Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Feb 16, 2026
Date Accepted: Jun 15, 2026
Cognitive workload and mental burden in healthcare professionals interacting with artificial intelligence: A systematic review and meta-analysis
ABSTRACT
Background:
AI adoption in healthcare has accelerated rapidly, yet cognitive demands on clinicians supervising AI systems remain understudied.
Objective:
To systematically review evidence on cognitive workload and burnoWe searched MEDLINE, Embase, Web of Science, and Cochrane Library through January 2026. Studies measuring cognitive workload or burnout using validated instruments were included. Meta-analysis was performed using random-effects models.ut in healthcare professionals using AI-powered clinical tools.
Methods:
We searched MEDLINE, Embase, Web of Science, and Cochrane Library through January 2026. Studies measuring cognitive workload or burnout using validated instruments were included. Meta-analysis was performed using random-effects models.
Results:
Twenty-one studies (2,885 healthcare professionals, 7 countries) were included. For ambient AI documentation (13 studies), meta-analysis demonstrated significant reductions in NASA-TLX subscales (mental demand: SMD −1.29; temporal demand: SMD −1.48; effort: SMD −1.29), work exhaustion (MD −0.35), burnout prevalence (OR 0.47; 95% CI 0.36–0.60), and documentation time (SMD −0.24). In contrast, diagnostic imaging AI and CDSS showed mixed or negative effects on workload.
Conclusions:
Well-designed AI documentation tools consistently reduce cognitive workload and burnout. However, AI's cognitive impact is context-dependent. Clinical Trial: PROSPERO CRD420261284298
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.