AbstractEnamel-only proximal caries, if detected, can be reversed by non-invasive treatments. Dental bitewing radiograph analysis is central to diagnosis and treatment planning and, when used to detect enamel-only proximal caries, it is an important tool in minimum intervention and preventive dentistry. However, the subtle patterns of enamel-only proximal caries visible in bitewing radiographs are difficult to detect and often missed by dental practitioners. This study measures the ability of dentists to detect enamel-only proximal caries in bitewing radiographs with and without the use of AssistDent® Artificial Intelligence (AI) software.23 dentists were randomly divided into a control arm, in which no Artificial Intelligence assistance was provided, and an experimental arm in which Artificial Intelligence assistance provided on-screen prompts for potential locations of enamel-only proximal caries. All participants analysed a set of 24 bitewings, gathered from one dental hospital and 11 general dental practices, which had previously been analysed independently by a panel of 5 dento-maxillofacial radiologists and 1 professor of restorative dentistry who, between them, identified a total of 65 enamel-only carious lesions and 241 healthy proximal surfaces.Results demonstrate that dentists using the assistive software found 75.8% of the enamel-only proximal caries compared to a 44.3% detection rate in the control group. This represents an absolute increase of 31.5% (relative increase in sensitivity of 71%). Participants in the experimental group incorrectly identified 14.6% of the healthy surfaces as having enamel-only proximal caries compared to 3.7% in the control group, an absolute increase of 10.9% (relative decrease in specificity of 11%).T-test analysis demonstrated a statistically significant difference (p<0.01) between the two arms in sensitivity (true positive caries detection rate) and specificity (false positive rate).We conclude that AssistDent® Artificial Intelligence software significantly improves dentists’ ability to detect enamel-only proximal caries, with only a slight increase in false positives, and could be considered as a tool to support minimum intervention and preventive dentistry in general practice.