Performance drift in a mortality prediction algorithm among patients with cancer during the SARS-CoV-2 pandemic. (21st November 2022)

• Record Type: Journal Article
• Authors: Parikh, Ravi B; Zhang, Yichen; Kolla, Likhitha; Chivers, Corey; Courtright, Katherine R; Zhu, Jingsan; Navathe, Amol S; Chen, Jinbo
• Is Part Of: Journal of the American Medical Informatics Association. Volume 30:Number 2(2023)
• Page Start: 348
• Page End: 354
• Publication Date: 2022-11-21
• Subjects: SARS-CoV-2 -- machine learning -- algorithm drift -- mortality -- cancer; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocac221
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Sudden changes in health care utilization during the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic may have impacted the performance of clinical predictive models that were trained prior to the pandemic. In this study, we evaluated the performance over time of a machine learning, electronic health record-based mortality prediction algorithm currently used in clinical practice to identify patients with cancer who may benefit from early advance care planning conversations. We show that during the pandemic period, algorithm identification of high-risk patients had a substantial and sustained decline. Decreases in laboratory utilization during the peak of the pandemic may have contributed to drift. Calibration and overall discrimination did not markedly decline during the pandemic. This argues for careful attention to the performance and retraining of predictive algorithms that use inputs from the pandemic period.