Making machine learning matter to clinicians: model actionability in medical decision-making
Open Access
- 24 January 2023
- journal article
- research article
- Published by Springer Nature in npj Digital Medicine
- Vol. 6 (1) , 1-5
Abstract
Machine learning (ML) has the potential to transform patient care and outcomes. However, there are important differences between measuring the performance of ML models in silico and usefulness at the point of care. One lens to use to evaluate models during early development is actionability, which is currently undervalued. We propose a metric for actionability intended to be used before the evaluation of calibration and ultimately decision curve analysis and calculation of net benefit. Our metric should be viewed as part of an overarching effort to increase the number of pragmatic tools that identify a model’s possible clinical impacts.Keywords
Funding Information
- Center for Research on Computation and Society (CRCS) at the Harvard John A. Paulson School of Engineering and Applied Sciences
- William G. Williams Directorship at the Hospital for Sick Children
This publication has 24 references indexed in Scilit:
- Decision-making under pressure: medical errors in uncertain and dynamic environmentsAustralian Health Review, 2017
- Cardiac output and systemic vascular resistance: Clinical assessment compared with a noninvasive objective measurement in children with shockJournal of Critical Care, 2017
- Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic testsBMJ, 2016
- Machine Learning in MedicineCirculation, 2015
- The challenges in defining and measuring diagnostic errorDiagnosis, 2015
- Clinical Uncertainty, Diagnostic Accuracy, and Outcomes in Emergency Department Patients Presenting With DyspneaArchives of internal medicine (1960), 2008
- Resident uncertainty in clinical decision making and impact on patient care: a qualitative studyQuality and Safety in Health Care, 2008
- Stress from Uncertainty from Graduation to Retirement—A Population-Based Study of Swiss PhysiciansJournal of General Internal Medicine, 2007
- Should we confirm our clinical diagnostic certainty by autopsies?Intensive Care Medicine, 2001
- Our Stubborn Quest for Diagnostic CertaintyNew England Journal of Medicine, 1989