中国组织工程研究 ›› 2024, Vol. 28 ›› Issue (33): 5295-5301.doi: 10.12307/2024.665

• 数字化骨科 digital orthopedics • 上一篇    下一篇

机器学习分析肱骨近端内侧柱不稳定骨折术后失效的风险因素

徐大星1,2,纪木强2,涂泽松2,3,许伟鹏3,徐伟龙4,牛 维5   

  1. 1广州中医药大学同等学力申请博士学位人员,广东省广州市   510006;2佛山市中医院三水医院骨科,广东省佛山市   528100;3佛山市中医院骨科,广东省佛山市 528000;4深圳平乐骨科医院骨科,广东省深圳市   518122;5广东省中医院关节外科,广东省广州市   510120
  • 收稿日期:2023-07-12 接受日期:2023-08-21 出版日期:2024-11-28 发布日期:2024-01-30
  • 通讯作者: 牛维,博士,主任中医师,博士生导师,广东省中医院关节外科,广东省广州市 510120
  • 作者简介:徐大星,男,1984年生,山西省晋中市人,汉族,广州中医药大学在职博士,副主任中医师,主要从事骨折创伤的流行病学以及中医药治疗骨折、关节疾病研究。
  • 基金资助:
    广东省医学科学技术研究基金项目(B2023493),项目负责人:徐大星;佛山市自筹经费类科技创新入库项目(2220001004493),项目负责人:徐大星;佛山市“十四五”中医重点专科建设项目(202KJS09,佛山市中医院三水医院中医骨伤科),项目负责人:涂泽松

Machine learning to analyze risk factors for postoperative failure of proximal humeral fractures with medial column instability

Xu Daxing1, 2, Ji Muqiang2, Tu Zesong2, 3, Xu Weipeng3, Xu Weilong4, Niu Wei5   

  1. 1Applicants with Equivalent Academic Qualifications for Doctoral Degrees, Guangzhou University of Chinese Medicine, Guangzhou 510006, Guangdong Province, China; 2Department of Orthopedics, Sanshui Branch of Foshan Hospital of Traditional Chinese Medicine, Foshan 528100, Guangdong Province, China; 3Department of Orthopedics, Foshan Hospital of Traditional Chinese Medicine, Foshan 528000, Guangdong Province, China; 4Department of Orthopedics, Shenzhen Pingle Orthopedics Hospital, Shenzhen 518122, Guangdong Province, China; 5Department of Articular Surgery, Guangdong Provincial Hospital of Chinese Medicine, Guangzhou 510120, Guangdong Province, China
  • Received:2023-07-12 Accepted:2023-08-21 Online:2024-11-28 Published:2024-01-30
  • Contact: Niu Wei, MD, Chief physician, Doctoral supervisor, Department of Articular Surgery, Guangdong Provincial Hospital of Chinese Medicine, Guangzhou 510120, Guangdong Province, China
  • About author:Xu Daxing, MD, Associate chief physician, Applicants with Equivalent Academic Qualifications for Doctoral Degrees, Guangzhou University of Chinese Medicine, Guangzhou 510006, Guangdong Province, China; Department of Orthopedics, Sanshui Branch of Foshan Hospital of Traditional Chinese Medicine, Foshan 528100, Guangdong Province, China
  • Supported by:
    Medical Science and Technology Research Foundation in Guangdong Province, No. B2023493 (to XDX); Self-Financed Science and Technology Innovation Projects in Foshan, No. 2220001004493 (to XDX); Key Specialty Construction Project of Traditional Chinese Medicine during the 14th Five-Year Plan in Foshan (Department of Orthopedics, Sanshui Branch of Foshan Hospital of Traditional Chinese Medicine), No. 202KJS09 (to TZS)

摘要:


文题释义:

机器学习:由计算机程序学习数据的特征训练得到最终模型来提供预测结果。机器学习具有超越传统统计方法的潜力,在处理高维度数据时能够捕获多个预测变量之间的非线性和复杂相互作用,提高模型预测能力。
SHAP解释工具:衡量每个变量加入模型的边际贡献度,是当前模型解释的最佳方法之一。对模型进行可视化的全局解释、局部解释,不但可以明确模型中各个变量的重要情况,也可解释变量对模型决策的影响方向。


背景:切开复位解剖锁定钢板内固定是治疗肱骨近端内侧柱不稳定型骨折的首选,但骨折复位失效是术后主要并发症之一,准确的风险因素评估有利于筛选高风险患者和临床决策的选择。

目的:通过机器学习算法构建4种预测模型,分析筛选出最优模型并按照风险变量对结局变量影响的权重评分排序,探讨其对临床诊疗的指导意义。
方法:纳入2012年6月至2022年6月期间佛山市中医院收治的262例肱骨近端内侧柱不稳定型骨折患者,年龄(60.6±10.2)岁,所有患者均接受切开复位锁定钢板手术治疗,根据术后5个月随访是否发生复位失效分为复位失效组(n=64)和复位维持组(n=198)。收集患者的临床资料,确定模型变量及其分类,将数据集随机按照7∶3比例分为训练集和测试集,训练集按照5折交叉检验获取最优超参数,构建逻辑回归、随机森林、支持向量机、极端梯度提升4种机器学习预测模型,在测试集用AUC、正确率、灵敏度、特异度和F1得分观察不同算法的表现,综合评价模型的预测性能。将表现最佳的模型利用SHAP评估重要风险变量,并对其临床指导意义进行评价。

结果与结论:①两组间三角肌结节指数、骨折类型术前骨折端合并内翻畸形、肱骨头下干骺端碎片长度、术后复位情况、肱骨近端内侧柱皮质支撑情况、肱骨距螺钉置入情况比较差异均有显著性意义(P < 0.05);②4种机器模型中综合表现能力最好的是极端梯度提升,其受试者工作特征曲线下面积AUC、准确度和F1分数分别为0.885,0.885和0.743,其次是随机森林和支持向量机,两种模型表现能力基本持平,逻辑回归的综合表现能力最差;在最优模型中利用SHAP解释工具发现三角肌结节指数、肱骨内侧柱皮质支撑、骨折类型、骨折复位质量、肱骨距螺钉状态是骨折术后复位失效的重要影响因素;③利用机器学习分析临床问题的准确性优于传统逻辑回归分析方法,在处理高维度数据时机器学习方法可以很好地解决多变量交互和共线性问题;利用SHAP解释工具不但可以明确各个变量的重要性,也可得到各变量中哑变量对结局影响的详细信息。

https://orcid.org/0000-0001-7021-2752 (徐大星) 

中国组织工程研究杂志出版内容重点:人工关节;骨植入物;脊柱;骨折;内固定;数字化骨科;组织工程

关键词: 肱骨近端骨折, 内侧柱不稳定, 机器学习, 影响因素, SHAP解释工具

Abstract: BACKGROUND: Internal fixation and open reduction with locking plate is the main treatment for proximal humeral fractures with medial column instability. However, reduction failure is one of the main postoperative complications, and accurate risk factor assessment is beneficial for screening high-risk patients and clinical decision selection.
OBJECTIVE: To construct four types of prediction models by different machine learning algorithms, compare the optimal model to analyze and sort the risk variables according to their weight scores on the impact of outcome, and explore their significance in guiding clinical diagnosis and treatment.
METHODS: 262 patients with proximal humeral fractures with medial column instability, aged (60.6±10.2) years, admitted to Foshan Hospital of Traditional Chinese Medicine between June 2012 and June 2022 were included. All patients underwent open reduction with locking plate surgery. According to the occurrence of reduction failure at 5-month follow-up, the patients were divided into a reduction failure group (n=64) and a reduction maintenance group (n=198). Clinical data of patients were collected, and model variables and their classification were determined. The data set was randomly divided into a training set and a test set according to a 7:3 ratio, and the optimal hyperparameters were obtained in the training set according to a 5-fold cross-over test. Four machine learning prediction models of logistic regression, random forest, support vector machine, and XGBoost were constructed, and the performance of different algorithms was observed in the test set using AUC, correctness, sensitivity, specificity, and F1 scores, so as to comprehensively evaluate the prediction performance of the models. The best-performing model was evaluated using SHAP to assess important risk variables and to evaluate its clinical guidance implications.
RESULTS AND CONCLUSION: (1) There were significant differences between the two groups in deltoid tuberosity index, fracture type, fracture end with varus deformity before operation, fragment length of inferior metaphyseal of humerus, postoperative reduction, cortical support of medial column of proximal humerus, and insertion of calcar screw (P < 0.05). (2) The best-combined performance of the four machine models was XGBoost. The AUC, accuracy, and F1 scores were 0.885, 0.885, and 0.743, respectively; followed by random forest and support vector machine, with both models performing at approximately equal levels. Logistic regression had the worst combined performance. The SHAP interpretation tool was used in the optimal model and results showed that deltoid tuberosity index, medial humeral column cortical support, fracture type, fracture reduction quality, and the status of the calcar screw were important influencing fators for postoperative fracture reduction failure. (3) The accuracy of using machine learning to analyze clinical problems is superior to that of traditional logistic regression analysis methods. When dealing with high-dimensional data, the machine learning approach can solve multivariate interaction and covariance problems well. The SHAP interpretation tool can not only clarify the importance of individual variables but also obtain detailed information on the impact of dummy variables in each variable on the outcome.

Key words: proximal humeral fracture, medial column instability, machine learning, influencing factor, SHAP interpretation tool

中图分类号: