首页|Taiyuan University of Technology Reports Findings in Machine Learning (Explainab le machine-learning-based prediction of QCT/FEA-calculated femoral strength unde r stance loading configuration using radiomics features)
Taiyuan University of Technology Reports Findings in Machine Learning (Explainab le machine-learning-based prediction of QCT/FEA-calculated femoral strength unde r stance loading configuration using radiomics features)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting out of Taiyuan, People's Repu blic of China, by NewsRx editors, research stated, "Finite element analysis can provide precise femoral strength assessment. However, its modeling procedures we re complex and time-consuming." Financial support for this research came from National Natural Science Foundatio n of China. Our news journalists obtained a quote from the research from the Taiyuan Univers ity of Technology, "This study aimed to develop a model to evaluate femoral stre ngth calculated by quantitative computed tomography-based finite element analysi s (QCT/FEA) under stance loading configuration, offering an effective, simple, a nd explainable method. One hundred participants with hip QCT images were selecte d from the Hong Kong part of the Osteoporotic fractures in men cohort. Radiomics features were extracted from QCT images. Filter method, Pearson correlation ana lysis, and least absolute shrinkage and selection operator method were employed for feature selection and dimension reduction. The remaining features were utili zed as inputs, and femoral strengths were calculated as the ground truth through QCT/FEA. Support vector regression was applied to develop a femoral strength pr ediction model. The influence of various numbers of input features on prediction performance was compared, and the femoral strength prediction model was establi shed. Finally, Shapley additive explanation, accumulated local effects, and part ial dependency plot methods were used to explain the model. The results indicate d that the model performed best when six radiomics features were selected. The c oefficient of determination ®, the root mean square error, the normalized root m ean square error, and the mean squared error on the testing set were 0.820, 1016 .299 N, 10.645%, and 750.827 N, respectively. Additionally, these f eatures all positively contributed to femoral strength prediction."
TaiyuanPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
