Trigger Tool-Based Automated Adverse Event Detection in Electronic Health Records: Systematic Review

BACKGROUND: Adverse events in health care entail substantial burdens to healthcare systems, institutions, and patients. Retrospective trigger tools are oftenmanually applied to detect AEs, although automated approaches using electronichealth records may offer real-time adverse event detection, allowing timelycorrective interventions.OBJECTIVE: The aim of this systematic review was to describe current studymethods and challenges regarding the use of automatic trigger tool-based adverse event detection methods in electronic health records. In addition, we aimed toappraise the applied studies' designs and to synthesize estimates of adverseevent prevalence and diagnostic test accuracy of automatic detection methodsusing manual trigger tool as a reference standard.METHODS: PubMed, EMBASE, CINAHL, and the Cochrane Library were queried. Weincluded observational studies, applying trigger tools in acute care settings,and excluded studies using nonhospital and outpatient settings. Eligible articleswere divided into diagnostic test accuracy studies and prevalence studies. Wederived the study prevalence and estimates for the positive predictive value. We assessed bias risks and applicability concerns using Quality Assessment tool for Diagnostic Accuracy Studies-2 (QUADAS-2) for diagnostic test accuracy studies andan in-house developed tool for prevalence studies.RESULTS: A total of 11 studies met all criteria: 2 concerned diagnostic testaccuracy and 9 prevalence. We judged several studies to be at high bias risks fortheir automated detection method, definition of outcomes, and type of statisticalanalyses. Across all the 11 studies, adverse event prevalence ranged from 0% to17.9%, with a median of 0.8%. The positive predictive value of all triggers todetect adverse events ranged from 0% to 100% across studies, with a median of40%. Some triggers had wide ranging positive predictive value values: (1) in 6studies, hypoglycemia had a positive predictive value ranging from 15.8% to 60%; (2) in 5 studies, naloxone had a positive predictive value ranging from 20% to91%; (3) in 4 studies, flumazenil had a positive predictive value ranging from38.9% to 83.3%; and (4) in 4 studies, protamine had a positive predictive valueranging from 0% to 60%. We were unable to determine the adverse event prevalence,positive predictive value, preventability, and severity in 40.4%, 10.5%, 71.1%,and 68.4% of the studies, respectively. These studies did not report the overall number of records analyzed, triggers, or adverse events; or the studies did notconduct the analysis.CONCLUSIONS: We observed broad interstudy variation in reported adverse eventprevalence and positive predictive value. The lack of sufficiently describedmethods led to difficulties regarding interpretation. To improve quality, we see the need for a set of recommendations to endorse optimal use of research designs and adequate reporting of future adverse event detection studies.