Application of a Comprehensive Evaluation Framework to COVID-19 Studies: Systematic Review of Translational Aspects of Artificial Intelligence in Health Care.

Results We observed a significant trend for studies to attain high scores for technical capability but low scores for the areas essential for clinical translatability.

also in 9,775 other papers

Thus, we classified the studies as being imaging (direct image analysis of X-rays or CT scans) or nonimaging (eg, studies that analyzed blood metabolites), and there was a strong trend for nonimaging studies to score higher than imaging studies, which included the “objective of the study” (imaging study mean score 1.79, SE 0.08; nonimaging study mean score 2.18, SE 0.13; P =.02), “safety and quality” (imaging study mean score 0.16, SE 0.05; nonimaging study mean score 0.36, SE 0.14; P =.015), “nonmaleficence” (imaging study mean score 0.04, SE 0.02; nonimaging study mean score 0.18, SE 0.07; P =.05), and “number of services” (imaging study mean score 0.25, SE 0.06; nonimaging study mean score 0.55, SE 0.11; P =.02) subcomponents ( Multimedia Appendix 4 C,D).

also in 5,725 other papers