The raw clinical data used for constructing the OPDoctorNet model

Osteoporosis poses a significant global public health challenge, and timely detection and treatment are crucial for preventing fragility fractures in the elderly. However, opportunistic screening remains challenging. Despite rapid deep learning development, its potential in medical data classification has yet to be fully realized, with traditional machine learning dominating. Therefore, deepening research on deep learning for clinical data recognition in osteoporosis screening holds practical significance. This study utilizes the latest artificial intelligence technology to develop the OPDoctorNet algorithm, combining Transformer and Mamba feature extraction advantages, innovatively proposing multiscale feature fusion and the FeatureBake Block to deeply extract global and local features. The algorithm improves osteoporosis recognition accuracy in clinical data and meets multi-task needs. Results show OPDoctorNet significantly outperforms traditional machine learning and other AI methods in accuracy, recall, and F1 scores, with strong robustness and generalization. Through the Innovation of the FeatureBake Block, this study provides a groundbreaking solution for Transformer and Mamba feature processing, enabling efficient, accurate opportunistic osteoporosis screening. Additionally, using SHAP Plot and feature importance mapping for visual analysis enhances interpretability, offering new ideas and methods for osteoporosis screening in clinical practice, aiding accurate, scientific clinical decision-making and promoting deep learning application in medical data classification.