AI-derived panoramic score and its association with major systemic diseases: A retrospective cross-sectional study.

OBJECTIVES: This study evaluated whether an AI-generated, panoramic radiograph-based score was associated with five selected systemic diseases. METHODS: 26,550 panoramic radiographs from two hospitals were analyzed using an AI model that detected teeth and implants and quantified alveolar bone loss. A radiograph-based score (0-100) was derived from missing teeth and weighted bone-loss severity. Associations with diabetes mellitus, hypertension, osteoporosis, ischemic heart disease, and hyperlipidemia were assessed using between-group comparisons, prevalence trends across score bins, and logistic regression adjusted for age, sex, and body mass index. Incremental discrimination over covariates alone was quantified using ΔAUC and the DeLong test. RESULTS: Patients with each condition had lower scores than controls (all P<0.001), with the largest adjusted difference for diabetes mellitus (β=-6.25). Prevalence of all five conditions showed a decreasing trend across ascending score strata (Cochran-Armitage P<0.001), with the highest Q1-to-Q5 relative risk for ischemic heart disease (4.73). After adjustment, the score remained independently associated with all diseases (AUC, 0.74-0.80), with significant incremental discrimination for diabetes mellitus, hypertension, and hyperlipidemia (ΔAUC =0.0015-0.0154; DeLong P<0.0188) but not ischemic heart disease or osteoporosis. CONCLUSIONS: An AI-derived panoramic radiograph-based score was independently associated with five selected systemic diagnoses. Clinical significance An AI-derived score obtained from routinely acquired panoramic radiographs was independently associated with major systemic diseases. This automated, quantitative score may serve as an exploratory image-based index, supporting integrated management between dental and medical care.