Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians

Objective Despite artificial intelligence (AI) being used increasingly in healthcare, implementation challenges exist leading to potential biases during the clinical decision process of the practitioner. The interaction of AI with novice clinicians was investigated through an identification task, an important component of diagnosis, in dental radiography. The study evaluated the performance, efficiency, and confidence level of dental students on radiographic identification of furcation involvement (FI), with and without AI assistance. Materials and Methods Twenty-two third- and 19 fourth-year dental students (DS3 and DS4, respectively) completed remotely administered surveys to identify FI lesions on a series of dental radiographs. The control group received radiographs without AI assistance while the test group received the same radiographs and AI-labeled radiographs. Data were appropriately analyzed using the Chi-square, Fischer's exact, analysis of variance, or Kruskal-Wallis tests. Results Performance between groups with and without AI assistance was not statistically significant except for 1 question where tendency was to err with AI-generated answer (P < .05). The efficiency of task completion and confidence levels was not statistically significant between groups. However, both groups with and without AI assistance believed the use of AI would improve the clinical decision-making. Discussion Dental students detecting FI in radiographs with AI assistance had a tendency towards over-reliance on AI. Conclusion AI input impacts clinical decision-making, which might be particularly exaggerated in novice clinicians. As it is integrated into routine clinical practice, caution must be taken to prevent overreliance on AI-generated information. Lay Summary Artificial intelligence (AI) is being used with increasing frequency in the healthcare field to provide earlier and easier detection of abnormalities. Although these AI systems are designed to optimize accuracy in detecting abnormalities less is known about the interaction of the clinician and system. We tested the interaction of an AI system with novice clinicians (dental students) that were attempting to diagnose abnormalities in dental radiographs. One group of the dental student participants received AI assistance, whereas the other group did not receive AI assistance. We investigated 3 primary metrics during AI and participant interactions: (1) performance, (2) efficiency, and (3) confidence. Our findings suggest that novice clinicians are more likely to over-rely on AI leading to potential lower performance when assisted with an AI system. In addition, the AI system used in this study did not improve decision-making speed or confidence in novice clinicians. Despite the limitations of this single study, those that are developing AI systems to aid in clinician decision-making should keep in mind the psychological interaction (machine/human) and end user experience that can potentially affect clinical performance and patient safety. Additionally, participants that used AI and did not use AI assistance felt that these systems have the potential to improve clinical decision-making.