Outlier detection for patient monitoring and alerting

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.

Figure optionsDownload high-quality image (90 K)Download as PowerPoint slideHighlights
► An approach for detecting unusual patient-management decisions from EHR data.
► A decision that is unusual may be due to an error and an alert should be considered.
► Tests the approach using expert reviews on data for postsurgical cardiac patients.
► The results show false alert rates from 25% to 66%.
► The results show stronger outliers are correlated with higher true alert rates.