The raw clinical data used for constructing the osteoporosis prediction model

With the development of artificial intelligence, new possibilities have been opened up for the diagnosis and prevention of osteoporosis. We have successfully constructed an osteoporosis risk prediction model using deep learning algorithms, combined with demographic data and laboratory results. To further promote human health, we will publicly disclose the dataset we used, which includes 2,186 cases of males over 50 years old and postmenopausal females. The dataset records demographic data and laboratory results, and patients are classified into three categories based on dual energy X-ray results: bone mineral density, osteopenia, and osteoporosis. This dataset can be used for AI model training and disease prediction.