
浏览全部资源
扫码关注微信
1.大连医科大学研究生院,辽宁 大连 116044
2.北部战区总医院骨科,辽宁 沈阳 110016
收稿:2025-04-21,
纸质出版:2026-04-25
移动端阅览
李俊潮,王洪伟,韩康恩等.骨质疏松性椎体压缩性骨折的风险因素分析及预测模型构建[J].局解手术学杂志,2026,35(04):303-307.
LI Jun-chao,WANG Hong-wei,HAN Kang-en,et al.Analysis of risk factors and construction of a prediction model for osteoporotic vertebral compression fracture[J].JOURNAL OF REGIONAL ANATOMY AND OPERATIVE SURGERY,2026,35(04):303-307.
李俊潮,王洪伟,韩康恩等.骨质疏松性椎体压缩性骨折的风险因素分析及预测模型构建[J].局解手术学杂志,2026,35(04):303-307. DOI: 10.11659/jjssx.04E025107.
LI Jun-chao,WANG Hong-wei,HAN Kang-en,et al.Analysis of risk factors and construction of a prediction model for osteoporotic vertebral compression fracture[J].JOURNAL OF REGIONAL ANATOMY AND OPERATIVE SURGERY,2026,35(04):303-307. DOI: 10.11659/jjssx.04E025107.
目的
2
应用机器学习技术开发骨质疏松性椎体压缩性骨折(OVCF)的风险预测模型,并阐释其决策机制,以促进OVCF的早期风险识别。
方法
2
将2022年1月至2024年12月于北部战区总医院经腰椎MRI证实为OVCF的188例患者纳入病例组,同期未骨折的394例患者作为对照组。通过R语言整合数据,以7∶3的比例分配为训练队列(408例)与验证队列(174例),并筛选出关键预测因子,构建十种机器学习模型,结合SHAP对最优模型进行分析使模型预测可视化并分析模型决策逻辑。
结果
2
通过单因素及多因素分析筛选出性别、外伤史、年龄、饮酒史及体质量指数(BMI)均为OVCF的预测因子。通过十种机器学习证明
Logistic
回归模型的受试者工作特征曲线下面积(
AUC
)值最高(
AUC
=0.851,95%
CI
:0.790~0.911),在风险阈值范围标准化净收益稳定,预测概率与实际概率一致性较高,
Logistic
回归模型为最优模型;基于SHAP构建的可视化分析显示,外伤史、性别、饮酒史、年龄及BMI是对模型预测贡献最大的关键特征。
结论
2
基于机器学习模型可显著提升OVCF诊断效能,
Logistic
回归结合列线图工具有助于临床决策支持。
Objective
2
To develop a risk prediction model for osteoporotic vertebral compression fracture (OVCF) using machine learning (ML) techniques and to interpret its decision-making mechanism, and thereby facilitating early risk identification of OVCF.
Methods
2
A total of 188 patients confirmed with OVCF via lumbar MRI at General Hospital of Northern Theater Command from January 2022 to December 2024 were enrolled as the case group, while 394 patients without fractures during the same period were included as the control group. Data were integrated using R language and randomly divided into training cohort (408 patients) and validation cohort (174 patients) at a ratio of 7∶3. The key predictive factors were selected to construct ten machine learning models. The optimal model was analyzed in combination with SHAP to visualize model predictions, and interpret its decision-making logic.
Results
2
Univariate and multivariate analysis identified that gender, history of trauma, age, history of alcohol consumption, and body mass index (BMI) were the predictive factors for OVCF. Ten machine learning models demonstrated that the
Logistic
regression model achieved the highest value of
area under the receiver operating characteristic curve
(
AUC
) (
AUC
=0.851, 95%
CI
: 0.790 to 0.911), with stable
standardized net benefits across the risk threshold range and high consistency between the predicted probabilities and actual probabilities. The
Logistic
regression model was identified as the optimal model. Additionally, SHAP-based visualization model revealed that the history of trauma, gender, history of alcohol consumption, age, and BMI were the key factors.
Conclusion
2
Machine learning-based models can significantly improve the diagnostic efficacy of OVCF, and
Logistic
regression combined with a nomogram tool is conducive to clinical decision support.
Biver E , Ferrari S . Ostéoporose [J]. Rev Med Suisse , 2020 , 16 ( 676-7 ): 7880 .
Cao Y , Dong B , Li Y , et al . Association of type 2 diabetes with osteoporosis and fracture risk: a systematic review and metaanalysis [J]. Medicine (Baltimore) , 2025 , 104 ( 6 ): e41444 . doi: 10.1097/MD. 0000000000041444 http://dx.doi.org/10.1097/MD.0000000000041444 .
Clynes MA , Harvey NC , Curtis EM , et al . The epidemiology of osteoporosis [J]. Br Med Bull , 2020 , 133 ( 1 ): 105 - 117 . doi: 10.1093/bmb/ldaa005 http://dx.doi.org/10.1093/bmb/ldaa005 .
Mccloskey E , Tan ATH , Schini M . Update on fracture risk assessment in osteoporosis [J]. Curr Opin Endocrinol Diabetes Obes , 2024 , 31 ( 4 ): 141 - 148 . doi: 10.1097/MED.0000000000000871 http://dx.doi.org/10.1097/MED.0000000000000871 .
DE Mattia G , Maffi M , Mazzantini M . Anabolic treatment for osteoporosis and fragility fracture risk:one year in review 2024 [J]. Clin Exp Rheumatol , 2024 , 42 ( 7 ): 1311 - 1316 . doi: 10.55563/clinexprheumatol/7f52vl http://dx.doi.org/10.55563/clinexprheumatol/7f52vl .
Bae WC . Advances and shortfalls in MRI evaluation of osteoporosis [J]. Radiology , 2023 , 307 ( 2 ): e223144 . doi: 10.1148/radiol.223144 http://dx.doi.org/10.1148/radiol.223144 .
Arfat Y , Mittone G , Esposito R , et al . Machine learning for cardiology [J]. Minerva Cardiol Angiol , 2022 , 70 ( 1 ): 75 - 91 . doi: 10.23736/S2724-5683.21.05709-4 http://dx.doi.org/10.23736/S2724-5683.21.05709-4 .
Alabi RO , Mäkitie AA , Pirinen M , et al . Comparison of nomogram with machine learning techniques for prediction of overall survival in patients with tongue cancer [J]. Int J Med Inform , 2021 , 145 : 104313 . doi: 10.1016/j.ijmedinf.2020.104313 http://dx.doi.org/10.1016/j.ijmedinf.2020.104313 .
Greener JG , Kandathil SM , Moffat L , et al . A guide to machine learning for biologists [J]. Nat Rev Mol Cell Biol , 2022 , 23 ( 1 ): 40 - 55 . doi: 10.1038/s41580-021-00407-0 http://dx.doi.org/10.1038/s41580-021-00407-0 .
Lee YW , Choi JW , Shin EH . Machine learning model for predicting malaria using clinical informati on [J]. Comput Biol Med , 2021 , 129 : 104151 . doi: 10.1016/j.compbiomed.2020.104151 http://dx.doi.org/10.1016/j.compbiomed.2020.104151 .
Silva GFS , Fagundes TP , Teixeira BC , et al . Machine Learning for hypertension prediction:a systematic review [J]. Curr Hypertens Rep , 2022 , 24 ( 11 ): 52333 . doi: 10.1007/s11906022012126 http://dx.doi.org/10.1007/s11906022012126 .
Lo Vercio L , Amador K , Bannister JJ , et al . Supervised machine learning tools:a tutorial for clinicians [J]. J Neural Eng , 2020 , 17 ( 6 ). doi: 10.1088/1741-2552/abbff2 http://dx.doi.org/10.1088/1741-2552/abbff2 .
中华医学会骨质疏松和骨矿盐疾病分会 . 原发性骨质疏松症诊疗指南(2022) [J]. 中国全科医学 , 2023 , 26 ( 14 ): 1671 - 1691 . doi: 10.12114/j.issn.1007-9572.2023.0121 http://dx.doi.org/10.12114/j.issn.1007-9572.2023.0121 .
蒙永晖 . 骨质疏松性脊柱骨折的研究进展 [J]. 国际医药卫生导报 , 2022 , 28 ( 9 ): 1330 - 1333 . doi: 10.3760/cma.j.issn.1007-1245. 2022.09.035 http://dx.doi.org/10.3760/cma.j.issn.1007-1245.2022.09.035 .
龙玲美 , 刘伟旺 , 伍媛 . 骨质疏松及骨折风险危险因素和评估工具的应用 [J]. 国际医药卫生导报 , 2023 , 29 ( 16 ): 2230 - 2234 . doi: 10.3760/cma.j.issn.1007-1245.2023.16.003 http://dx.doi.org/10.3760/cma.j.issn.1007-1245.2023.16.003 .
林华 , 包丽华 . 骨质疏松性骨折的骨损害 [J]. 中华医学杂志 , 2022 , 102 ( 13 ): 903 - 907 . doi: 10.3760/cma.j.cn112137-2021 1214-02790 http://dx.doi.org/10.3760/cma.j.cn112137-20211214-02790 .
Barron RL , Oster G , Grauer A , et al . Determinants of imminent fracture risk in postmenopausal women with osteoporosis [J]. Osteoporos Int , 2020 , 31 ( 11 ): 2103 - 2111 . doi: 10.1007/s00198-020-05294-3 http://dx.doi.org/10.1007/s00198-020-05294-3 .
Tarantino U , Baldi J , Scimeca M , et al . The role of sarcopenia with and without fracture [J]. Injury , 2016 , 47 ( Suppl 4 ): S3 - S10 . doi: 10.1016/j.injury.2016.07.057 http://dx.doi.org/10.1016/j.injury.2016.07.057 .
Wu Y , Chao J , Bao M , et al . Predictive value of machine learning on fracture risk in osteoporosis:a systematic review and metaanalysis [J]. BMJ Open , 2023 , 13 ( 12 ): e071430 . doi: 10.1136/bmjopen-2022-071430 http://dx.doi.org/10.1136/bmjopen-2022-071430 .
Uragami M , Matsushita K , Shibata Y , et al . A machine learningbased scoring system and ten factors associated with hip fracture occurrence in the elderly [J]. Bone , 2023 , 176 : 116865 . doi: 10.1016/j.bone.2023.116865 http://dx.doi.org/10.1016/j.bone.2023.116865 .
Dritsas E , Trigka M . Machine learning methods for hypercholesterolemia longterm risk prediction [J]. Sensors (Basel) , 2022 , 22 ( 14 ): 5365 . doi: 10.3390/s22145365 http://dx.doi.org/10.3390/s22145365 .
Nopour R . Comparison of machine learning models to predict complications of bariatric surgery:a systematic review [J]. Health Informatics J , 2024 , 30 ( 3 ): 14604582241285794 . doi: 10.1177/14604582241285794 http://dx.doi.org/10.1177/14604582241285794 .
Uddin S , Ong S , Lu H . Machine learning in project analytics:a datadriven framework and case study [J]. Sci Rep , 2022 , 12 ( 1 ): 15252 . doi: 10.1038/s41598-022-19728-x http://dx.doi.org/10.1038/s41598-022-19728-x .
Lai PK , Fernando A , Cloutier TK , et al . Machinelearning feature selection for predicting high concentration therapeutic antibody aggregation [J]. J Pharm Sci , 2021 , 110 ( 4 ): 1583 - 1591 . doi: 10.1016/j.xphs.2020.12.014 http://dx.doi.org/10.1016/j.xphs.2020.12.014 .
Zhu S , Lu H , Ptak M , et al . Lake waterlevel fluctuation forecasting using machine learning models:a systematic review [J]. Environ Sci Pollut Res Int , 2020 , 27 ( 36 ): 44807 - 44819 . doi: 10.1007/s11356-020-10917-7 http://dx.doi.org/10.1007/s11356-020-10917-7 .
Sandhu S , Lin AL , Brajer N , et al . Integrating a machine learning system Into clinical workflows:qualitative study [J]. J Med Internet Res , 2020 , 22 ( 11 ): e22421 . doi: 10.2196/22421 http://dx.doi.org/10.2196/22421 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621