Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning based clinical decision support system in an inpatient setting

• Published in: Journal of the American Medical Informatics Association : JAMIA Vol. 26; no. 12; pp. 1560 - 1565
• Main Authors: Segal, G, Segev, A, Brom, A, Lifshitz, Y, Wasserstrum, Y, Zimlichman, E
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.12.2019
• Subjects: Academic Medical Centers; Algorithms; Decision Support Systems, Clinical; Drug Therapy, Computer-Assisted; Drug-Related Side Effects and Adverse Reactions - prevention & control; Humans; Israel; Machine Learning; Medical Order Entry Systems; Medication Errors - prevention & control; Medication Systems, Hospital; Patient Safety; Prospective Studies; Research and Applications; Israel; drug prescription errors; outlier system; adverse drug events; patient safety; drug safety; in-patient setting
• ISSN: 1527-974X; 1067-5027; 1527-974X
• DOI: 10.1093/jamia/ocz135

Drug prescription errors are made, worldwide, on a daily basis, resulting in a high burden of morbidity and mortality. Existing rule-based systems for prevention of such errors are unsuccessful and associated with substantial burden of false alerts. In this prospective study, we evaluated the accuracy, validity, and clinical usefulness of medication error alerts generated by a novel system using outlier detection screening algorithms, used on top of a legacy standard system, in a real-life inpatient setting. We integrated a novel outlier system into an existing electronic medical record system, in a single medical ward in a tertiary medical center. The system monitored all drug prescriptions written during 16 months. The department's staff assessed all alerts for accuracy, clinical validity, and usefulness. We recorded all physician's real-time responses to alerts generated. The alert burden generated by the system was low, with alerts generated for 0.4% of all medication orders. Sixty percent of the alerts were flagged after the medication was already dispensed following changes in patients' status which necessitated medication changes (eg, changes in vital signs). Eighty-five percent of the alerts were confirmed clinically valid, and 80% were considered clinically useful. Forty-three percent of the alerts caused changes in subsequent medical orders. A clinical decision support system that used a probabilistic, machine-learning approach based on statistically derived outliers to detect medication errors generated clinically useful alerts. The system had high accuracy, low alert burden and low false-positive rate, and led to changes in subsequent orders.