How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection
Open Access
- 4 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Translational Psychiatry
- Vol. 11 (1), 1-9
- https://doi.org/10.1038/s41398-021-01224-x
Abstract
Decision support systems embodying machine learning models offer the promise of an improved standard of care for major depressive disorder, but little is known about how clinicians’ treatment decisions will be influenced by machine learning recommendations and explanations. We used a within-subject factorial experiment to present 220 clinicians with patient vignettes, each with or without a machine-learning (ML) recommendation and one of the multiple forms of explanation. We found that interacting with ML recommendations did not significantly improve clinicians’ treatment selection accuracy, assessed as concordance with expert psychopharmacologist consensus, compared to baseline scenarios in which clinicians made treatment decisions independently. Interacting with incorrect recommendations paired with explanations that included limited but easily interpretable information did lead to a significant reduction in treatment selection accuracy compared to baseline questions. These results suggest that incorrect ML recommendations may adversely impact clinician treatment selections and that explanations are insufficient for addressing overreliance on imperfect ML algorithms. More generally, our findings challenge the common assumption that clinicians interacting with ML tools will perform better than either clinicians or ML algorithms individually.Keywords
This publication has 46 references indexed in Scilit:
- Prediction of Individual Response to Electroconvulsive Therapy via Machine Learning on Structural Magnetic Resonance Imaging DataJAMA Psychiatry, 2016
- Cross-trial prediction of treatment outcome in depression: a machine learning approachThe Lancet Psychiatry, 2016
- The Role of Explanations on Trust and Reliance in Clinical Decision Support SystemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A Clinical Risk Stratification Tool for Predicting Treatment Resistance in Major Depressive DisorderBiological Psychiatry, 2013
- Cigarette Smoking Among Persons With Schizophrenia or Bipolar Disorder in Routine Clinical Settings, 1999–2011Psychiatric Services, 2013
- Cigarette Smoking Among Persons With Schizophrenia or Bipolar Disorder in Routine Clinical Settings, 1999–2011Psychiatric Services, 2012
- Simplicity and probability in causal explanationCognitive Psychology, 2007
- Multiple Segment Factorial Vignette DesignsJournal of Marriage and Family, 2006
- Automation Bias and Errors: Are Crews Better Than Individuals?The International Journal of Aviation Psychology, 2000