癌症门诊患者7个月静脉血栓栓塞与临床相关出血预测模型的开发
基于514例高风险门诊癌症患者随机试验数据,开发并内部验证7个月静脉血栓栓塞(VTE)和临床相关出血的预测模型。全变量极端梯度提升模型表现最佳,VTE的AUC为0.92,出血的AUC为0.90。关键预测因子包括因子V Leiden、拓扑异构酶抑制剂使用、阿哌沙班、胃或胰腺癌、血红蛋白和高敏肌钙蛋白T等。
要点
- 全变量极端梯度提升模型对VTE预测AUC达0.92,对出血预测AUC达0.90。
- VTE关键预测因子包括因子V Leiden、拓扑异构酶抑制剂、阿哌沙班、胃或胰腺癌等。
- 出血关键预测因子包括细胞外囊泡促凝活性、NT-proBNP、CRP、年龄、BMI和血细胞计数。
核心结论
- 纳入生物标志物和遗传变量的预测模型能准确预测癌症患者的VTE和临床相关出血,但样本量有限需谨慎。
研究设计与样本
- 使用阿哌沙班预防高风险门诊癌症患者VTE随机试验中514例参与者的数据,开发并内部验证预测模型。
主要发现
- VTE和临床相关出血发生率分别为8.4%和9.0%。
- 全变量极端梯度提升模型表现最佳,VTE的AUC为0.92,出血的AUC为0.90。
- VTE关键预测因子包括因子V Leiden、拓扑异构酶抑制剂使用、阿哌沙班、胃或胰腺癌、血红蛋白和高敏肌钙蛋白T。
- 出血关键预测因子包括细胞外囊泡促凝活性、N末端B型利钠肽原、C反应蛋白、年龄、体重指数和血细胞计数。
局限性
- 样本量有限,需谨慎解读结果。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Patients with cancer are at elevated risk of venous thromboembolism (VTE). While primary thromboprophylaxis reduces VTE incidence, it also increases bleeding risk, necessitating accurate risk stratification. Existing tools (eg, the Khorana score) have modest predictive value, and bleeding risk models have not been validated in ambulatory patients with cancer. OBJECTIVES: To develop and internally validate prediction models for VTE and clinically relevant bleeding in ambulatory patients with cancer initiating chemotherapy. METHODS: We used data from 514 participants in the apixaban for the prevention of venous thromboembolism in high-risk ambulatory cancer patients randomized trial. Outcomes included objectively confirmed VTE and clinically relevant bleeding over 7 months. For each outcome, we trained 3 models: logistic regression with L1 regularization and 2 extreme gradient boosting models (1 using all variables, including biomarkers and genetic data; 1 using only routinely collected variables). Performance was evaluated using optimism-adjusted area under the curve (AUC) values, precision-recall AUC values, calibration, and diagnostic statistics. RESULTS: VTE and clinically relevant bleeding occurred in 8.4% and 9.0% of patients, respectively. The full-variable extreme gradient boosting model performed best (VTE AUC: 0.92; bleeding AUC: 0.90). Key VTE predictors included factor V Leiden, topoisomerase inhibitor use, apixaban, stomach or pancreatic cancer, hemoglobin and high-sensitivity troponin T whereas top bleeding predictors included extracellular vesicles procoagulant activity, N-terminal pro-B-type natriuretic peptide, C-reactive protein, age, body mass index, and blood counts. CONCLUSION: In this proof-of-concept study, prediction models incorporating biomarker and genetic variables accurately predicted VTE and clinically relevant bleeding in patients with cancer, though caution is warranted due to the modest sample size.
引用
- Roy DC, Wang TF, Wells P, et al. Development of models for predicting the 7-month risk of venous thromboembolism and clinically relevant bleeding in ambulatory patients with cancer: analysis from the apixaban for the prevention of venous thromboembolism in high-risk ambulatory cancer patients trial. J Thromb Haemost. 2026. PMID: 42107707. doi:10.1016/j.jtha.2026.04.028
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。