Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography

ObjectiveTo examine whether incorrect AI results impact radiologist performance, and if so, whether human factors can be optimized to reduce error.MethodsMulti-reader design, 6 radiologists interpreted 90 identical chest radiographs (follow-up CT needed: yes/no) on four occasions (09/20-01/22). No AI result was provided for session 1. Sham AI results were provided for sessions 2-4, and AI for 12 cases were manipulated to be incorrect (8 false positives (FP), 4 false negatives (FN)) (0.87 ROC-AUC). In the Delete AI (No Box) condition, radiologists were told AI results would not be saved for the evaluation. In Keep AI (No Box) and Keep AI (Box), radiologists were told results would be saved. In Keep AI (Box), the ostensible AI program visually outlined the region of suspicion. AI results were constant between conditions.ResultsRelative to the No AI condition (FN = 2.7%, FP = 51.4%), FN and FPs were higher in the Keep AI (No Box) (FN = 33.0%, FP = 86.0%), Delete AI (No Box) (FN = 26.7%, FP = 80.5%), and Keep AI (Box) (FN = to 20.7%, FP = 80.5%) conditions (all ps < 0.05). FNs were higher in the Keep AI (No Box) condition (33.0%) than in the Keep AI (Box) condition (20.7%) (p = 0.04). FPs were higher in the Keep AI (No Box) (86.0%) condition than in the Delete AI (No Box) condition (80.5%) (p = 0.03).ConclusionIncorrect AI causes radiologists to make incorrect follow-up decisions when they were correct without AI. This effect is mitigated when radiologists believe AI will be deleted from the patient's file or a box is provided around the region of interest.

Automated summary

This study aimed to investigate the impact of incorrect AI results on radiologist performance and explore the possibility of reducing errors through optimizing human factors. The results showed that incorrect AI results increased the number of errors in follow-up decisions made by radiologists compared to when they did not have AI assistance. However, this effect was mitigated when radiologists believed the AI results would be deleted or when a box was provided around the region of interest.