MeDeep chest X-ray AI platform scores 84.93 on SUS; residents trust algorithm more than attendings

[medRxiv] A multicenter cross-sectional study across hospitals in Kermanshah evaluated the MeDeep artificial intelligence platform among 88 medical professionals, including attending radiologists, radiology residents, internal medicine physicians and medical externs, according to the paper. The platform achieved a mean System Usability Scale score of 84.93, with no significant difference across professional subgroups (p=0.387), the authors said. However, overarching AI acceptance and algorithmic trust varied significantly by clinical role, with radiology residents showing significantly higher overarching AI acceptance (p=0.016) and algorithmic trust (p=0.008) than attending radiologists. Multivariate regression found user familiarity (Beta=0.500, p<0.001) and perceived system usability (Beta=0.236, p=0.012), rather than years of clinical experience, were the primary independent positive predictors of AI acceptance; higher perceived usability also directly predicted greater algorithmic trust (Beta=0.282, p=0.009). The authors said technical usability is a necessary baseline for diagnostic platforms, but professional trust dictates ultimate clinical adoption.