Prediction of lumbar vertebral strength of elderly men based on quantitative computed tomography images using machine learning

Summary: The parameters extracted from quantitative computed tomography (QCT) images were used to predict vertebral strength through machine learning models, and the highly accurate prediction indicated that it may be a promising approach to assess fracture risk in clinics. Introduction: Vertebral fracture is common in elderly populations. The main factor contributing to vertebral fracture is the reduced vertebral strength. This study aimed to predict vertebral strength based on clinical QCT images by using machine learning. Methods: Eighty subjects with QCT data of lumbar spine were randomly selected from the MrOS cohorts. L1 vertebral strengths were computed by QCT-based finite element analysis. A total of 58 features of each L1 vertebral body were extracted from QCT images, including grayscale distribution, grayscale values of 39 partitioned regions, BMD_QCT, structural rigidity, axial rigidity, and BMD_QCTA_min. Feature selection and dimensionality reduction were used to simplify the 58 features. General regression neural network and support vector regression models were developed to predict vertebral strength. Performance of prediction models was quantified by the mean squared error, the coefficient of determination, the mean bias, and the SD of bias. Results: The 58 parameters were simplified to five features (grayscale value of the 60% percentile, grayscale values of three specific partitioned regions, and BMD_QCTA_min) and nine principal components (PCs). High accuracy was achieved by using the five features or the nine PCs to predict vertebral strength. Conclusions: This study provided an effective approach to predict vertebral strength and showed that it may have great potential in clinical applications for noninvasive assessment of vertebral fracture risk.