Clinical research underlies ethical integration of healthcare artificial intelligence
MD McCradden et al, Nature Medicine, September 9, 2020
MD McCradden et al, Nature Medicine, September 9, 2020
Despite the promise of machine learning (ML), only a small fraction of developed models are successfully implemented at the point of care, a phenomenon called the ‘AI chasm’1. Crossing this chasm requires careful consideration of the most appropriate method of evaluation and oversight.
Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension
X Liu et al, Nature Medicine, September 9, 2020
X Liu et al, Nature Medicine, September 9, 2020
The CONSORT-AI (Consolidated Standards of Reporting Trials–Artificial Intelligence) extension is a new reporting guideline for clinical trials evaluating interventions with an AI component. Guidelines were developed through a staged consensus process involving literature review and expert consultation to generate 29 candidate items.
Guiding better design and reporting of AI-intervention trials
Lancet Digital Health, September 9, 2020
Lancet Digital Health, September 9, 2020
AI is reshaping the global landscape of medicine. But evaluation of these AI interventions can be poorly reported, omitting vital information such as sample size calculations and how missing data were handled. To demonstrate their clinical efficacy, AI interventions must be assessed by randomized trials and findings accurately disseminated.
No hay comentarios:
Publicar un comentario