Gerard Gurumurthy, Filip Kisiel, Lianna Reynolds, Will Thomas, Maha Othman, Deepa J Arachchillage, Jecko Thachil
{"title":"机器学习在静脉血栓栓塞中的应用——为什么?下一步是什么?","authors":"Gerard Gurumurthy, Filip Kisiel, Lianna Reynolds, Will Thomas, Maha Othman, Deepa J Arachchillage, Jecko Thachil","doi":"10.1055/a-2669-7933","DOIUrl":null,"url":null,"abstract":"<p><p>Venous thromboembolism (VTE) remains a leading cause of cardiovascular morbidity and mortality, despite advances in imaging and anticoagulation. VTE arises from diverse and overlapping risk factors, such as inherited thrombophilia, immobility, malignancy, surgery or trauma, pregnancy, hormonal therapy, obesity, chronic medical conditions (e.g., heart failure, inflammatory disease), and advancing age. Clinicians, therefore, face challenges in balancing the benefits of thromboprophylaxis against the bleeding risk. Existing clinical risk scores often exhibit only modest discrimination and calibration across heterogeneous patient populations. Machine learning (ML) has emerged as a promising tool to address these limitations. In imaging, convolutional neural networks and hybrid algorithms can detect VTE on CT pulmonary angiography with areas under the curves (AUCs) of 0.85 to 0.96. In surgical cohorts, gradient-boosting models outperform traditional risk scores, achieving AUCs between 0.70 and 0.80 in predicting postoperative VTE. In cancer-associated venous thrombosis, advanced ML models demonstrate AUCs between 0.68 and 0.82. However, concerns about bias and external validation persist. Bleeding risk prediction models remain challenging in extended anticoagulation settings, often matching conventional models. Predicting recurrent VTE using neural networks showed AUCs of 0.93 to 0.99 in initial studies. However, these lack transparency and prospective validation. Most ML models suffer from limited external validation, \"black box\" algorithms, and integration hurdles within clinical workflows. Future efforts should focus on standardized reporting (e.g., Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis [TRIPOD]-ML), transparent model interpretation, prospective impact assessments, and seamless incorporation into electronic health records to realize the full potential of ML in VTE.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.1000,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine Learning in Venous Thromboembolism - Why and What Next?\",\"authors\":\"Gerard Gurumurthy, Filip Kisiel, Lianna Reynolds, Will Thomas, Maha Othman, Deepa J Arachchillage, Jecko Thachil\",\"doi\":\"10.1055/a-2669-7933\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Venous thromboembolism (VTE) remains a leading cause of cardiovascular morbidity and mortality, despite advances in imaging and anticoagulation. VTE arises from diverse and overlapping risk factors, such as inherited thrombophilia, immobility, malignancy, surgery or trauma, pregnancy, hormonal therapy, obesity, chronic medical conditions (e.g., heart failure, inflammatory disease), and advancing age. Clinicians, therefore, face challenges in balancing the benefits of thromboprophylaxis against the bleeding risk. Existing clinical risk scores often exhibit only modest discrimination and calibration across heterogeneous patient populations. Machine learning (ML) has emerged as a promising tool to address these limitations. In imaging, convolutional neural networks and hybrid algorithms can detect VTE on CT pulmonary angiography with areas under the curves (AUCs) of 0.85 to 0.96. In surgical cohorts, gradient-boosting models outperform traditional risk scores, achieving AUCs between 0.70 and 0.80 in predicting postoperative VTE. In cancer-associated venous thrombosis, advanced ML models demonstrate AUCs between 0.68 and 0.82. However, concerns about bias and external validation persist. Bleeding risk prediction models remain challenging in extended anticoagulation settings, often matching conventional models. Predicting recurrent VTE using neural networks showed AUCs of 0.93 to 0.99 in initial studies. However, these lack transparency and prospective validation. Most ML models suffer from limited external validation, \\\"black box\\\" algorithms, and integration hurdles within clinical workflows. Future efforts should focus on standardized reporting (e.g., Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis [TRIPOD]-ML), transparent model interpretation, prospective impact assessments, and seamless incorporation into electronic health records to realize the full potential of ML in VTE.</p>\",\"PeriodicalId\":21673,\"journal\":{\"name\":\"Seminars in thrombosis and hemostasis\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2025-08-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Seminars in thrombosis and hemostasis\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1055/a-2669-7933\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"HEMATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seminars in thrombosis and hemostasis","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1055/a-2669-7933","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"HEMATOLOGY","Score":null,"Total":0}
Machine Learning in Venous Thromboembolism - Why and What Next?
Venous thromboembolism (VTE) remains a leading cause of cardiovascular morbidity and mortality, despite advances in imaging and anticoagulation. VTE arises from diverse and overlapping risk factors, such as inherited thrombophilia, immobility, malignancy, surgery or trauma, pregnancy, hormonal therapy, obesity, chronic medical conditions (e.g., heart failure, inflammatory disease), and advancing age. Clinicians, therefore, face challenges in balancing the benefits of thromboprophylaxis against the bleeding risk. Existing clinical risk scores often exhibit only modest discrimination and calibration across heterogeneous patient populations. Machine learning (ML) has emerged as a promising tool to address these limitations. In imaging, convolutional neural networks and hybrid algorithms can detect VTE on CT pulmonary angiography with areas under the curves (AUCs) of 0.85 to 0.96. In surgical cohorts, gradient-boosting models outperform traditional risk scores, achieving AUCs between 0.70 and 0.80 in predicting postoperative VTE. In cancer-associated venous thrombosis, advanced ML models demonstrate AUCs between 0.68 and 0.82. However, concerns about bias and external validation persist. Bleeding risk prediction models remain challenging in extended anticoagulation settings, often matching conventional models. Predicting recurrent VTE using neural networks showed AUCs of 0.93 to 0.99 in initial studies. However, these lack transparency and prospective validation. Most ML models suffer from limited external validation, "black box" algorithms, and integration hurdles within clinical workflows. Future efforts should focus on standardized reporting (e.g., Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis [TRIPOD]-ML), transparent model interpretation, prospective impact assessments, and seamless incorporation into electronic health records to realize the full potential of ML in VTE.
期刊介绍:
Seminars in Thrombosis and Hemostasis is a topic driven review journal that focuses on all issues relating to hemostatic and thrombotic disorders. As one of the premiere review journals in the field, Seminars in Thrombosis and Hemostasis serves as a comprehensive forum for important advances in clinical and laboratory diagnosis and therapeutic interventions. The journal also publishes peer reviewed original research papers.
Seminars offers an informed perspective on today''s pivotal issues, including hemophilia A & B, thrombophilia, gene therapy, venous and arterial thrombosis, von Willebrand disease, vascular disorders and thromboembolic diseases. Attention is also given to the latest developments in pharmaceutical drugs along with treatment and current management techniques. The journal also frequently publishes sponsored supplements to further highlight emerging trends in the field.