we proposed an optimized encrypted matrix multiplication scheme, a secure ciphertext refresh protocol, and used lightweight encryption parameters and low-degree approximated activation polynomials. The system was evaluated on 4 real-world intensive care unit datasets for tasks like mortality and sepsis prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The system demonstrated practical efficiency, requiring approximately 1 minute per training iteration for processing 125 local batches over 39 variables and 48 time steps, and scaling well with data size and participant number. Securely trained models achieved predictive performance that was comparable to, and in some cases superior to, nonsecure centralized models, highlighting their ability to learn generalizable patterns in different unseen data distributions. For example, on the PhysioNet Challenge 2012 dataset, our secure model achieved an area under the curve (AUC) of 0.8480, outperforming the nonsecure baseline AUC of 0.8404.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This work provides a viable and efficient solution for cross-institutional, privacy-preserving analysis of longitudinal medical data. The framework successfully bridges the utility-privacy gap, facilitating safer collaborative research and enabling robust knowledge discovery and decision support while adhering to strict data protection standards.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/87306","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T20:28:21Z","timestamp":1786134501000},"page":"e87306-e87306","source":"Crossref","is-referenced-by-count":1,"title":["Privacy-Preserving Framework for Multi-Institutional Medical Time-Series Analysis via Homomorphic Encryption: Design and Development Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0713","authenticated-orcid":false,"given":"Yao","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6791-8217","authenticated-orcid":false,"given":"Yu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5858-6353","authenticated-orcid":false,"given":"Tianshu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5476-727X","authenticated-orcid":false,"given":"Jing","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1838-2919","authenticated-orcid":false,"given":"Zhensong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7183-7649","authenticated-orcid":false,"given":"Huiyao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9248-0157","authenticated-orcid":false,"given":"Kangli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1064-637X","authenticated-orcid":false,"given":"Jingsong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.1965","article-title":"Small data challenges of studying rare diseases","volume":"3","author":"Mitani","journal-title":"JAMA Netw Open"},{"issue":"7","key":"R2","doi-asserted-by":"publisher","first-page":"827","DOI":"10.3390\/healthcare9070827","article-title":"Sharing biomedical data: strengthening AI development in healthcare","volume":"9","author":"Pereira","journal-title":"Health Care (Don Mills)"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3332030","article-title":"Leveraging big data analytics for enhanced clinical decision-making in healthcare","volume":"11","author":"Hussain","journal-title":"IEEE Access"},{"issue":"10226","key":"R4","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/S0140-6736(19)32008-2","article-title":"Modifiable risk factors, cardiovascular disease, and mortality in 155\u2008722 individuals from 21 high-income, middle-income, and low-income countries (PURE): a prospective cohort study","volume":"395","author":"Yusuf","journal-title":"Lancet"},{"issue":"8","key":"R5","first-page":"96","volume":"10","author":"Hansen","journal-title":"Med Interface"},{"issue":"2","key":"R6","doi-asserted-by":"publisher","DOI":"10.2196\/25120","article-title":"Revolutionizing medical data sharing using advanced privacy-enhancing technologies: technical, legal, and ethical synthesis","volume":"23","author":"Scheibner","journal-title":"J Med Internet Res"},{"key":"R7","unstructured":"IBM report: escalating data breach disruption pushes costs to new highs. IBM Security. Jul 30, 2024. URL: https:\/\/newsroom.ibm.com\/2024-07-30-ibm-report-escalating-data-breach-disruption-pushes-costs-to-new-highs [Accessed 25-06-2026]"},{"key":"R8","doi-asserted-by":"crossref","unstructured":"Mehrabi S Sohn S Li D et al. Temporal pattern and association discovery of diagnosis codes using deep learning. In: 2015 International Conference on Healthcare Informatics. IEEE; 2015. [doi: 10.1109\/ICHI.2015.58]","DOI":"10.1109\/ICHI.2015.58"},{"key":"R9","volume":"56","author":"Choi","journal-title":"JMLR Workshop Conf Proc"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpbup.2022.100089","article-title":"Predicting the evolution of COVID-19 mortality risk: a recurrent neural network approach","volume":"3","author":"Villegas","journal-title":"Comput Methods Programs Biomed Update"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104165","article-title":"Dual-level diagnostic feature learning with recurrent neural networks for treatment sequence recommendation","volume":"134","author":"Min","journal-title":"J Biomed Inform"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/TIFS.2017.2787987","article-title":"Privacy-preserving deep learning via additively homomorphic encryption","volume":"13","author":"Phong","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","article-title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","volume":"3","author":"Kaissis","journal-title":"Nat Mach Intell"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Frigerio L de Oliveira AS Gomez L Duverger P . Differentially private generative adversarial networks for time series, continuous, and discrete open data. In: Dhillon G Karlsson F Hedstr\u00f6m K Z\u00faquete A , editors. 34th IFIP International Conference on ICT Systems Security and Privacy Protection. Springer; 2019. [doi: 10.1007\/978-3-030-22312-0_11]","DOI":"10.1007\/978-3-030-22312-0_11"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2021.107669","article-title":"Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks","volume":"137","author":"Fekri","journal-title":"Int J Electr Power Energy Syst"},{"issue":"8","key":"R16","doi-asserted-by":"publisher","first-page":"7751","DOI":"10.1109\/JIOT.2020.2991401","article-title":"Privacy-preserving traffic flow prediction: a federated learning approach","volume":"7","author":"Liu","journal-title":"IEEE Internet Things J"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Singh M Madhulika M Bansal S . A proposed federated learning model for vaccination tweets. In: Computational Intelligence in Pattern Recognition CIPR 2022. Springer; 2022. [doi: 10.1007\/978-981-19-3089-8_37]","DOI":"10.1007\/978-981-19-3089-8_37"},{"key":"R18","doi-asserted-by":"crossref","unstructured":"Gandhi N Mishra S Bharti SK Bhagat K . Leveraging towards privacy-preserving using federated machine learning for healthcare systems. In: 2021 IEEE International Conference on Electronics, Computing and Communication Technologies. IEEE; 2021. [doi: 10.1109\/CONECCT52877.2021.9622730]","DOI":"10.1109\/CONECCT52877.2021.9622730"},{"issue":"7862","key":"R19","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1038\/s41586-021-03583-3","article-title":"Swarm learning for decentralized and confidential clinical machine learning","volume":"594","author":"Warnat-Herresthal","journal-title":"Nature"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Nasr M Shokri R Houmansadr A . Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning. In: 2019 IEEE Symposium on Security and Privacy. IEEE; 2019. [doi: 10.1109\/SP.2019.00065]","DOI":"10.1109\/SP.2019.00065"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.007","article-title":"A survey on security and privacy of federated learning","volume":"115","author":"Mothukuri","journal-title":"Future Generation Computer Systems"},{"key":"R22","unstructured":"Kariyappa S Guo C Maeng K et al. Cocktail party attack: breaking aggregation-based privacy in federated learning using independent component analysis. In: Proceedings of the 40th International Conference on Machine Learning. MLR Press; 2023:15884-15899. URL: https:\/\/proceedings.mlr.press\/v202\/kariyappa23a\/kariyappa23a.pdf [Accessed 25-06-2026]"},{"key":"R23","unstructured":"McMahan HB Ramage D Talwar K Zhang L . Learning differentially private recurrent language models. Presented at: 6th International Conference on Learning Representations; Apr 30 to May 3, 2018; Vancouver, BC, Canada. URL: https:\/\/openreview.net\/pdf?id=BJ0hF1Z0b [Accessed 20-07-2026]"},{"issue":"8","key":"R24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3547139","article-title":"A critical review on the use (and misuse) of differential privacy in machine learning","volume":"55","author":"Blanco-Justicia","journal-title":"ACM Comput Surv"},{"key":"R25","unstructured":"Yue K Jin R Wong CW Baron D Dai H . Gradient obfuscation gives a false sense of security in federated learning. In: 32nd USENIX Security Symposium. USENIX Association; 2023. ISBN: 978-1-939133-37-3"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"68","DOI":"10.56553\/popets-2023-0005","article-title":"On the privacy risks of deploying recurrent neural networks in machine learning models","volume":"2023","author":"Yang","journal-title":"Proc Priv Enhanc Technol"},{"key":"R27","unstructured":"Jayaraman B Evans D . Evaluating differentially private machine learning in practice. In: 28th USENIX Security Symposium. USENIX Association; 2019. ISBN: 9781939133069"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Rathee D Rathee M Goli RKK et al. SiRnn: a math library for secure RNN inference. In: 2021 IEEE Symposium on Security and Privacy. IEEE; 2021. [doi: 10.1109\/SP40001.2021.00086]","DOI":"10.1109\/SP40001.2021.00086"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2997134","article-title":"SecureNLP: a system for multi-party privacy-preserving natural language processing","volume":"15","author":"Feng","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Podschwadt R Takabi D . Non-interactive privacy preserving recurrent neural network prediction with homomorphic encryption. In: 2021 IEEE 14th International Conference on Cloud Computing. IEEE; 2021. [doi: 10.1109\/CLOUD53861.2021.00019]","DOI":"10.1109\/CLOUD53861.2021.00019"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Tosevski V Gulak G . Large-scale recurrent neural networks with fully homomorphic encryption for privacy-enhanced speaker identification. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025). IEEE; 2025. [doi: 10.1109\/ICASSP49660.2025.10888434]","DOI":"10.1109\/ICASSP49660.2025.10888434"},{"key":"R32","doi-asserted-by":"crossref","unstructured":"Wang Z Ikeda M . High-throughput privacy-preserving GRU network with homomorphic encryption. In: 2023 International Joint Conference on Neural Networks (IJCNN). IEEE; 2023. [doi: 10.1109\/IJCNN54540.2023.10191194]","DOI":"10.1109\/IJCNN54540.2023.10191194"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Jang J Lee Y Kim A et al. Privacy-preserving deep sequential model with matrix homomorphic encryption. In: Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security. Association for Computing Machinery; 2022. [doi: 10.1145\/3488932.3523253]","DOI":"10.1145\/3488932.3523253"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Xie Q Guo H Wang W et al. HARMONY: a privacy-preserving and sensor-agnostic tele-monitoring system. In: Proceedings of the 34th International Joint Conference on Artificial Intelligence. ACM; 2025. [doi: 10.24963\/ijcai.2025\/1105]","DOI":"10.24963\/ijcai.2025\/1105"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3114581","article-title":"Privacy-preserving collective learning with homomorphic encryption","volume":"9","author":"Paul","journal-title":"IEEE Access"},{"issue":"4","key":"R36","doi-asserted-by":"publisher","first-page":"500","DOI":"10.56553\/popets-2023-0122","article-title":"Privacy-preserving federated recurrent neural networks","volume":"2023","author":"Sav","journal-title":"Proc Priv Enhanc Technol"},{"key":"R37","unstructured":"Guo Q Nabokov D Suvanto E Johansson T . Key recovery attacks on approximate homomorphic encryption with non-worst-case noise flooding countermeasures. In: 33rd USENIX Security Symposium. USENIX Association; 2024. URL: https:\/\/www.usenix.org\/conference\/usenixsecurity24\/presentation\/guo-qian [Accessed 23-07-2026] [doi: 10.5555\/3698900.3699316]"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Bergamaschi F Costache A Dachman-Soled D et al. Revisiting the security of approximate FHE with noise-flooding countermeasures. In: 28th IACR International Conference on Practice and Theory of Public-Key Cryptography. Springer; 2025. [doi: 10.1007\/978-3-031-91832-2_4]","DOI":"10.1007\/978-3-031-91832-2_4"},{"issue":"9","key":"R39","doi-asserted-by":"publisher","first-page":"3310","DOI":"10.1109\/JBHI.2021.3071270","article-title":"Multicenter privacy-preserving Cox analysis based on homomorphic encryption","volume":"25","author":"Lu","journal-title":"IEEE J Biomed Health Inform"},{"key":"R40","doi-asserted-by":"crossref","unstructured":"Li B Micciancio D Schultz-Wu M Sorrell J . Securing approximate homomorphic encryption using differential privacy. In: 42nd Annual International Cryptology Conference. Springer; 2022. [doi: 10.1007\/978-3-031-15802-5_20]","DOI":"10.1007\/978-3-031-15802-5_20"},{"key":"R41","unstructured":"Paverd A Martin A Brown I . Modelling and automatically analysing privacy properties for honest-but-curious adversaries. University of Oxford; 2014. URL: https:\/\/ajpaverd.org\/publications\/casper-privacy-report.pdf [Accessed 25-06-2026]"},{"key":"R42","unstructured":"Yu Z Liu G . Sliced recurrent neural networks. Presented at: Proceedings of the 27th International Conference on Computational Linguistics; Aug 20-26, 2018; Santa Fe, NM. URL: https:\/\/aclanthology.org\/C18-1250.pdf [Accessed 20-07-2026]"},{"issue":"1","key":"R43","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","journal-title":"Sci Data"},{"issue":"23","key":"R44","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet","volume":"101","author":"Goldberger","journal-title":"Circulation"},{"issue":"2","key":"R45","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1097\/CCM.0000000000004145","article-title":"Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge 2019","volume":"48","author":"Reyna","journal-title":"Crit Care Med"},{"key":"R46","volume":"216","author":"Hripcsak","journal-title":"Stud Health Technol Inform"},{"key":"R47","doi-asserted-by":"crossref","unstructured":"Cheon JH Choe H Passel\u00e8gue A Stehl\u00e9 D Suvanto E . Attacks against the IND-CPA\n                      D\n                      security of exact FHE schemes. In: Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery; 2024. [doi: 10.1145\/3658644.3690341]","DOI":"10.1145\/3658644.3690341"},{"key":"R48","doi-asserted-by":"crossref","unstructured":"Cheon JH Kim A Kim M Song Y . Homomorphic encryption for arithmetic of approximate numbers. In: 23rd International Conference on the Theory and Applications of Cryptology and Information Security. Springer; 2017. [doi: 10.1007\/978-3-319-70694-8_15]","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"R49","doi-asserted-by":"crossref","unstructured":"Akleylek S Da\u011fdelen \u00d6 Y\u00fcce Tok Z . On the efficiency of polynomial multiplication for lattice-based cryptography on GPUs using CUDA. In: 2nd International Conference on Cryptography and Information Security in the Balkans. Springer; 2016. [doi: 10.1007\/978-3-319-29172-7_10]","DOI":"10.1007\/978-3-319-29172-7_10"},{"key":"R50","doi-asserted-by":"crossref","unstructured":"Bajard JC Eynard J Hasan MA Zucca V . A full RNS variant of FV like somewhat homomorphic encryption schemes. In: 23rd International Conference on Selected Areas in Cryptography. Springer; 2017. [doi: 10.1007\/978-3-319-69453-5_23]","DOI":"10.1007\/978-3-319-69453-5_23"},{"issue":"1","key":"R51","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s10623-012-9720-4","article-title":"Fully homomorphic SIMD operations","volume":"71","author":"Smart","journal-title":"Des Codes Cryptogr"},{"key":"R52","doi-asserted-by":"crossref","unstructured":"Kim A Papadimitriou A Polyakov Y . Approximate homomorphic encryption with reduced approximation error. In: Cryptographers\u2019 Track at the RSA Conference 2022. Springer; 2022. [doi: 10.1007\/978-3-030-95312-6_6]","DOI":"10.1007\/978-3-030-95312-6_6"},{"key":"R53","doi-asserted-by":"crossref","unstructured":"Jiang X Kim M Lauter K Song Y . Secure outsourced matrix computation and application to neural networks. In: Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery; 2018. [doi: 10.1145\/3243734.3243837]","DOI":"10.1145\/3243734.3243837"},{"key":"R54","doi-asserted-by":"crossref","unstructured":"Rizomiliotis P Triakosia A . On matrix multiplication with homomorphic encryption. In: Proceedings of the 2022 on Cloud Computing Security Workshop. Association for Computing Machinery; 2022. [doi: 10.1145\/3560810.3564267]","DOI":"10.1145\/3560810.3564267"},{"key":"R55","unstructured":"Albrecht M Chase M Chen H et al. Homomorphic encryption standard. Nov 21, 2018. URL: http:\/\/homomorphicencryption.org\/wp-content\/uploads\/2018\/11\/HomomorphicEncryptionStandardv1.1.pdf [Accessed 25-06-2026]"},{"key":"R56","unstructured":"Microsoft SEAL (release 4.1). Microsoft Research. Jan 2023. URL: https:\/\/github.com\/Microsoft\/SEAL [Accessed 25-06-2026]"},{"issue":"S2","key":"R57","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1007\/s10462-023-10561-w","article-title":"Machine and deep learning for longitudinal biomedical data: a review of methods and applications","volume":"56","author":"Cascarano","journal-title":"Artif Intell Rev"},{"issue":"4","key":"R58","doi-asserted-by":"publisher","first-page":"291","DOI":"10.2478\/popets-2021-0071","article-title":"Multiparty homomorphic encryption from ring-learning-with-errors","volume":"2021","author":"Mouchet","journal-title":"Proc Priv Enhanc Technol"},{"issue":"4","key":"R59","doi-asserted-by":"publisher","first-page":"209","DOI":"10.56553\/popets-2024-0114","article-title":"Summation-based private segmented membership test from threshold-fully homomorphic encryption","volume":"2024","author":"Koirala","journal-title":"Proc Priv Enhanc Technol"},{"issue":"4","key":"R60","doi-asserted-by":"publisher","DOI":"10.62056\/ayl83z10k","article-title":"Application-aware approximate homomorphic encryption: configuring FHE for practical use","volume":"2","author":"Alexandru","journal-title":"IACR Commun Cryptol"},{"issue":"10","key":"R61","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1038\/s42256-025-01107-6","article-title":"Towards compute-efficient byzantine-robust federated learning with fully homomorphic encryption","volume":"7","author":"Jiang","journal-title":"Nat Mach Intell"},{"issue":"14","key":"R62","doi-asserted-by":"publisher","first-page":"24569","DOI":"10.1109\/JIOT.2024.3382875","article-title":"Efficiency optimization techniques in privacy-preserving federated learning with homomorphic encryption: a brief survey","volume":"11","author":"Xie","journal-title":"IEEE Internet Things J"},{"key":"R63","unstructured":"Papernot N Steinke T . Hyperparameter tuning with Renyi differential privacy. Presented at: International Conference on Learning Representations; Apr 25-29, 2022; Virtual Event. URL: https:\/\/openreview.net\/pdf?id=-70L8lpp9DF [Accessed 20-07-2026]"},{"key":"R64","volume":"5","author":"Kuo","journal-title":"Proc Mach Learn Syst"},{"key":"R65","volume":"34","author":"Khodak","journal-title":"Adv Neural Inf Process Syst"},{"key":"R66","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3188145","article-title":"Efficient homomorphic evaluation on large intervals","volume":"17","author":"Cheon","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"#cr-split#-R67.1","unstructured":"Silva I Moody G Mark R Celi LA . Predicting mortality of ICU patients: the PhysioNet\/Computing in Cardiology Challenge 2012 (version 1.0.0). PhysioNet"},{"key":"#cr-split#-R67.2","unstructured":"Jan 20, 2012. URL: https:\/\/physionet.org\/content\/challenge-2019\/1.0.0\/"},{"key":"#cr-split#-R68.1","doi-asserted-by":"crossref","unstructured":"Reyna M Josef C Jeter R et al. Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge 2019 (version 1.0.0). PhysioNet","DOI":"10.22489\/CinC.2019.412"},{"key":"#cr-split#-R68.2","unstructured":"Aug 5, 2019. [doi: 10.13026\/v64v-d857]"},{"key":"R69","unstructured":"Johnson A Pollard T Mark R . MIMIC-III Clinical Database (version 1.4). PhysioNet; Sep 4, 2016. [doi: 10.13026\/C2XW26]"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T20:28:27Z","timestamp":1786134507000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e87306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":71,"URL":"https:\/\/doi.org\/10.2196\/87306","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]},"article-number":"v10i3e87306"}}