Evidence-based anomaly detection in clinical domains

TL;DR

This paper introduces probabilistic anomaly detection methods using Bayesian networks to identify unusual patient management decisions in clinical settings, aiding decision evaluation.

Contribution

It develops new probabilistic models for anomaly detection tailored to clinical decision analysis, focusing on post-surgical cardiac patients.

Findings

Effective identification of unusual management decisions

Models learned from historical patient data

Potential to improve clinical decision evaluation

Abstract

Anomaly detection methods can be very useful in identifying interesting or concerning events. In this work, we develop and examine new probabilistic anomaly detection methods that let us evaluate management decisions for a specific patient and identify those decisions that are highly unusual with respect to patients with the same or similar condition. The statistics used in this detection are derived from probabilistic models such as Bayesian networks that are learned from a database of past patient cases. We apply our methods to the problem of identifying unusual patient-management decisions in post-surgical cardiac patients.