2000 character limit reached
DP-RuL: Differentially-Private Rule Learning for Clinical Decision Support Systems
Published 15 May 2024 in cs.CR | (2405.09721v1)
Abstract: Serious privacy concerns arise with the use of patient data in rule-based clinical decision support systems (CDSS). The goal of a privacy-preserving CDSS is to learn a population ruleset from individual clients' local rulesets, while protecting the potentially sensitive information contained in the rulesets. We present the first work focused on this problem and develop a framework for learning population rulesets with local differential privacy (LDP), suitable for use within a distributed CDSS and other distributed settings. Our rule discovery protocol uses a Monte-Carlo Tree Search (MCTS) method integrated with LDP to search a rule grammar in a structured way and find rule structures clients are likely to have. Randomized response queries are sent to clients to determine promising paths to search within the rule grammar. In addition, we introduce an adaptive budget allocation method which dynamically determines how much privacy loss budget to use at each query, resulting in better privacy-utility trade-offs. We evaluate our approach using three clinical datasets and find that we are able to learn population rulesets with high coverage (breadth of rules) and clinical utility even at low privacy loss budgets.
- Specification-based monitoring of cyber-physical systems: a survey on theory, tools and applications. Lectures on Runtime Verification: Introductory and Advanced Topics 2018 (2018), 135–175.
- Survey on mining signal temporal logic specifications. Information and Computation 2022 (2022), 104957.
- The T1D Exchange clinic registry. The Journal of Clinical Endocrinology & Metabolism 97, 12 (2012), 4383–4389.
- Combining unsupervised, supervised and rule-based learning: the case of detecting patient allergies in electronic health records. BMC Medical Informatics and Decision Making 23, 1 (2023), 188.
- A survey of monte carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in games 4, 1 (2012), 1–43.
- Cynergistek Insights Center. 2019. Measuring Progress: Expanding the Horizon: 2019 Annual Report. Available: https://insights.cynergistek.com/reports/2019-healthcare-cybersecurity-privacy-report?utm_source=press_release&utm_medium=pr&utm_campaign=&utm_content=2019_report.
- Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries. arxiv 2016, 3 (2015), 41–61. https://doi.org/10.1515/popets-2016-0015 arXiv:1503.01214 Available: http://arxiv.org/abs/1503.01214.
- Sam Fletcher and Md Zahidul Islam. 2019. Decision tree classification with differential privacy: A survey. ACM Computing Surveys (CSUR) 52, 4 (2019), 1–33.
- Cosima Gretton. 2018. Trust and Transparency in Machine Learning-Based Clinical Decision Support. In Human and Machine Learning. Springer, USA, 279–292.
- Jinyuan Jia and Neil Zhenqiang Gong. 2019. Calibrate: Frequency estimation and heavy hitter identification with local differential privacy via incorporating prior knowledge. In IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, IEEE, USA, 2008–2016.
- What can we learn privately? SIAM J. Comput. 40, 3 (2011), 793–826.
- Taxonomy of Hybrid Architectures involving Rule-Based Reasoning and Machine Learning in Clinical Decision Systems: A Scoping Review. Journal of Biomedical Informatics 2023 (2023), 104428.
- Learning new words from keystroke data with local differential privacy. IEEE Transactions on Knowledge and Data Engineering 32, 3 (2018), 479–491.
- Levente Kocsis and Csaba Szepesvári. 2006. Bandit based monte-carlo planning. In European conference on machine learning. Springer, Springer, Europe, 282–293.
- A Logic-Based Learning Approach to Explore Diabetes Patient Behaviors. In International Conference on Computational Methods in Systems Biology. Springer, Springer, Italy, 188–206.
- Privacy at Risk: Exploiting Similarities in Health Data for Identity Inference. arXiv preprint arXiv:2308.08310 2023 (2023), 1.
- Implementation and use of disease diagnosis systems for electronic medical records based on machine learning: A complete review. IEEE Access 8 (2020), 150489–150513.
- Privacy-preserving gradient boosting decision trees. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. AAAI, USA, 784–791.
- Mobile clinical decision support systems and applications: a literature and commercial review. Journal of medical systems 38, 1 (2014), 4.
- Cardiorespiratory dynamics measured from continuous ECG monitoring improves detection of deterioration in acute care patients: A retrospective cohort study. PloS one 12, 8 (2017), 1.
- Clinical decision-support systems. In Biomedical informatics. Springer, USA, 643–674.
- A robust genetic algorithm for learning temporal specifications from data. In International Conference on Quantitative Evaluation of Systems. Springer, Springer, USA, 323–338.
- W. Nicholson Price and I. Glenn Cohen. 2019. Privacy in the age of medical big data. Nature Medicine 25, 1 (2019), 37–43. https://doi.org/10.1038/s41591-018-0272-7 Available: http://dx.doi.org/10.1038/s41591-018-0272-7.
- Early prediction of sepsis from clinical data: the PhysioNet/Computing in Cardiology Challenge 2019. In 2019 Computing in Cardiology (CinC). IEEE, IEEE, USA, Page–1.
- Differential privacy preservation in interpretable feedforward-designed convolutional neural networks. In 2020 IEEE 19th international conference on trust, security and privacy in computing and communications (TrustCom). IEEE, IEEE, USA, 631–638.
- PrivTrie: Effective frequent term discovery under local differential privacy. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, IEEE, USA, 821–832.
- Locally differentially private protocols for frequency estimation. In 26th {{\{{USENIX}}\}} Security Symposium. USENIX, USA, 729–745.
- Locally differentially private frequent itemset mining. In 2018 IEEE Symposium on Security and Privacy (SP). IEEE, IEEE, USA, 127–143.
- Locally differentially private heavy hitter identification. IEEE Transactions on Dependable and Secure Computing 2019 (2019), 1.
- A comprehensive survey on local differential privacy toward data statistics and analysis. Sensors 20, 24 (2020), 7030.
- Federated latent dirichlet allocation: A local differential privacy based framework. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. AAAI, USA, 6283–6290.
- Clinical applications of machine learning algorithms: beyond the black box. Bmj 364 (2019), l886.
- Fully-adaptive composition in differential privacy. In International Conference on Machine Learning. PMLR, PMLR, USA, 36990–37007.
- A comprehensive survey on local differential privacy. Security and Communication Networks 2020 (2020), 1–29.
- An arithmetic differential privacy budget allocation method for the partitioning and publishing of location information. In 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom). IEEE, IEEE, USA, 1395–1401.
- PrivKV: Key-value data collection with local differential privacy. In 2019 IEEE Symposium on Security and Privacy (SP). IEEE, IEEE, USA, 317–331.
- A numerical splitting and adaptive privacy budget-allocation-based LDP mechanism for privacy preservation in blockchain-powered IoT. IEEE Internet of Things Journal 10, 8 (2022), 6733–6741.
- LDPart: effective location-record data publication via local differential privacy. IEEE Access 7 (2019), 31435–31445.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.