Development and validation of a machine learning model to predict mortality risk in patients with COVID-19. Issue 1 (7th May 2021)

• Record Type: Journal Article
• Authors: Stachel, Anna; Daniel, Kwesi; Ding, Dan; Francois, Fritz; Phillips, Michael; Lighter, Jennifer
• Is Part Of: BMJ health & care informatics. Volume 28:Issue 1(2021)
• Publication Date: 2021-05-07
• Subjects: information science -- patient care -- medical informatics; Medical informatics -- Great Britain -- Periodicals; Information storage and retrieval systems -- Medical care -- Periodicals; Primary care (Medicine) -- Great Britain -- Data processing -- Periodicals; 362.10285
• DOI: 10.1136/bmjhci-2020-100235
• Languages: English
• ISSNs: 2632-1009

Abstract

Abstract : New York City quickly became an epicentre of the COVID-19 pandemic. An ability to triage patients was needed due to a sudden and massive increase in patients during the COVID-19 pandemic as healthcare providers incurred an exponential increase in workload, which created a strain on the staff and limited resources. Further, methods to better understand and characterise the predictors of morbidity and mortality was needed. Methods: We developed a prediction model to predict patients at risk for mortality using only laboratory, vital and demographic information readily available in the electronic health record on more than 3395 hospital admissions with COVID-19. Multiple methods were applied, and final model was selected based on performance. A variable importance algorithm was used for interpretability, and understanding of performance and predictors was applied to the best model. We built a model with an area under the receiver operating characteristic curve of 83–97 to identify predictors and patients with high risk of mortality due to COVID-19. Oximetry, respirations, blood urea nitrogen, lymphocyte per cent, calcium, troponin and neutrophil percentage were important features, and key ranges were identified that contributed to a 50% increase in patients' mortality prediction score. With an increasing negative predictive value starting 0.90 after the second day of admission suggests we might be able to more confidently identify likely survivors Discussion: This study serves as a use case of a machine learning methods with visualisations to aide clinicians with a better understanding of the model and predictors of mortality. Conclusion: As we continue to understand COVID-19, computer assisted algorithms might be able to improve the care of patients.