北京生物医学工程

泌尿肿瘤住院患者DVT发生风险相关性因素及预后模型研究

Research on risk-related factors and prognostic models of deep vein thrombosis in patients with urinary tumors during hospitalization

作者：王正源张姬黄宗浩王奕

单位：复旦大学附属肿瘤医院信息中心-复旦大学上海医学院肿瘤学系(上海 200032)<br />复旦大学附属肿瘤医院护理部-复旦大学上海医学院肿瘤学系(上海 200032)<br />上海肿瘤疾病人工智能工程技术研究中心(上海 200032)<br />通信作者：王奕，高级工程师。E-mail: tonywang@shca.org.cn

关键词：泌尿肿瘤；深静脉血栓形成；预后；分类器

分类号：R318

出版年·卷·期（页码）：2023·42·2（144-151）

摘要：

目的基于泌尿外科肿瘤患者，对其深静脉血栓形成（deep vein thrombosis, DVT）发生风险相关性因素及预后模型进行探究，以此辅助临床更好地进行风险评估，作出准确的预后判断并采取相应预防措施。方法抽取选用复旦大学附属肿瘤医院2019年12月—2021年12月收治的泌尿外科肿瘤患者住院期间建立的3 814条DVT发生风险评估表单记录的数据。首先，对数据样本进行相关性因素提取，并行数据清洗、脱敏及结构化处理；然后，使用Mann-Whitney U检验对特征数据进行单因素分析，使用Logistic回归模型进行回归性分析，得到患者DVT发生风险的显著性相关因素；最后，基于机器学习支持向量机(support vector machine, SVM）算法和决策树算法，采用交叉验证方法训练分类器并检验相关性因素对患者DVT发生风险的预测能力。结果 Mann-Whitney U检验分析结果显示，体质量指数（BMI）、活动、特殊风险以及外科手术与患者DVT发生风险相关（P<0.05）。Logistic回归分析显示，BMI、活动、特殊风险以及外科手术与患者DVT发生风险显著相关（P<0.05），SVM分类器分类结果显示最高分类准确率为87.6%，最大曲线下的面积(area under curve, AUC）为0.904，即这4种特征可以对患者的DVT发生风险作出较为准确的预测。结论 BMI、活动、特殊风险以及外科手术4种因素是泌尿外科肿瘤患者DVT发生风险的显著性相关因素。

Objective Based on urological tumor patients to explore the risk-related factors and prognostic models of Deep Vein Thrombosis (DVT), to assist the clinic can better assess the risk, make accurate prognostic judgments, and take corresponding preventive measures. Methods The data collected from 3814 DVT risk assessment forms established during the hospitalization of urological tumor patients admitted to Fudan University Shanghai Cancer Center from December 2019 to December 2021 were selected. First, extract the relevant factors of the data sample, parallel data cleaning, desensitization and structuring; then, use the Mann-Whitney U test to perform single factor analysis on the characteristic data, and use the logistic regression model to perform regression analysis to obtain the urology Significant factors related to the risk of DVT in cancer patients; finally, based on machine learning support vector machine (SVM) algorithm and decision tree algorithm, The cross-validation method is used to train the classifier and test the predictive ability of related factors on the risk of DVT in urological tumor patients. Results Mann-Whitney U test analysis showed that body mass index (BMI), activity, special risks, and surgery were related to the risk of DVT in patients with urological tumors (P<0.05). Logistic regression analysis showed that BMI, activity, special risks, and surgical procedures were significantly related to the risk of DVT in patients with urological tumors (P<0.05). The classification results of SVM classifier showed that the highest classification accuracy rate was 87.6%, the largest curve The area under curve (AUC) is 0.904, which means that these four characteristics can make a more accurate prediction of the risk of DVT in patients with urinary tumors. Conclusions The four factors of BMI, activity, special risk, and surgery are significant factors related to the risk of DVT in patients with urinary tumors.

参考文献：

[1] 叶定伟, 秦晓健. “互联网+”时代泌尿肿瘤多学科诊治模式探索——“中国泌尿肿瘤MDT会诊平台”简介[J]. 现代泌尿外科杂志, 2018, 23(1): 1-2.
[2] 祁莎莎, 曹鑫, 徐宁宁, 等. 深静脉血栓关键基因AP2B1和miRNAs及其相关通路的筛选[J]. 北京生物医学工程, 2022, 41(4): 344-351, 367.
Qi SS, Cao X, Xu NN, et al. Screening of key gene AP2B1, miRNAs and related pathways in deep venous thrombosis[J]. Beijing Biomedical Engineering, 2022, 41(4): 344-351, 367.
[3] 杨扬扬, 张晓红, 申丽. 3种风险评估量表对泌尿外科术后患者深静脉血栓形成的风险预测分析[J]. 中国民间疗法, 2021, 29(16): 91-94.
[4] Guanella R, Ducruet T, Johri M, et al. Economic burden and cost determinants of deep vein thrombosis during 2 years following diagnosis: a prospective evaluation[J]. Journal of Thrombosis and Haemostasis, 2011, 9(12): 2397-2405.
[5] 蔡永俊, 闫士举, 宋成利. 深静脉取栓器流体动力碎栓数值模拟[J]. 北京生物医学工程, 2018, 37(1): 27-33.
Cai YJ, Yan SJ, Song CL. Fluid dynamics numerical simulation of thrombectomy device for deep vein[J]. Beijing Biomedical Engineering, 2018, 37(1): 27-33.
[6] Walker AJ, Card TR, West J, et al. Incidence of venous thromboembolism in patients with cancer - a cohort study using linked United Kingdom databases[J]. European Journal of Cancer, 2013, 49(6): 1404-1413.
[7] Gee E. The National VTE Exemplar Centres Network response to implementation of updated NICE guidance: venous thromboembolism in over 16s: reducing the risk of hospital-acquired deep vein thrombosis or pulmonary embolism (NG89)[J]. British Journal of Haematology, 2019, 186(5): 792-793.
[8] Falck-Ytter Y, Francis CW, Johanson NA, et al. Prevention of VTE in orthopedic surgery patients: antithrombotic therapy and prevention of thrombosis, 9th ed: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines[J]. Chest, 2012, 141(2): e278S-e325S.
[9] Lobastov K, Barinov V, Schastlivtsev I, et al. Validation of the Caprini risk assessment model for venous thromboembolism in high-risk surgical patients in the background of standard prophylaxis[J]. Journal of Vascular Surgery: Venous and Lymphatic Disorders, 2016, 4(2): 153-160.
[10] Barber EL, Clarke-Pearson DL. The limited utility of currently available venous thromboembolism risk assessment tools in gynecological oncology patients[J]. American Journal of Obstetrics & Gynecology, 2016, 215(4): 445.E1-445.E9.
[11] Khorana AA, Kuderer NM, Culakova E, et al. Development and validation of a predictive model for chemotherapy-associated thrombosis[J]. Blood, 2008, 111(10): 4902-4907.
[12] Metcalf RL, Al-Hadithi E, Hopley N, et al. Characterisation and risk assessment of venous thromboembolism in gastrointestinal cancers[J]. World Journal of Gastrointestinal Oncology, 2017, 9(9): 363-371.
[13] Rogers Jr SO, Kilaru RK, Hosokawa P, et al. Multivariable predictors of postoperative venous thromboembolic events after general and vascular surgery: results from the patient safety in surgery study[J]. Journal of the American College of Surgeons, 2007, 204(6): 1211-1221.
[14] 田博, 宋春凤, 李辉, 等. Caprini和Rogers风险评估模型联合使用可以提高胸外科术后患者筛选静脉血栓栓塞症的准确性[J]. 中华胸部外科电子杂志, 2017, 4(3): 186-189.
Tian B, Song CF, Li H, et al. The combination of Caprini and Rogers risk assessment models can improve the accuracy of screening for venous thromboembolism in patients undergoing thoracic surgery[J]. Chinese Journal of Thoracic Surgery(Electronic Edition), 2017, 4(3): 186-189.
[15] 郭海, 方强, 黄建鸣, 等. Caprini和Rogers血栓风险评估模型在胸外科肺癌患者围手术期应用的验证研究[J]. 肿瘤预防与治疗, 2019, 32(8): 660-667.
Guo H, Fang Q, Huang JM, et al. Application of Caprini and Rogers risk assessment models in the perioperative management of lung cancer patients[J]. Journal of Cancer Control and Treatment, 2019, 32(8): 660-667.
[16] Autar R. Nursing assessment of clients at risk of deep vein thrombosis (DVT): the Autar DVT scale[J]. Journal of Advanced Nursing, 1996, 23(4): 763-770.
[17] Wang MM, Qin XJ, He XX, et al. Comparison and screening of different risk assessment models for deep vein thrombosis in patients with solid tumors[J]. Journal of Thrombosis and Thrombolysis, 2019, 48(2): 292-298.
[18] Müller G, Fritz E, Them C. Translation of the "Autar Deep Vein Thrombosis Scale" to assess the risk of thrombosis[J]. Pflege Zeitschrift, 2008, 61(2): 94-99.
[19] 肖冕,贾汝福,尹桂梅, 等.下肢深静脉血栓形成患者自我感受负担现状及其影响因素分析[J].中国医药导报,2022,19(8): 43-47.
Xiao M, Jia RF, Yin GM, et al. Analysis of status quo and influencing factors of self-perceived burden in patients with lower extremity deep vein thrombosis[J]. China Medical Herald, 2022,19(8): 43-47.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录