Journal of the American Medical Informatics Association · 2022 · 15 citations · 12 references
ComputingBiomedical InformaticsHealth InformaticsElectronic Health RecordsMachine LearningPredictive AnalyticsClinical AnalyticsDecision Support AnalyticsElectronic Health Record AnalyticsHealthcare AnalyticsPredictive Health ModelingRisk PredictionAdvance Care PlanningCancer Mortality PredictionElectronic Health Record PredictionElectronic Health Record Prediction ModelsMachine Learning For HealthcareMortality PredictionPredictive ModellingPrognostic Prediction
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.
12
Assessing the Performance of Prediction Models
Ewout W. Steyerberg, Andrew J. Vickers, Nancy R. Cook et al. · Epidemiology · 2009 · 4.9K citations · Full text
Machine Learning Approaches to Predict 6-Month Mortality Among Patients With Cancer
Ravi B. Parikh, Christopher R. Manz, Corey Chivers et al. · JAMA Network Open · 2019 · 232 citations · Full text