Detection of Anomalous Events in Electronic Health Records
Over the past decade, Health Information Technology (Health IT) has enabled an explosion in the amount of digital information stored in electronic health records (EHRs). According to recent studies, safety-related issues in healthcare can present themselves as anomalies in EHR data. Motivating examples of anomalous events in EHRs include clinical events related to invalid order cancellations or rejections, which may be initiated by clinical staff or automatic software routines in Health IT systems. Such events may be detected using anomaly detection or change point detection methods. In this paper, we explore the use of a forecasting approach to detect anomalies in EHR data using an online Support Vector Regression technique. Specifically, the proposed approach uses temporal frequency of activities in EHRs, coupled with dynamic robust confidence intervals, to characterize events as normal or anomalous. Once an event is characterized as an anomaly, our approach suppresses its effects in subsequent time intervals. The proposed approach shows encouraging results using real-world EHR data from the Veterans Affairs' corporate data warehouse
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1649357
- Resource Relation:
- Conference: 2020 IISE Annual Conference - New Orleans, Louisiana, United States of America - 5/30/2020 4:00:00 AM-6/2/2020 4:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records
Evaluating the Dynamic Behavior of Information Technology Systems in Healthcare using Markov Simulation