Concordance between large language models and orthodontists in photo-based orthodontic assessment.

Two artificial intelligence language models showed moderate clinical acceptability when assessing orthodontic cases from photographs, though ChatGPT-4o performed better for treatment recommendations in certain patient groups; both systems showed variability in complex decision-making and should only supplement professional oversight.

A plain-English summary of the study's own findings — we don't add our own claims or interpretation. Read the full paper for the complete methods and results, and apply your own clinical judgement.