Diagnosis in pediatric dentistry plays a vital role in the treatment of dental diseases and the prevention of their complications. Regarding the AI application, ChatGPT and POE’s diagnostic models are being proposed for pediatric diagnosis. To assess the accuracy of two AI programs in diagnosing pediatric cases. To compare POE and ChatGPT and to evaluate the completeness of the responses generated by each AI program. This is a retrospective study comparing the accuracy of two AI programs in diagnosing pediatric dental cases conducted in the Pediatric Department at Riyadh Elm University, Riyadh, KSA. Clinical cases/scenarios were collected from actual cases in REU clinics and from textbooks. A convenient sampling technique was used, and a total of 100 case scenarios and treatments were entered into the two programs (ChatGPT and POE). Chi-square test was done to compare the two AI programs, and a value of 0.05 or less will be considered significant if there is a difference between the accuracy levels of the two AI programs. Out of the 100 questions entered into the two AI systems, both ChatGPT and POE answered 70 correctly. The chi-square test showed no statistically significant difference between the two systems in the correct diagnosis of pediatric cases. There is no difference in diagnostic accuracy between the two systems.
