Conditional anomaly detection using soft harmonic functions: An application to clinical alerting

TL;DR

This paper introduces a non-parametric method for conditional anomaly detection using soft harmonic functions, aimed at improving clinical alerting by identifying unusual data responses in electronic health records.

Contribution

The paper presents a novel soft harmonic-based approach for conditional anomaly detection, with regularization to reduce false positives and demonstrated effectiveness on real-world clinical data.

Findings

Effective detection of unusual labels in electronic health records

Outperforms baseline methods in identifying anomalies

Regularization reduces false alarms in anomaly detection

Abstract

Timely detection of concerning events is an important problem in clinical practice. In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response, such as the omission of an important lab test. We develop a new non-parametric approach for conditional anomaly detection based on the soft harmonic solution, with which we estimate the confidence of the label to detect anomalous mislabeling. We further regularize the solution to avoid the detection of isolated examples and examples on the boundary of the distribution support. We demonstrate the efficacy of the proposed method in detecting unusual labels on a real-world electronic health record dataset and compare it to several baseline approaches.