Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus

Li Siyi; Zeng Yan; Zhong Jian; Liu Qiao; Qin Fen; Hong Yuqin; Zhou Daiquan

doi:10.13406/j.cnki.cyxb.003467

您当前的位置：

首页 >

文章列表页 >

Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus

Clinical research | 更新时间：2025-10-22

- Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus
- Journal of Chongqing Medical University Vol. 49, Issue 4, Pages: 493-499(2024)
- 作者机构：
  
  1.重庆医科大学附属第三医院放射科，重庆 401120
  2.重庆医科大学附属第三医院内分泌科，重庆 401120
- 作者简介：
- 基金信息：
- DOI：10.13406/j.cnki.cyxb.003467
  CLC： R319;R587;R814.42
- Received：01 February 2024，
  
  Revised：2024-03-07，
  
  Accepted：12 March 2024，
  
  Published：28 April 2024
- 稿件说明：
移动端阅览
李思燚,曾燕,钟健,等.机器学习结合CT影像组学预测2型糖尿病患者椎体脆性骨折[J].重庆医科大学学报,2024,49(4):493-499.

Li Siyi,Zeng Yan,Zhong Jian,et al.Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus[J].Journal of Chongqing Medical University,2024,49(4):493-499.
李思燚,曾燕,钟健,等.机器学习结合CT影像组学预测2型糖尿病患者椎体脆性骨折[J].重庆医科大学学报,2024,49(4):493-499. DOI： 10.13406/j.cnki.cyxb.003467.

Li Siyi,Zeng Yan,Zhong Jian,et al.Machine learning combined with computed tomography radiomics in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus[J].Journal of Chongqing Medical University,2024,49(4):493-499. DOI： 10.13406/j.cnki.cyxb.003467.

摘要

目的

探讨机器学习结合CT影像组学特征构建模型预测2型糖尿病（type 2 diabetes mellitus，T2DM）患者椎体脆性骨折的准确性。

方法

回顾性收集140例（新发椎体脆性骨折的T2DM患者70例，对照组70例）患者CT图像和临床资料。另收集18例（椎体脆性骨折的T2DM患者16例，对照组2例）患者的前次CT图像和临床资料作为外部验证集。应用单因素分析、Pearson相关分析、最小冗余度最大相关度算法、二元logistic回归分析和最小绝对值收缩和选择算子模型筛选出最佳特征。基于支持向量机、多层感知器、极端梯度提升（eXtreme Gradient Boosting，XGBoost）构建预测模型。应用受试者工作特征曲线下面积（area under the curve，AUC）对模型效能进行评估。

结果

从每例患者的CT图像中提取了1 037个影像组学特征，然后精简为14个影像组学特征。17个临床特征中性别、年龄、体质指数是预测结果的独立因素。其中XGBoost分类器表现最好，训练集中XGBoost模型的AUC分别为1.000、0.929、1.000；测试集中分别为0.954、0.862、0.969。

结论

基于临床及影像组学特征构建的XGBoost模型可作为预测T2DM患者椎体脆性骨折的一种无创性辅助工具。

Abstract

Objective

To investigate the accuracy of a model established based on machine learning and computed tomography（CT） radiomics features in predicting vertebral fragility fractures in patients with type 2 diabetes mellitus（T2DM）.

Methods

A retrospective analysis was performed for the CT images and clinical data of 140 patients，among whom there were 70 T2DM patients with newly diagnosed vertebral fragility fractures and 70 patients in the control group. The previous CT images and clinical data of 18 patients（16 T2DM patients with vertebral fragility fractures and 2 patients in the control group） were collected as an external validation set. The optimal features were screened by the univariate analysis，the Pearson correlation analysis，minimum redundancy maximum relevance algorithm，the binary logistic regression analysis，and the least absolute shrinkage and selection operator regression model，and then a predictive model was constructed by support vector machine，multi-layer perceptron，and eXtreme gradient boosting（XGBoost） classifiers. The area under the ROC curve（AUC） was used to evaluate the predictive performance of the model.

Results

A total of 1 037 radiomics features were extracted from the CT images of each patient and were then simplified into 14 radiomics features. Among the 17 clinical features，sex，age，and body mass index were independent factors for predicting outcome. XGBoost classifier showed the best performance，and the XGBoost model showed an AUC of 1.000，0.929，and 1.000，respectively，in the training set and an AUC of 0.954，0.862，and 0.969，respectively，in the test set.

Conclusion

The XGBoost model based on clinical and radiomics features can be used as a noninvasive tool for predicting vertebral fragility fractures in T2DM patients.

关键词

Keywords

references

Janghorbani M ， Van Dam RM ， Willett WC ， et al . Systematic review of type 1 and type 2 diabetes mellitus and risk of fracture [J ] . Am J Epidemiol ， 2007 ， 166 （ 5 ）： 495 - 505 ．

Vestergaard P . Discrepancies in bone mineral density and fracture risk in patients with type 1 and type 2 diabetes：a meta-analysis [J ] . Osteoporos Int ， 2007 ， 18 （ 4 ）： 427 - 444 ．

Madsen CM ， Jantzen C ， Norring-Agerskov D ， et al . Excess mortality following hip fracture in patients with diabetes according to age：a nationwide population-based cohort study of 154，047 hip fracture patients [J ] . Age Ageing ， 2019 ， 48 （ 4 ）： 559 - 563 ．

Martinez-Laguna D ， Nogues X ， Abrahamsen B ， et al . Excess of all-cause mortality after a fracture in type 2 diabetic patients：a population-based cohort study [J ] . Osteoporos Int ， 2017 ， 28 （ 9 ）： 2573 - 2581 ．

Sirsat MS ， Fermé E ， Câmara J . Machine learning for brain stroke：a review [J ] . J Stroke Cerebrovasc Dis ， 2020 ， 29 （ 10 ）： 105162 ．

Mayerhoefer ME ， Materka A ， Langs G ， et al . Introduction to radiomics [J ] . J Nucl Med ， 2020 ， 61 （ 4 ）： 488 - 495 ．

Kumar V ， Gu YH ， Basu S ， et al . Radiomics：the process and the challenges [J ] . Magn Reson Imaging ， 2012 ， 30 （ 9 ）： 1234 - 1248 ．

Muehlematter UJ ， Mannil M ， Becker AS ， et al . Vertebral body insufficiency fractures：detection of vertebrae at risk on standard CT images using texture analysis and machine learning [J ] . Eur Radiol ， 2019 ， 29 （ 5 ）： 2207 - 2217 ．

Ling X ， Cummings SR ， Mingwei Q ， et al . Vertebral fractures in Beijing，China：the Beijing osteoporosis project [J ] . J Bone Miner Res ， 2000 ， 15 （ 10 ）： 2019 - 2025 ．

Tebé C ， Martínez-Laguna D ， Carbonell-Abella C ， et al . The association between type 2 diabetes mellitus，hip fracture，and post-hip fracture mortality：a multi-state cohort analysis [J ] . Osteoporos Int ， 2019 ， 30 （ 12 ）： 2407 - 2415 ．

卢艳慧，李春霖 . 老年2型糖尿病合并骨质疏松的临床进展 [J ] . 中华糖尿病杂志， 2020 ， 12 （ 6 ）： 353 - 356 ．

Lu YH ， Li CL . Clinical progress of senile type 2 diabetes mellitus with osteoporosis [J ] . Chin J Diabetes Mellit ， 2020 ， 12 （ 6 ）： 353 - 356 ．

Schwartz AV ， Vittinghoff E ， Bauer DC ， et al . Association of BMD and FRAX score with risk of fracture in older adults with type 2 diabetes [J ] . JAMA ， 2011 ， 305 （ 21 ）： 2184 - 2192 ．

Fraser LA ， Pritchard J ， Ioannidis G ， et al . Clinical risk factors for fracture in diabetes：a matched cohort analysis [J ] . J Clin Densitom ， 2011 ， 14 （ 4 ）： 416 - 421 ．

刘泽群，孙文阁 . 影像组学在胰腺囊性肿瘤中的应用进展 [J ] . 中国医学计算机成像杂志， 2022 ， 28 （ 2 ）： 221 - 224 ．

Liu ZQ ， Sun WG . Advances in radiomics ofPancreatic cystic neoplasm [J ] . Chin Comput Med Imag ， 2022 ， 28 （ 2 ）： 221 - 224 ．

Chen YX ， Yang TY ， Gao XF ， et al . Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis [J ] . Front Med ， 2022 ， 16 （ 3 ）： 496 - 506 .

Chu SJ ， Jiang AJ ， Chen LZ ， et al . Machine learning algorithms for predicting the risk of fracture in patients with diabetes in China [J ] . Heliyon ， 2023 ， 9 （ 7 ）： e18186 .

Yosibash Z ， Trabelsi N ， Buchnik I ， et al . Hip Fracture Risk Assessment in Elderly and Diabetic Patients：Combining Autonomous Finite Element Analysis and Machine Learning [J ] . J Bone Miner Res ， 2020 ， 38 （ 6 ）： 876 - 886 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research advances in plasma lipid metabolites for predicting the progression of gestational diabetes mellitus to postpartum type 2 diabetes mellitus

Advances in the application of ultrasound combined with radiomics and artificial intelligence in the diagnosis and prognostic evaluation of gastrointestinal stromal tumors

Risk prediction of early esophageal varices in patients with liver cirrhosis based on interpretable machine learning

Optimization strategy and practice analysis of airway management based on artificial intelligence

Prevalence rate of type 2 diabetes mellitus and related influencing factors in the Yi population in Jinning District，Yunnan Province，China

Related Author

Zhang Shenrui

Xiao Xinhua

Zheng Jia

Liu Yang

He Xuemei

Wang Yuwen

Fan Jie

Yang Chun

Related Institution

Department of Endocrinology，Peking University First Hospital

Department of Endocrinology，Peking Union Medical College Hospital

Department of Ultrasound，The First Affiliated Hospital of Chongqing Medical University

College of Public Health，Chongqing Medical University

School of Public Health Emergency Management，Chongqing Medical and Pharmaceutical College

⁰