MAIBAI: developing a metrological framework for assessment of image-based artificial intelligence systems for disease detection

Le résumé fourni par la source

thresholds of £15,000/QALY and over.Incremental QALY gains were negligible (<0.001QALYs) and did not represent a clinically meaningful health benefit.AI implementation incurs notable costs in the context of limited staffing and material resource budgets, with demands on clinical staff potentially adding to short-term pressures on diagnostic services.AI-assisted diagnostic CXR is costeffective compared with usual care (non-AI) in the lung cancer pathway, but marginal diagnostic performance improvement and limitations in clinical outcomes data restrict the gains in estimated health and cost in our analysis.The findings indicate value in further deployment of AI; however, a stronger evidence base is needed to fully capture costs and health outcomes upon which decision-makers rely.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.