Application of Artificial Intelligence for Osteoporosis Screening Using Chest Radiographs

Abstract

Objective: To create the artificial intelligence screening osteoporosis tool (AISOT) to predict bone mineral density (BMD) using chest radiographs and to describe statistics characterizing the tool's effectiveness and satisfaction of the tool usage. Materials and Methods: All 525 BMD examinations individually paired with chest radiographs during the years2022–2023. The AISOT was developed based on deep learning concept on chest radiograph images to predict BMD value. Both BMD observed and predicted values were classified osteoporosis condition by using T-scores of preclinical guidelines. The AISOT demonstrated the accuracy, sensitivity, specificity at 94% (95% CI: 84 -99%), 95% (95% CI: 83-99%) and 90% (95% CI: 56- 99%) respectively. The AISOT model was tested with 195 participants. The research instrument was a questionnaire developed by the researcher including personal health history, observed and predicted BMD values, FRAX tool osteoporosis evaluation and AISOT satisfaction. Z-test was utilized to compare statistics characterized the tool effectiveness. Results: The AISOT vs the FRAX tool comprised accuracy at 74% (95% CI: 67- 80%) vs 51% (95% CI: 44 -58%) (p < .001); sensitivity at 61% (95% CI: 52-70%) vs 24 % (95% CI: 17-33%) (p = .012); specificity at 93% (95% CI: 85-98%) vs 92% (95% CI: 84-97%) (p > .05); PPV at 94% vs 83% (p = .015); NPV at 61% vs 44% (p = .016). AISOT satisfaction was at very satisfied level (mean = 4.81, SD.= 0.434). Conclusions: AISOT is effective for screening abnormal BMD in people with osteoporotic risk factors. Future study of various settings will enhance its credibility.