Background Medical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS for fundus diseases using data derived from the real world, and externally test the model using fundus photographs collected prospectively from the settings in which the model would most likely be adopted.Methods In this national real-world evidence study, we trained a DLS, the Comprehensive AI Retinal Expert (CARE) system, to identify the 14 most common retinal abnormalities using 207 228 colour fundus photographs derived from 16 clinical settings with different disease distributions. CARE was internally validated using 21 867 photographs and externally tested using 18 136 photographs prospectively collected from 35 real-world settings across China where CARE might be adopted, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres. The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. This study was registered with ClinicalTrials.gov, NCT04213430, and is currently closed.
FindingsThe area under the receiver operating characteristic curve (AUC) in the internal validation set was 0•955 (SD 0•046). AUC values in the external test set were 0•965 (0•035) in tertiary hospitals, 0•983 (0•031) in community hospitals, and 0•953 (0•042) in physical examination centres. The performance of CARE was similar to that of ophthalmologists. Large variations in sensitivity were observed among the ophthalmologists in different regions and with varying experience. The system retained strong identification performance when tested using the non-Chinese dataset (AUC 0•960, 95% CI 0•957-0•964 in referable diabetic retinopathy).Interpretation Our DLS (CARE) showed satisfactory performance for screening multiple retinal abnormalities in real-world settings using prospectively collected fundus photographs, and so could allow the system to be implemented and adopted for clinical care.
Grooming and dress style have both been found to influence the probability of a job applicant being hired. We argue that as these two elements take effect simultaneously during a job application, it is necessary to simultaneously examine the interaction of these two elements of appearance. Based on cue consistency theory, we propose that grooming and a gender-inconsistent dress style weaken the effects of each other, especially when the evaluators are men. We used three samples to progressively test our hypotheses. With Sample 1 (n = 142), we found that masculine dress weakened the positive effect of grooming on the hirability of female applicants. Furthermore, the interaction effect of grooming and dress style was stronger for male than for female evaluators. With Sample 2 (n = 152), we found that perceived competence mediated the two-way interaction effect of grooming and dress style on hirability. We used Sample 3 (n = 155) to further examine whether these findings could be generalized to male applicants and found that the interaction effect of grooming and masculine dress was stronger for male than for female evaluators.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.