Ensuring the clinical impact of medical artificial intelligence
Abstract
Randomised controlled trials (RCTs) testing artificial intelligence (AI) approaches in health care (AI-RCTs) mostly use measures of processes rather than measures of health outcomes. Measures of processes refer to indicators that assess the performance of a tool or an intervention, rather than their actual results. These measures include diagnostic accuracy, detection rate, specificity, time-to-test results, and workflow-related efficiency. In contrast, measures of health outcomes reflect the actual effects on patient’s health.
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
Machine Learning in Healthcare
Clinical Reasoning and Diagnostic Skills
Publication details
- Journal / source
- The Lancet Digital Health
- Publisher
- Elsevier BV
- Volume
- 8
- Issue
- 7
- Pages
- 101030–101030
- Publication date
- 16 June 2026
- Language
- EN