Conditional outlier detection for clinical alerting
For clinicians, this work offers a potential tool to flag potential errors in patient management, but the results are preliminary and domain-specific.
The paper proposes a data-driven method to detect unusual patient-management actions from EHR data, aiming to reduce clinical errors. Evaluation on 4,486 post-cardiac surgical patients shows low false alert rates and correlation between anomaly strength and alert rates.
We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management actions using past patient cases stored in an electronic health record (EHR) system. Our hypothesis is that patient-management actions that are unusual with respect to past patients may be due to a potential error and that it is worthwhile to raise an alert if such a condition is encountered. We evaluate this hypothesis using data obtained from the electronic health records of 4,486 post-cardiac surgical patients. We base the evaluation on the opinions of a panel of experts. The results support that anomaly-based alerting can have reasonably low false alert rates and that stronger anomalies are correlated with higher alert rates.