基于机器学习构建住院患者深静脉血栓风险预测模型的系统评价

doi:10.16460/j.issn1008-9969.2023.23.044

摘要/Abstract

摘要： 目的系统评价基于机器学习构建的住院患者深静脉血栓风险预测模型。方法检索PubMed、Embase、CHINHAL、Cochrane Library、Web of Science、中国知网、万方数据库中关于机器学习对住院患者深静脉血栓预测模型构建相关研究,检索时限为建库至2023年3月。2名研究者独立完成文献筛选并提取资料,使用预测模型构建研究数据提取和质量评价清单对纳入文献进行质量评价。结果最终纳入11篇研究,包括28个机器学习模型,ROC曲线下面积为0.710~0.976。年龄、血栓史、住院时间、用药史、D-二聚体等实验室指标是主要预测因子。结论机器学习可更准确识别住院患者发生深静脉血栓的风险,预测性能优于传统风险预测模型。文献整体偏倚风险较低,预测模型适用性水平一般。

关键词: 深静脉血栓, DVT, 机器学习, 护理, 预测模型, 系统评价

Abstract: Objective To systematically evaluate the risk prediction model for deep vein thrombosis in hospitalized patients based on machine learning. Methods We conducted literature research in PubMed, Embase, CHINHAL, Cochrane Library, Web of Science, CNKI, and Wanfang databases for literature on risk prediction models for deep vein thrombosis in hospitalized patients constructed by machine learning. The search period spanned from the inception to March 2023. Two researchers completed literature screening and data extraction independently, and used predictive models to construct a research data extraction and quality evaluation checklist (CHARMS) to evaluate the quality of the included literature and screened high-quality literature for discussion. Results Totally 11 high-quality studies were collected, including 28 machine learning models, with an area under the ROC curve ranging from 0.710 to 0.976. Laboratory indicators such as age, VTE history, length of hospital stay, medication history, and D-dimer were are the main predictive factors. Conclusions Risk prediction models constructed using machine learning can accurately identify the risk of DVT events in hospitalized patients, and its predictive performance is superior to traditional risk prediction models. The available literature on the topic exhibits a low overall risk of bias, however, the applicability level of the prediction model is considered average.

Key words: Deep vein thrombosis, DVT, machine learning, nursing, predictive model, systematic review

中图分类号:

R471

杨楠楠, 蒋慧萍, 史婷奇. 基于机器学习构建住院患者深静脉血栓风险预测模型的系统评价[J]. 护理学报, 2023, 30(23): 44-49.

YANG Nan-nan, JIANG Hui-ping, SHI Ting-qi. Machine learning-based a risk predictive model for deep vein thrombosis in hospitalized patients: a systematic review[J]. Journal of Nursing, 2023, 30(23): 44-49.

参考文献

[1] 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(第三版)[J].中华普通外科杂志, 2017, 32(9):807-812. DOI:10.3760/cma.j.issn.1007-631X.2017.09. 032.
[2] 邵翔,翟振国,王辰.医院相关性静脉血栓栓塞症[J].中华医学杂志,2018,98(46):3792-3794.DOI:10.3760/cma.j.issn.0376-2491.2018.46.014.
[3] Valerio L, Barco S, Jankowski M, et al.Quality of life 3 and 12 months following acute pulmonary embolism: analysis from a prospective multicenter cohort study[J]. Chest, 2021,9(6):2428-2438. DOI:10.1016/j.chest.2021.01.071.
[4] 张煜,张春艳,金玉,等.内科危重症患者深静脉血栓预防审查指标的制定及障碍因素分析[J].护理学报, 2020,27(4):37-41.DOI:10.16460/j.issn1008-9969.2020.04.037.
[5] Wang P, Wang Y, Yuan Z, et al, Venous thromboembolism risk assessment of surgical patients in Southwest China using real-world data: establishment and evaluation of an improved venous thromboembolism risk model[J]. BMC Med Inform Decis Mak, 2022,22(1):59.DOI:10.1186/s12911-022-01795-9.
[6] 刘雨安,杨小文,李乐之.机器学习在疾病预测的应用研究进展[J]. 护理学报,2021, 28(7):30-34.DOI:10.16460/j.issn1008-9969.2021.07.030.
[7] 王贝伦. 机器学习[M].南京:南京东南大学出版社, 2021:355.
[8] 王晶,李玲利,赵春林,等.机器学习在构建护理风险预测模型中的研究进展[J].护士进修杂志,2022, 37(23):2167-2171.DOI:10.16821/j.cnki.hsjx.2022.23.011.
[9] Moher D, Liberati A, Tetzlaff J, et al.Preferred reporting items for systematic reviews and Meta-analyses: the PRISMA statement[J]. PloS Med, 2009,6(7):e1000097. DOI:10. 1371/journal.pmed.1000097.
[10] Moons KG, de Groot JA, Bouwmeester W, et al. Critical appraisal and data extraction for systematic reviews of prediction modelling studies: the CHARMS checklist[J]. PLoS Med, 2014, 11(10):e1001744. DOI:10.1371/journal.pmed.1001744.
[11] 徐泽,张贤祚,张林林,等.全膝关节置换术后深静脉血栓预测模型的建立[J].中国矫形外科杂志,2022,30(23):2123-2128.DOI:10.3977/j.issn.1005-8478.2022.23.03.
[12] 刘佳丽,冯自波,谢燕妮,等.极限梯度提升算法风险预测模型在全膝关节置换术后深静脉血栓中的预测性能[J].血管与腔内血管外科杂志,2022, 8(5):563-567;586.DOI:10.19418/j.cnki.issn2096-0646.2022.05.11.
[13] Wang X, Xi H, Geng X, et al.Artificial intelligence-based prediction of lower extremity deep vein thrombosis risk after knee/hip arthroplasty[J]. Clin Appl Thromb Hemost, 2023(29):10760296221139263.DOI:10.1177/10760296221139263.
[14] Shohat N, Ludwick L, Sherman MB, et al.Using machine learning to predict venous thromboembolism and major bleeding events following total joint arthroplasty[J]. Sci Rep, 2023,13(1):2197.DOI:10.1038/s41598-022-26032-1.
[15] Wang KY, Ikwuezunma I, Puvanesarajah V, et al.Using predictive modeling and supervised machine learning to identify patients at risk for venous thromboembolism following posterior lumbar fusion[J]. Global Spine J,2023,13(4):1097-1103. DOI:10.1177/21925682211019361.
[16] Nudel J, Bishara AM, de Geus SWL, et al. Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery:an analysis of the MBSAQIP database[J]. Surg Endosc,2021,35(1):182-191.DOI:10.1007/s00464-020-07378-x.
[17] He L, Luo L, Hou X, et al.Predicting venous thromboembolism in hospitalized trauma patients: a combination of the Caprini score and data-driven machine learning model[J]. BMC Emerg Med,2021,21(1):60.DOI:10.1186/s12873-021-00447-x.
[18] Liu H, Yuan H, Wang Y, et al.Prediction of venous thromboembolism with machine learning techniques in young-middle-aged inpatients[J]. Sci Rep, 2021,11(1):12868. DOI:10.1038/s41598-021-92287-9.
[19] Ryan L, Mataraso S, Siefkas A, et al.A machine learning approach to predict deep venous thrombosis among hospitalized patients[J]. Clin Appl Thromb Hemost, 2021(27):1076029621991185. DOI:10.1177/1076029621991185.
[20] Jin S, Qin D, Liang BS, et al.Machine learning predicts cancer-associated deep vein thrombosis using clinically available variables[J]. Int J Med Inform,2022(161):104733. DOI:10.1016/j.ijmedinf.2022.104733.
[21] Lei H, Zhang M, Wu Z, et al, Development and validation of a risk prediction model for venous thromboembolism in lung cancer patients using machine learning[J]. Front Cardiovasc Med,2022(9):845210. DOI:10.3389/fcvm.2022.845210.
[22] Meng L, Wei T, Fan R, et al, Development and validation of a machine learning model to predict venous thromboembolism among hospitalized cancer patients[J]. Asia Pac J Oncol Nurs, 2022,9(12):100128. DOI:10.1016/j.apjon.2022.100128.
[23] 梁菲,王瑜,武海英.妊娠期深静脉血栓的临床特点、危险因素分析及预测模型构建[J].现代妇产科进展,2022,31(1):50-53.DOI:10.13283/j.cnki.xdfckjz.2022.01.008.
[24] Andaur Navarro CL, Damen JAA, van Smeden M, et al, Systematic review identifies the design and methodological conduct of studies on machine learning-based prediction models[J]. J Clin Epidemiol, 2023(154):8-22. DOI:10.1016/j.jclinepi.2022.11.015.
[25] Hayssen H, Cires-Drouet R, Englum B, et al, Systematic review of venous thromboembolism risk categories derived from Caprini score[J]. J Vasc Surg Venous Lymphat Disord, 2022,10(6):1401-1409.e7. DOI:10.1016/j.jvsv.2022.05.003.
[26] 旷小羿,侯惠如.基于电子病历数据的风险预测模型在临床护理中的应用现状[J].护理学报,2020,27(16):21-24.DOI:10.16460/j.issn1008-9969.2020.16.021.
[27] 李芸,朱剑清,王惠英,等.基于电子病历的静脉血栓栓塞症风险评估和防控[J].中国病案,2017,18(9):49-51.
[28] Lu Y, Forlenza E, Cohn MR, et al, Machine learning can reliably identify patients at risk of overnight hospital admission following anterior cruciate ligament reconstruction[J]. Knee Surg Sports Traumatol Arthrosc, 2021, 29(9):2958-2966. DOI:10.1007/s00167-020-06321-w.
[29] Kumar V, Roche C, Overman S, et al.Using machine learning to predict clinical outcomes after shoulder arthroplasty with a minimal feature set[J].J Shoulder Elbow Surg, 2021,30(5):e225-e236. DOI:10.1016/j.jse.2020.07.042.
[30] 张舒雯,何晖,闫寒冰,等.静脉血栓栓塞症风险评估模型在临床实践中的研究进展[J].中国医药导报,2023,20(7):63-67.DOI:10.20047/j.issn1673-7210.2023.07.13.
[31] 黄光成,周良,石建伟,等.机器学习算法在疾病风险预测中的应用与比较[J].中国卫生资源,2020, 23(4):432-436.DOI:10.13688/j.cnki.chr.2020.19608.

相关文章 15

[1]	张静, 彭焕椽, 陈佳, 鲁永锦, 刘克玄, 侯晓敏. 成人体外循环心脏手术患者预防手术部位感染的最佳证据总结[J]. 护理学报, 2025, 32(4): 41-47.
[2]	郑小静, 严红虹, 李慧景, 陈思涓, 陈秀梅. 肝细胞癌伴低血糖症风险预测模型的构建与验证[J]. 护理学报, 2025, 32(4): 53-58.
[3]	刘璐, 朱钰, 曹义, 张华, 彭玉娜. 腹腔热灌注化疗患者术中实施不同目标体温管理的效果观察[J]. 护理学报, 2025, 32(4): 59-63.
[4]	李疆伟, 王树君, 李长仔, 胡宝山, 焦桂梅, 张卫红. 基于压力应对理论的护理干预对结直肠癌术后永久性肠造口患者心理压力、负性情绪及自我管理的影响[J]. 护理学报, 2025, 32(4): 64-69.
[5]	龚祖华, 孙丽, 谭璇, 张悦, 施丹, 程娟娟. 肝胆外科术后患者基础体征采集-比对-识别隐匿型病情变化的效果观察[J]. 护理学报, 2025, 32(4): 74-78.
[6]	伍丽华, 吴心雨, 赖湘瑜, 邓宝贵, 黄泽青, 赵耀, 廖源, 沈彩萍, 李瑜. 人工关节置换术后患者深静脉血栓风险预测模型的系统评价[J]. 护理学报, 2025, 32(3): 12-16.
[7]	李苗苗, 熊莉娟, 齐磊, 李敏, 向御婷. 基于Ridit分析法和秩和比法的疾病诊断相关分组在护理绩效管理中的应用[J]. 护理学报, 2025, 32(3): 22-26.
[8]	焦雪萍, 王志稳, 韩舒羽. ICU老年患者躁动行为的干预研究进展[J]. 护理学报, 2025, 32(3): 38-42.
[9]	李若雨, 刘鑫, 林萍, 陈丹, 林桦. 出院患者用药安全管理的最佳证据总结[J]. 护理学报, 2025, 32(3): 50-55.
[10]	杨小娟, 毛孝容, 王静, 江华, 李蓉, 樊宇, 文青, 李林章, 陈晓容. 成人重度烧伤患者早期肠内营养管理的最佳证据总结[J]. 护理学报, 2025, 32(3): 56-61.
[11]	朱天顺, 朱可可, 薛会元, 焦聪聪, 魏长慧, 王贺. 信息框架效应理论在健康管理领域应用的范围综述[J]. 护理学报, 2025, 32(2): 44-49.
[12]	刘硕怡, 熊莉娟, 李凌, 王玉梅, 何嘉, 李鑫, 袁淑蕾, 郭雪琴, 王暘婧, 张慧娟. 老年住院患者衰弱预防及管理临床实践指南的质量评价及内容分析[J]. 护理学报, 2025, 32(2): 50-55.
[13]	李嘉琪, 莫文娟, 王一棋, 王洁, 李梦楠, 刘兴, 冯佳. 基于COSMIN方法对慢性疼痛患者恐动症坦帕评分表的系统评价[J]. 护理学报, 2025, 32(2): 56-62.
[14]	李雪, 廖常菊, 张健, 丁娟, 陈晓丽, 胡玉庭. 三级甲等医院ICU护士睡眠障碍的风险预测模型构建及验证[J]. 护理学报, 2025, 32(2): 63-69.
[15]	闫亚铃, 乐美妮, 姚桃琴, 王雪莲, 姜建玲, 辛艺. 老年胃肠肿瘤患者围手术期衰弱管理方案的构建[J]. 护理学报, 2025, 32(2): 74-78.

Metrics

Viewed

Full text

Abstract

Cited

Shared