Outlier detection for patient monitoring and alerting

TL;DR

This paper presents a data-driven outlier detection method for identifying unusual patient management decisions in EHRs to generate alerts that may indicate errors, validated with expert opinions on post-cardiac surgery cases.

Contribution

The study introduces an outlier-based alerting approach for patient management decisions, demonstrating its potential effectiveness in a real clinical dataset.

Findings

True alert rates ranged from 25% to 66% across different actions.

66% of alerts corresponded to the strongest outliers.

Expert evaluation supported the effectiveness of the approach.

Abstract

We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). Our hypothesis is that a patient-management decision that is unusual with respect to past patient care may be due to an error and that it is worthwhile to generate an alert if such a decision is encountered. We evaluate this hypothesis using data obtained from EHRs of 4486 post-cardiac surgical patients and a subset of 222 alerts generated from the data. We base the evaluation on the opinions of a panel of experts. The results of the study support our hypothesis that the outlier-based alerting can lead to promising true alert rates. We observed true alert rates that ranged from 25\% to 66\% for a variety of patient-management actions, with 66\% corresponding to the strongest outliers.