Association of Clinician Diagnostic Performance With Machine Learning–Based Decision Support Systems
TL
TL;DR
No robust evidence was found to suggest an association between the use of machine learning–based clinical algorithms to support rather than replace human decision-making and improved clinician diagnostic performance.
Abstract
Key Points Question Is clinician diagnostic performance associated with the use of machine learning–based clinical decision support systems? Findings In this systematic review of 37 studies, no robust evidence was found to suggest an association between the use of machine learning–based clinical algorithms to support rather than replace human decision-making and improved clinician diagnostic performance. Meaning Caution should be observed when estimating the current ability of machine learning algorithms to affect patient care, and emphasis on the evaluation of the human-computer interaction is needed.
References69 items
1
Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension
2
Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies
3
Augment Intelligence Dermatology : Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders.
4
A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis.
5