OIDPR: : Optimized insulin dosage via privacy‐preserving reinforcement learning
Abstract
The precision of insulin dosage is essential in the process of diabetes treatment. The fact is providing precise dosage is almost impossible for clinicians since blood sugar levels are dynamically affected by many factors. Even though some auxiliary dosing systems have been proposed, the required real‐time physical data about the health situation of diabetics is still hard to synchronize to the end‐devices instantly. The traditional personalized drug delivery frameworks for accurate dosing of insulin always collect and transmit medical data in cleartext, which raises privacy problems. In this article, we propose a framework for an optimized insulin dosage via privacy‐preserving reinforcement learning to diabetics (OIDPR). In OIDPR, both the additive secret sharing and edge computing are deployed to achieve data confidentiality and performance optimization. The medical data is divided into multiple secret shares uniformly at random for outsourcing and operating at the edge servers. During the computation task of reinforcement learning, data is encrypted and processed via our proposed additive secret sharing protocol, where the privacy is reserved by the efficient encryption mechanism and the secret sharing system only incurs little workload. We provide comprehensive theoretical analyses and experimental results that demonstrate the supervisor functionality and high performance of our framework.
Graphical Abstract
In this paper, we propose a lightweight Q‐Learning‐based additive secret sharing protocol that can be used in the privacy protection system of personal data of diabetics. The proposed additive secret sharing enables data encryption and decryption only need additive operations. It reduces the demand for computing power, guarantees efficiency and privacy protection in terms of practicality.
References
[1]
Cho N, Shaw J, Karuranga S, et al. IDF diabetes Atlas: global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes Res Clin Pract. 2018;138:271‐281.
[2]
Meneghini L, Doshi A, Gouet D, et al. Insulin degludec/liraglutide (IDegLira) maintains glycaemic control and improves clinical outcomes, regardless of pre‐trial insulin dose, in people with type 2 diabetes that is uncontrolled on basal insulin. Diabet Med. 2019;37(2): 267‐276.
[3]
Saria S. Individualized sepsis treatment using reinforcement learning. Nat Med. 2018;24(11):1641.
[4]
Balle B, Gascon A, Ohrimenko O, Raykova M, Schoppmann P, Troncoso C. Ppml'19: privacy preserving machine learning. Paper presented at: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security; 2019;2717‐2718.
[5]
Nordon G, Koren G, Shalev V, Kimelfeld B, Shalit U, Radinsky K. Building causal graphs from medical literature and electronic medical records. Paper presented at: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33; 2019;1102‐1109.
[6]
Zhu H, Liu X, Lu R, Li H. Efficient and privacy‐preserving online medical prediagnosis framework using nonlinear SVM. IEEE J Biomed Health Inf. 2016;21(3):838‐850.
[7]
Zhao P, Li J, Zeng F, Xiao F, Wang C, Jiang H. ILLIA: enabling k‐anonymity‐based privacy preserving against location injection attacks in continuous LBS queries. IEEE Internet Things J. 2018;5(2):1033‐1042.
[8]
Mehta BB, Rao UP. Improved l‐diversity: scalable anonymization approach for privacy preserving big data publishing. J King Saud Univ Comput Inf Sci. 2019.
[9]
Rajendran K, Jayabalan M, Rana ME. A study on k‐anonymity, l‐diversity, and t‐closeness techniques. IJCSNS. 2017;17(12):172.
[10]
Kocabas O, Soyata T. Towards privacy‐preserving medical cloud computing using homomorphic encryption. Paper presented at: Virtual and Mobile Healthcare: Breakthroughs in Research and Practice; 2020;93‐125; IGI Global.
[11]
Qin Z, Weng J, Cui Y, Ren K. Privacy‐preserving image processing in the cloud. IEEE Cloud Comput. 2018;5(2):48‐57.
[12]
Xu M, Wu J, Huang L, Zhou R, Wang T, Hu D. Network‐ wide traffic signal control based on the discovery of critical nodes and deep reinforcement learning. J Intell Transp Syst. 2020;24(1):1‐10.
[13]
Mooney SJ, Pejaver V. Big data in public health: terminology, machine learning, and privacy. Annu Rev Public Health. 2018;39:95‐112.
[14]
Jiang Y, Wang C, Wu Z, Du X, Wang S. Privacy‐preserving biomedical data dissemination via a hybrid approach. Paper presented at: AMIA Annual Symposium Proceedings, Vol. 2018, 2018; 1176; American Medical Informatics Association.
[15]
Bogdanov D, Laur S, Willemson J. Sharemind: a framework for fast privacy‐preserving computations. Paper presented at: European Symposium on Research in Computer Security; 2008;192‐206; Springer.
[16]
Lu H, Gu C, Luo F, Ding W, Liu X. Optimization of lightweight task offloading strategy for mobile edge computing based on deep reinforcement learning. Futur Gener Comput Syst. 2020;102:847‐861.
[17]
Lecuyer M, Atlidakis V, Geambasu R, Hsu D, Jana S. On the connection between differential privacy and adversarial robustness in machine learning. Statistics. 2018;1050:9.
[18]
Liu X, Deng R, Choo K‐KR, Yang Y. Privacy‐preserving reinforcement learning design for patient‐centric dynamic treatment regimes. IEEE Trans Emerg Top Comput. 2019;1‐1.
[19]
Plis K, Bunescu R, Marling C, Shubrook J, Schwartz F. A machine learning approach to predicting blood glucose levels for diabetes management. Paper presented at: Workshops at the Twenty‐Eighth AAAI Conference on Artificial Intelligence; 2014.
[20]
Iniesta R, Stahl D, McGuffin P. Machine learning, statistical learning and the future of biological research in psychiatry. Psychol Med. 2016;46(12):2455‐2465.
[21]
Gaweda AE, Muezzinoglu MK, Aronoff GR, Jacobs AA, Zurada JM, Brier ME. Individualization of pharmacological anemia management using reinforcement learning. Neural Netw. 2005;18(5‐6):826‐834.
[22]
Nemati S, Ghassemi MM, Clifford GD. Optimal medication dosing from suboptimal clinical examples: a deep reinforcement learning approach. Paper presented at: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016;2978‐2981; IEEE.
[23]
Yang Y, Zheng X, Guo W, Liu X, Chang V. Privacy‐preserving fusion of IoT and big data for e‐health. Futur Gener Comput Syst. 2018;86:1437‐1455.
[24]
Alfred R. The rise of machine learning for big data analytics. Paper presented at: 2016 2nd International Conference on Science in Information Technology (ICSITech); 2016;1; IEEE.
[25]
Yang Y, Zheng X, Guo W, Liu X, Chang V. Privacy‐preserving smart IoT‐based healthcare big data storage and self‐adaptive access control system. Inf Sci. 2019;479:567‐592.
[26]
Luo E, Bhuiyan MZA, Wang G, Rahman MA, Wu J, Atiquzzaman M. PrivacyProtector: privacy‐protected patient data collection in IoT‐based healthcare systems. IEEE Commun Mag. 2018;56(2):163‐168.
[27]
Yang Y, Zheng X, Tang C. Lightweight distributed secure data management system for health internet of things. J Netw Comput Appl. 2017;89:26‐37.
[28]
Liu X, Deng RH, Ding W, Lu R, Qin B. Privacy‐preserving outsourced calculation on floating point numbers. IEEE Trans Inf Foren Secur. 2016;11(11):2513‐2527.
[29]
Yang Y, Liu X, Deng R. Expressive query over outsourced encrypted data. Inf Sci. 2018;442:33‐53.
[30]
Yang J‐J, Li J‐Q, Niu Y. A hybrid solution for privacy preserving medical data sharing in the cloud environment. Futur Gener Comput Syst. 2015;43:74‐86.
[31]
Al Badawi AQA, Polyakov Y, Aung KMM, Veeravalli B, Rohloff K. Implementation and performance evaluation of RNS variants of the BFV homomorphic encryption scheme. IEEE Trans Emerg Top Comput. 2019;1‐1.
[32]
Watkins CJ, Dayan P. Q‐learning. Mach Learn. 1992;8(3‐4):279‐292.
[33]
Ma Z, Liu Y, Liu X, Ma J, Ren K. Lightweight privacy‐preserving ensemble classification for face recognition. IEEE Internet Things J. 2019;6(3):5778‐5790.
[34]
Paverd A, Martin A, Brown I. Modelling and automatically analysing privacy properties for honest‐but‐curious adversaries; University of Oxford, Technical Report; 2014.
[35]
Damgaard I, Fitzi M, Kiltz E, Nielsen JB, Toft T. Unconditionally secure constant‐rounds multi‐party computation for equality, comparison, bits and exponentiation. Paper presented at: Theory of Cryptography Conference; 2006;285‐304; Springer.
[36]
Beaver D. Efficient multiparty protocols using circuit randomization. Paper presented at: Annual International Cryptology Conference; 1991;420‐432; Springer.
[37]
Bogdanov D, Niitsoo M, Toft T, Willemson J. High‐performance secure multi‐party computation for data mining applications. Int J Inf Secur. 2012;11(6):403‐418.
Index Terms
- OIDPR: Optimized insulin dosage via privacy‐preserving reinforcement learning
Index terms have been assigned to the content through auto-classification.
Recommendations
Identification of Major Adverse Kidney Events Within the Electronic Health Record
AbstractAcute kidney injury is common among critically ill adults and is associated with increased mortality and morbidity. The Major Adverse Kidney Events by 30 days (MAKE30) composite of death, new renal replacement therapy, or persistent renal ...
Automated detection of medication administration errors in neonatal intensive care
Display Omitted We developed computerized algorithms to detect medication administration errors.We defined administration error rates for high-risk medications using the algorithms.Compared to incident reporting, the algorithms had better sensitivity ...
The effect of medication therapy management service combined with a national PharmaCloud system for polypharmacy patients
The study built up a new model by using Taiwan National Health Insurance Administration PharmaCloud system to facilitate medication reconciliation for pharmacists in the medication therapy management service.The model improved the patients' attitude and ...
Comments
Information & Contributors
Information
Published In
© 2020 John Wiley & Sons, Ltd.
Publisher
John Wiley & Sons, Inc.
United States
Publication History
Published: 07 May 2021
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 30 Aug 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in