基于机器学习与SHAP的全髋关节置换术患者下肢深静脉血栓可解释性预测模型构建研究

doi:10.3969/j.issn.1006-5253.2024.01.003

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (6533 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS) 背景资料

文章导读

摘要目的本研究旨在构建预测全髋关节置换术（THA）患者下肢深静脉血栓（DVT）风险的机器学习模型，并利用shapley additive explanations（SHAP）方法分析影响DVT风险的关键因素。方法回顾性分析2017年1月1日至2022年7月31日在温州市某医院接受THA患者的数据，按4∶〖KG-*2/3〗1随机分为训练集和测试集。采用递归特征消除法及5折交叉验证选取最佳特征；运用6种机器学习算法开发预测模型，并用多种指标评估性能；SHAP方法用于对最优模型进行可解释性分析。结果共416例THA患者纳入最终研究，其中训练集患者333例，测试集患者83例。XGBoost模型在测试集上表现最佳，其敏感度为0.817，特异度为0.783，F1分数为0.860，ROC-AUC为0.800，Brier评分为0.106。SHAP摘要图显示，影响THA术后DVT发生的前5位最重要因素依次为年龄、胆固醇、术后卧床时间、纤维蛋白原、术前血浆D-二聚体浓度。SHAP值的特征依赖图显示，年龄、胆固醇、术后卧床时间以及纤维蛋白原对THA患者DVT的影响均呈现出复杂的非线性关系，其中年龄、术后卧床时间和纤维蛋白原与DVT风险之间表现为倒“U”型关联，而胆固醇呈正相关。单样本特征影响SHAP从个体角度解释了各预测因素对其发生DVT的影响。结论本研究开发了高效可解释的预测THA患者DVT风险的机器学习模型，有助于临床识别高风险患者并给予个性化干预。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	徐青
	余冰
	周佩敏
	戴沈洁
	董晓敏

关键词 ：全髋关节置换术, 深静脉血栓, 机器学习, 预测模型, 模型解释

Abstract：Objective To construct a machine learning model to predict the risk of deep venous thrombosis (DVT) in patients undergoing total hip arthroplasty (THA), and to identify key risk factors influencing DVT using shapley additive explanations (SHAP) method.Methods We retrospectively analyzed data from 416 patients who underwent THA in Wenzhou People′s Hospital from January 1, 2017 to July 31, 2022, and randomly divided them into a training set and a test set in a 4∶〖KG-*2/3〗1 ratio. Recursive feature elimination and five-fold cross-validation were used to select the best features. Six machine learning algorithms were utilized to develop predictive models, and various performance metrics were employed to evaluate them. The SHAP method was used to analyze the interpretability of the optimal model.Results Four hundred and sixteen patients were included in the final study, including 333 in the training set and 83 in the test set. The XGBoost model was the most accurate on the test dataset, achieving a sensitivity of 0.817, specificity of 0.783, F1 score of 0.860, ROC-AUC of 0.800, and a Brier score of 0.106. SHAP summary plots showed that age, cholesterol, postoperative bed time, fibrinogen, and preoperative plasma D-dimer levels were the top five determinants for post-THA DVT. SHAP values feature dependence plots revealed complex non-linear effects of these factors on DVT risk, with age, bed rest, and fibrinogen showing an inverted U-shaped relationship, and cholesterol displaying a positive correlation. Individual SHAP values offered insights into each predictor′s role in DVT risk.Conclusion This study developed an efficient and interpretable machine learning model to predict DVT risk in THA patients, which is helpful for clinical health professionals in identifying high-risk patients and providing personalized intervention.

Key words： total hip arthroplasty deep venous thrombosis machine learning predictive model model interpretation

收稿日期: 2023-09-08

PACS:

基金资助:

通讯作者: 徐青，Email：xuqingabby@126.com

引用本文:

徐青，余冰，周佩敏，戴沈洁，董晓敏. 基于机器学习与SHAP的全髋关节置换术患者下肢深静脉血栓可解释性预测模型构建研究[J]. 中国医院统计, 2024, 31(1): 11-18.
Xu Qing，Yu Bing，Zhou Peimin，Dai Shenjie，Dong Xiaomin. Construction of interpretable prediction model for lower limb deep vein thrombosis in patients undergoing total hip arthroplasty based on machine learning and SHAP. journal1, 2024, 31(1): 11-18.

链接本文:

http://manu58.magtech.com.cn/Jwk_zgyytj/CN/10.3969/j.issn.1006-5253.2024.01.003 或 http://manu58.magtech.com.cn/Jwk_zgyytj/CN/Y2024/V31/I1/11

［1］SCOTT C E H, CLEMENT N D, DAVIS E T, et al. Modern total hip arthroplasty: Peak of perfection or room for improvement?［J］. Bone Joint J, 2022, 104-B(2):189-192. DOI: 10.1302/0301-620X.104B2.BJJ-2022-0007.

［2］楼小华，章炳文，景道远．机械通气患者深静脉血栓的发病率和危险因素分析［J］．中国医院统计，2022，29(1)：18-24．DOI: 10.3969/j.issn.1006-5253.2022.01.004.

［3］BAWA H, WEICK J W, DIRSCHL D R, et al. Trends in deep vein thrombosis prophylaxis and deep vein thrombosis rates after total hip and knee arthroplasty［J］. J Am Acad Orthop Surg, 2018, 26(19):698-705. DOI: 10.5435/JAAOS-D-17-00235.

［4］周玥杉．医院静脉血栓栓塞症综合防治管理体系建设及实践研究［D］．遵义：遵义医科大学，2021．

［5］KLEN J, HORVAT G, BLINC A. Perioperative prevention of venous thromboembolism in abdominal surgery patients based on the caprini or the Padua risk score-a single centre prospective observational study［J］. Life (Basel), 2022, 12(11):1843. DOI: 10.3390/life12111843.

［6］GREENER J G, KANDATHIL S M, 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.

［7］HAUG C J, DRAZEN J M. Artificial intelligence and machine learning in clinical medicine, 2023［J］. N Engl J Med, 2023, 388(13):1201-1208. DOI: 10.1056/NEJMra2302038.

［8］THE LANCET RESPIRATORY MEDICINE. Opening the black box of machine learning［J］. Lancet Respir Med, 2018, 6(11):801. DOI: 10.1016/s2213-2600(18)30425-9.

［9］CHOWDHURY S U, SAYEED S, RASHID I, et al. Shapley-additive-explanations-based factor analysis for dengue severity prediction using machine learning［J］. J Imaging, 2022, 8(9):229. DOI: 10.3390/jimaging8090229.

［10］中华医学会外科学分会血管外科学组．深静脉血栓形成的诊断和治疗指南：第二版［J］．中国血管外科杂志(电子版)，2013，5(1)：23-26． DOI: 10.3969/j.issn.1674-7429.2013.01.009.

［11］LINGYU, LI, . Robust biomarker screening from gene expression data by stable machine learning-recursive feature elimination methods［J］. Comput Biol Chem, 2022, 100:107747. DOI: 10.1016/j.compbiolchem.2022.107747.

［13］HEIT J A, SPENCER F A, WHITE R H. The epidemiology of venous thromboembolism［J］. J Thromb Thrombolysis, 2016, 41(1):3-14. DOI: 10.1007/s11239-015-1311-6.

［14］ZHANG Z, SONG K, YAO Y, et al. Incidence and risk factors for post-thrombotic syndrome in patients with deep vein thrombosis following total knee and hip arthroplasty［J］. J Arthroplasty, 2019, 34(3):560-563. DOI: 10.1016/j.arth.2018.10.013.

［15］孙丹丹．基于德尔菲法的髋关节置换术患者下肢深静脉血栓风险预警模型的构建［D］．呼和浩特：内蒙古医科大学，2020．

［16］KARASAVVIDIS T, BOURIS V, XIANG W, et al. Prophylaxis for venous thromboembolic events in elective total hip and total knee arthroplasty［J］. Curr Pharm Des, 2022, 28(10):771-777. DOI: 10.2174/1381612828666220418090928.

［17］王宇，张攀，韩文锋，等．快速康复理念在髋关节置换围手术期中的应用［J］．实用骨科杂志，2017，23(2)：110-113．

［18］YANG B S, ZHU Y K, LU X, et al. A novel composite indicator of predicting mortality risk for heart failure patients with diabetes admitted to intensive care unit based on machine learning［J］. Front Endocrinol (Lausanne), 2022, 13:917838. DOI: 10.3389/fendo.2022.917838.

［19］NOHARA Y, MATSUMOTO K, SOEJIMA H, et al. Explanation of machine learning models using shapley additive explanation and application for real data in hospital［J］. Comput Methods Programs Biomed, 2022, 214:106584. DOI: 10.1016/j.cmpb.2021.106584.