Loading…

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

Hip fracture is the most common complication of osteoporosis, and its major contributor is compromised femoral strength. This study aimed to develop practical machine learning models based on clinical quantitative computed tomography (QCT) images for predicting proximal femoral strength. Eighty subj...

Full description

Saved in:
Bibliographic Details
Published in:Journal of orthopaedic research 2023-01, Vol.41 (1), p.170-182
Main Authors: Zhang, Meng, Gong, He, Zhang, Ming
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hip fracture is the most common complication of osteoporosis, and its major contributor is compromised femoral strength. This study aimed to develop practical machine learning models based on clinical quantitative computed tomography (QCT) images for predicting proximal femoral strength. Eighty subjects with entire QCT data of the right hip region were randomly selected from the full MrOS cohorts, and their proximal femoral strengths were calculated by QCT‐based finite element analysis (QCT/FEA). A total of 50 parameters of each femur were extracted from QCT images as the candidate predictors of femoral strength, including grayscale distribution, regional cortical bone mapping (CBM) measurements, and geometric parameters. These parameters were simplified by using feature selection and dimensionality reduction. Support vector regression (SVR) was used as the machine learning algorithm to develop the prediction models, and the performance of each SVR model was quantified by the mean squared error (MSE), the coefficient of determination (R2), the mean bias, and the SD of bias. For feature selection, the best prediction performance of SVR models was achieved by integrating the grayscale value of 30% percentile and specific regional CBM measurements (MSE ≤ 0.016, R2≥ 0.93); and for dimensionality reduction, the best prediction performance of SVR models was achieved by extracting principal components with eigenvalues greater than 1.0 (MSE ≤ 0.014, R2≥ 0.93). The femoral strengths predicted from the well‐trained SVR models were in good agreement with those derived from QCT/FEA. This study provided effective machine learning models for femoral strength prediction, and they may have great potential in clinical bone health assessments. This study found the dominant parameters from clinical quantitative computed tomography images and used them to develop machine learning models for assessing femoral strength. Our results suggested that the well‐trained machine learning models could predict femoral strength effectively, and their performance was comparable to that of finite element analysis. Because of the relatively high computational efficiency, this computer‐aided diagnostic approach shows great potential in clinical applications, and can be utilized in routine bone health assessments.
ISSN:0736-0266
1554-527X
DOI:10.1002/jor.25334