DP-RuL: Differentially-Private Rule Learning for Clinical Decision Support Systems

arXiv:2405.09721v1 Announce Type: new
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 …

arxiv clients cs.cr data decision goal information learn local patient data privacy privacy concerns private protecting ruleset rulesets sensitive sensitive information serious support systems