Nopp Stephan, Spielvogel Clemens P, Schmaldienst Sabine, Klauser-Braun Renate, Lorenz Matthias, Bauer Benedikt N, Pabinger Ingrid, Säemann Marcus, Königsbrügge Oliver, Ay Cihan
Clinical Division of Haematology and Hemostaseology, Department of Medicine I, Medical University of Vienna, Vienna, Austria.
Division of Nuclear Medicine, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
Thromb Haemost. 2022 Aug 29;122(9). doi: 10.1055/a-1754-7551.
Patients with end-stage kidney disease (ESKD) on hemodialysis (HD) are at increased risk for bleeding. However, despite relevant clinical implications regarding dialysis modalities or anticoagulation, no bleeding risk assessment strategy has been established in this challenging population.
Analyses on bleeding risk assessment models were performed in the population-based Vienna InVestigation of Atrial fibrillation and thromboemboLism in patients on hemoDialysIs (VIVALDI) study including 625 patients. In this cohort study, patients were prospectively followed for a median observation period of 3.5 years for the occurrence of major bleeding. First, performances of existing bleeding risk scores (i.e., HAS-BLED, HEMORRHAGES, ATRIA, and four others) were evaluated in terms of discrimination and calibration. Second, four machine learning-based prediction models that included clinical, dialysis-specific, and laboratory parameters were developed and tested using Monte Carlo cross-validation.
Of 625 patients (median age: 66 years, 37% women), 89 (14.2%) developed major bleeding, with a 1-year, 2-year, and 3-year cumulative incidence of 6.1% (95% confidence interval [CI]: 4.2-8.0), 10.3% (95% CI: 8.0-12.8), and 13.5% (95% CI: 10.8-16.2), respectively. C-statistics of the seven contemporary bleeding risk scores ranged between 0.54 and 0.59 indicating poor discriminatory performance. The HAS-BLED score showed the highest C-statistic of 0.59 (95% CI: 0.53-0.66). Similarly, all four machine learning-based predictions models performed poorly in internal validation (C-statistics ranging from 0.49 to 0.55).
Existing bleeding risk scores and a machine learning approach including common clinical parameters fail to assist in bleeding risk prediction of patients on HD. Therefore, new approaches, including novel biomarkers, to improve bleeding risk prediction in patients on HD are needed.
接受血液透析（HD）的终末期肾病（ESKD）患者出血风险增加。然而，尽管透析方式或抗凝存在相关临床意义，但在这一具有挑战性的人群中尚未建立出血风险评估策略。
在基于人群的维也纳血液透析患者房颤和血栓栓塞研究（VIVALDI）中对625例患者进行出血风险评估模型分析。在这项队列研究中，对患者进行前瞻性随访，中位观察期为3.5年，观察严重出血的发生情况。首先，从区分度和校准度方面评估现有出血风险评分（即HAS - BLED、HEMORRHAGES、ATRIA和其他四种）的性能。其次，开发并使用蒙特卡洛交叉验证测试了四个基于机器学习的预测模型，这些模型包括临床、透析特异性和实验室参数。
625例患者（中位年龄：66岁，37%为女性）中，89例（14.2%）发生严重出血，1年、2年和3年累积发病率分别为6.1%（95%置信区间[CI]：4.2 - 8.0）、10.3%（95% CI：8.0 - 12.8）和13.5%（95% CI：10.8 - 16.2）。七个当代出血风险评分的C统计量在0.54至0.59之间，表明区分性能较差。HAS - BLED评分的C统计量最高，为0.59（95% CI：0.53 - 0.66）。同样，所有四个基于机器学习的预测模型在内部验证中表现不佳（C统计量范围为0.49至0.55）。
现有的出血风险评分和包括常见临床参数的机器学习方法无法协助预测血液透析患者的出血风险。因此，需要新的方法，包括新型生物标志物，来改善血液透析患者的出血风险预测。
