基于机器学习算法的恶性肿瘤患者VTE风险预测模型的研究进展

摘要/Abstract

摘要： 目的综述机器学习算法在恶性肿瘤患者VTE风险预测模型中应用的研究进展。方法通过检索PubMed、知网等数据库,筛选出近五年相关文献,分析当前恶性肿瘤患者VTE风险预测模型的构建方法、预测性能等。结果恶性肿瘤患者静脉血栓栓塞症（venous thromboembolism, VTE）的风险是非癌人群的4-7倍,且抗癌治疗进一步加剧血栓风险。传统预测模型虽然简便易行,但预测效能有限。目前已基于机器学习算法开发出许多综合性以及针对特定瘤种的预测模型,实现多维数据的整合以及性能更为优秀的动态预测。结论文章从癌症患者VTE风险预测模型的构建方法、预测性能等方面进行综述,以期为肿瘤患者VTE风险预测与临床抗凝获益评估决策的选择提供参考。

关键词: 癌症, 静脉血栓栓塞症, 机器学习, 风险预测模型

向珂漫, 黄莹, 李毅, 刘越琴, 李滨锐, 卜晓青. 基于机器学习算法的恶性肿瘤患者VTE风险预测模型的研究进展[J]. 心血管病防治知识, 2025, 15(23): 140-144.

参考文献

[1] Moik F, Ay C, Pabinger I.Risk prediction for cancer-associated thrombosis in ambulatory patients with cancer: past, present and future[J]. Thrombosis Research, 2020, 191: S3-S11.
[2] Pavlovic D, Niciforovic D, Markovic M, et al.Cancer-Associated Thrombosis: Epidemiology, Pathophysiological Mechanisms, Treatment, and Risk Assessment[J]. Clinical Medicine Insights. Oncology, 2023, 17: 11795549231220297.
[3] 姚宇婷,许启霞,庞颖颖,等.恶性肿瘤合并静脉血栓栓塞症临床特征分析及预测模型的评估[J].中华全科医学,2021,19(5):723-726,808.
[4] Elshoury A, Schaefer J K, Lim M Y, et al.Update on Guidelines for the Prevention of Cancer-Associated Thrombosis[J]. Journal of the National Comprehensive Cancer Network: JNCCN, 2022, 20(13).
[5] 李晓强,张福先,王深明.深静脉血栓形成的诊断和治疗指南(第三版)[J].中国血管外科杂志(电子版),2017,9(4):250-257.
[6] 高世林, 刘常清, 刘逸文, 等. 血栓后综合征风险评估工具的研究进展[J]. 护理研究, 2024, 38(14): 2554-2558.
[7] Spiezia L, Campello E, Simion C, et al.Risk Factors for Post-Thrombotic Syndrome in Patients With a First Proximal Deep Venous Thrombosis Treated With Direct Oral Anticoagulants[J]. Angiology, 2022, 73(7): 649-654.
[8] 王忠祥,章夏萍,阮萍,等.恶性肿瘤相关静脉血栓栓塞风险评估模型的系统评价[J].护理与康复,2023,22(4):42-48.
[9] Rhea I B, Lyon A R, Fradley M G.Anticoagulation of Cardiovascular Conditions in the Cancer Patient: Review of Old and New Therapies[J]. Current Oncology Reports, 2019, 21(5): 45.
[10] Cundiff D K, Manyemba J, Pezzullo J C. Anticoagulants versus non-steroidal anti-inflammatories or placebo for treatment of venous thromboembolism[J]. The Cochrane Database of Systematic Reviews, 2006, 2006(1): CD003746.
[11] Kim AS, Khorana AA, McCrae KR. Mechanisms and biomarkers of cancer-associated thrombosis. Transl Res. 2020, 225:33-53.
[12] Khorana A A, Kuderer N M, McCrae K, et al. Cancer associated thrombosis and mortality in patients with cancer stratified by khorana score risk levels[J]. Cancer Medicine, 2020, 9(21): 8062-8073.
[13] Khorana A A, DeSancho M T, Liebman H, et al. Prediction and Prevention of Cancer-Associated Thromboembolism[J]. The Oncologist, 2021, 26(1): e2-e7.
[14] Mulder F I, Candeloro M, Kamphuisen P W, et al.The Khorana score for prediction of venous thromboembolism in cancer patients: a systematic review and meta-analysis[J]. Haematologica, 2019, 104(6): 1277-1287.
[15] Chiasakul T, Lam B D, McNichol M, et al. Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis[J]. European Journal of Haematology, 2023, 111(6): 951-962.
[16] Greener J G, Kandathil S M, Moffat L, et al.A guide to machine learning for biologists[J]. Nature Reviews. Molecular Cell Biology, 2022, 23(1): 40-55.
[17] Jin S, Qin D, Liang B S, et al.Machine learning predicts cancer-associated deep vein thrombosis using clinically available variables[J]. International Journal of Medical Informatics, 2022, 161: 104733.
[18] 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-Pacific Journal of Oncology Nursing, 2022, 9(12): 100128.
[19] Mantha S, Chatterjee S, Singh R, et al. Application of Machine Learning to the Prediction of Cancer-Associated Venous Thromboembolism[J/OL]. Research Square, 2023: rs.3.rs-2870367.
[20] 汤心雨. 基于机器学习技术的肿瘤化疗患者VTE风险预测模型的构建[D].大连医科大学,2024.
[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]. Frontiers in Cardiovascular Medicine, 2022, 9: 845210.
[22] Liu X, Shu X, Zhou Y, et al.Construction of a risk prediction model for postoperative deep vein thrombosis in colorectal cancer patients based on machine learning algorithms[J]. Frontiers in Oncology, 2024, 14: 1499794.
[23] Xu Q, Lei H, Li X, et al.Machine learning predicts cancer-associated venous thromboembolism using clinically available variables in gastric cancer patients[J]. Heliyon, 2023, 9(1): e12681.
[24] Qiao N, Zhang Q, Chen L, et al.Machine learning prediction of venous thromboembolism after surgeries of major sellar region tumors[J]. Thrombosis Research, 2023, 226: 1-8.
[25] Chen K, Zhang Y, Zhang L, et al.Machine learning models for risk prediction of cancer-associated thrombosis: a systematic review and meta-analysis[J]. Journal of thrombosis and haemostasis: JTH, 2025, 23(2): 610-626.
[26] Ed-Driouch C, Mars F, Gourraud P A, et al.Addressing the Challenges and Barriers to the Integration of Machine Learning into Clinical Practice: An Innovative Method to Hybrid Human-Machine Intelligence[J]. Sensors (Basel, Switzerland), 2022, 22(21): 8313.
[27] Patell R, Zwicker J I, Singh R, et al.Machine learning in cancer-associated thrombosis: hype or hope in untangling the clot[J]. Bleeding, Thrombosis and Vascular Biology, 2024, 3(Suppl 1): 123.
[28] Charilaou P, Battat R.Machine learning models and over-fitting considerations[J]. World Journal of Gastroenterology, 2022, 28(5): 605-607.