Artificial intelligence score from panoramic radiographs independently linked to five systemic diseases

An artificial intelligence (AI)-derived panoramic score was independently associated with diabetes, hypertension, hyperlipidemia, osteoporosis, and ischemic heart disease in 26,550 radiographs; adjusted AUC 0.74–0.80.

• Retrospective cross-sectional study of 26,550 panoramic radiographs from two hospitals; the AI model quantified alveolar bone loss and missing teeth to generate a 0–100 score.
• Prevalence of all five conditions decreased across ascending score strata (Cochran-Armitage P<0.001); the highest Q1-to-Q5 relative risk was ischemic heart disease at 4.73.
• After adjustment, the score remained independently associated with all diseases (AUC 0.74–0.80); incremental discrimination over age, sex, and BMI was significant only for diabetes mellitus, hypertension, and hyperlipidemia (ΔAUC 0.0015–0.0154; DeLong P<0.0188).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.