Machine learning to assist clinical decision-making during the COVID-19 pandemic

Abstract

Background: The number of cases from the coronavirus disease 2019 (COVID-19) global pandemic has overwhelmed existing medical facilities and forced clinicians, patients, and families to make pivotal decisions with limited time and information.

Main body: While machine learning (ML) methods have been previously used to augment clinical decisions, there is now a demand for "Emergency ML." Throughout the patient care pathway, there are opportunities for ML-supported decisions based on collected vitals, laboratory results, medication orders, and comorbidities. With rapidly growing datasets, there also remain important considerations when developing and validating ML models.

Conclusion: This perspective highlights the utility of evidence-based prediction tools in a number of clinical settings, and how similar models can be deployed during the COVID-19 pandemic to guide hospital frontlines and healthcare administrators to make informed decisions about patient care and managing hospital volume.

Keywords: Artificial intelligence (AI); Clinical decision-making; Coronavirus disease 19 (COVID-19); Healthcare; Machine learning (ML).

Fig. 1

a ML/AI in the patient care pathway. The black asterisks represent multiple decision points during the patient care pathway that could be augmented by ML/AI tools. The green traces represent a COVID-19 negative diagnosis or recovery while the orange and red traces represent risk stratification of patients by lower and higher risks of deterioration, respectively, as determined by a potential ML/AI model. Additional decisions in the hospital include prioritization of care, allocation of resources, and estimation of prognosis. b An expanding COVID-19 database. Since March 1, 2020, there has been an increasing amount of COVID-19 patient data, shown here by new admissions and new medical data entries at Northwell Health, New York’s largest health system, facilities. Given increasing hospital admissions (black trace, left y-axis), there have been hundreds of thousands of new data entries per day (colored bars, right y-axis), including vitals, laboratory results, medication orders, and patient comorbidities. This vast data allows a unique opportunity to implement ML/AI to support medical frontlines and healthcare administrators in the fight against COVID-19. c Evolving patient profiles and discharge rates. Basic characteristics of the patient population changed during the progression of the wave of new cases, which can affect performance of a predictive model. For example, the average length of stay for expired patients and those discharged alive (dark blue with square markers and light blue with triangle markers, respectively, left y-axis) diverged in mid-April. Because of these changes, a predictive model with good early performance may decline because of differences between patients hospitalized for three weeks compared to less than a week. Also, an individual’s patient profile may have evolved significantly from hospital admission to those timepoints later during hospitalization. Discharges per day (grey bars, right y-axis) increased with the pandemic’s peak and declined with reduced numbers of new cases