Artificial intelligence (AI) technology may provide high diagnostic accuracy in detecting osteoporosis on panoramic dental x-rays, according to a review study published in February in the Journal of Dentistry.
Furthermore, deep learning and machine learning AI show promise in classifying osteoporosis, the authors wrote.
“The application of AI in analyzing panoramic radiographs could transform osteoporosis screening in routine dental practice by providing early and accurate diagnosis,” wrote the authors, led by Nikoo Ghasemi of the Zanjan University of Medical Sciences in Iran (J Dent, February 25, 2025, 105650).
To study the benefits of AI, a comprehensive search across multiple electronic databases was conducted to evaluate current research on the technology for detecting osteoporosis in dental panoramic images. The analysis focused on studies that included dental panoramic radiographs as the population and AI-based interventions such as deep learning and machine learning.
Comparisons were made using reference standards like dual-energy x-ray absorptiometry. Diagnostic outcomes varied by task, with classification studies assessing accuracy, specificity, and sensitivity, they wrote.
A total of 24 studies were included, with accuracy ranging from 50% to 99%, sensitivity from 50% to 100%, and specificity from 38% to 100%. While 10 studies had a low risk of bias in all domains, 18 showed a low risk of applicability concerns.
Pooled sensitivity and specificity were 87.92% and 81.93%, respectively, with a diagnostic odds ratio of 32.99 and a positive likelihood ratio of 4.87. Meta-regression analysis found that sample size had minimal impact on heterogeneity (R² = 0.078, p = 0.052), suggesting other study-level factors contributed to variability, they wrote.
However, the study had limitations. Variations in AI models, datasets, reference standards, and evaluation metrics may limit the generalizability of the findings, the authors added.
"This systematic review underscores the promising role of AI, both deep learning and machine learning, in classifying osteoporosis using dental panoramic radiographs," Ghasemi and colleagues concluded.
