Prediction of Osteoporosis Risk Level Using Machine Learning Techniques

Low bone density and bone tissue degeneration are prominent symptoms of osteoporosis, which increases the risk of fractures. To avoid long term consequences and enhance patient outcomes, osteoporosis fractures must be identified early and prevented. In this research, we offer a Machine Learning based method for calculating the risk of osteoporosis fractures based on a variety of inputs, including age, gender, weight, height, smoking, alcohol use, diabetes, arthritis, parental fractures, and T-score. We use the Logistic Regression, K-Nearest Neighbour, and Support Vector Machine Machine Learning models to predict the risk level of osteoporosis fractures, which may be high risk, medium risk, or low risk. We evaluate the performance of these models based on a number of factors, such as accuracy, precision, recall, and F1-score. The estimated risk level of osteoporosis fractures is stored in a database together with other input data for future use.