Development and Validation of AI Algorithms for Dental Radiography Interpretation

This study developed and validated AI algorithms for for orthopantomogram (OPTG) interpretation, comparing accuracy with radiologists. An experimental study design was used in a dental setting for this research. A sample of 138 orthopantomogram (OPTG) were divided into two groups (AI and Human) using stratified random sampling. The performance of AI and human-AI was evaluated using confusion matrices, sensitivity, specificity, accuracy, and error analysis conducted in R Studio. The study analyzed 138 individuals (mean age 44.59 years) with a balanced gender distribution (50% male, 50% female) and varying severity levels (mild, moderate, severe). Diagnoses included caries, fractures (roots of teeth), and other abnormalities such as periodontal disease, traumatic lesions, and neoplasms (benign and malignant). The AI model showed better performance than the human control model in all the important markers, such as sensitivity (86.84 vs 79.41), specificity (90.32 vs 88.57), and accuracy (88.4 vs 84.1). The AI showed better results than the above parameters in the ROC curve (AUC 0.886 vs 0.84). Compared to the interpretations made by humans, AI has proven to be more accurate in its diagnostics and has a higher sensitivity and specificity rate.