当前位置: X-MOL 学术Eur. Heart J. Acute Cardiovasc. Care › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving 1-year mortality prediction in ACS patients using machine learning
European Heart Journal - Acute Cardiovascular Care ( IF 4.1 ) Pub Date : 2021-04-22 , DOI: 10.1093/ehjacc/zuab030
Sebastian Weichwald 1, 2 , Alessandro Candreva 3 , Rebekka Burkholz 1 , Roland Klingenberg 3, 4, 5, 6 , Lorenz Räber 7 , Dik Heg 8 , Robert Manka 3 , Baris Gencer 9 , François Mach 9 , David Nanchen 10 , Nicolas Rodondi 11, 12 , Stephan Windecker 7 , Reijo Laaksonen 13, 14 , Stanley L Hazen 15, 16 , Arnold von Eckardstein 17 , Frank Ruschitzka 3 , Thomas F Lüscher 18, 19 , Joachim M Buhmann 1 , Christian M Matter 3, 18
Affiliation  

Background The Global Registry of Acute Coronary Events (GRACE) score is an established clinical risk stratification tool for patients with acute coronary syndromes (ACS). We developed and internally validated a model for 1-year all-cause mortality prediction in ACS patients. Methods Between 2009 and 2012, 2’168 ACS patients were enrolled into the Swiss SPUM-ACS Cohort. Biomarkers were determined in 1’892 patients and follow-up was achieved in 95.8% of patients. 1-year all-cause mortality was 4.3% (n = 80). In our analysis we consider all linear models using combinations of 8 out of 56 variables to predict 1-year all-cause mortality and to derive a variable ranking. Results 1.3% of 1’420’494’075 models outperformed the GRACE 2.0 Score. The SPUM-ACS Score includes age, plasma glucose, NT-proBNP, left ventricular ejection fraction (LVEF), Killip class, history of peripheral artery disease (PAD), malignancy, and cardio-pulmonary resuscitation. For predicting 1-year mortality after ACS, the SPUM-ACS Score outperformed the GRACE 2.0 Score which achieves a 5-fold cross-validated AUC of 0.81 (95% CI 0.78–0.84). Ranking individual features according to their importance across all multivariate models revealed age, trimethylamine N-oxide, creatinine, history of PAD or malignancy, LVEF, and haemoglobin as the most relevant variables for predicting 1-year mortality. Conclusions The variable ranking and the selection for the SPUM-ACS Score highlight the relevance of age, markers of heart failure, and comorbidities for prediction of all-cause death. Before application, this score needs to be externally validated and refined in larger cohorts. Clinical Trial Registration NCT01000701.

中文翻译:

使用机器学习提高 ACS 患者的 1 年死亡率预测

背景 急性冠脉事件全球登记 (GRACE) 评分是针对急性冠脉综合征 (ACS) 患者的既定临床风险分层工具。我们开发并内部验证了 ACS 患者 1 年全因死亡率预测模型。方法 2009 年至 2012 年间,2,168 名 ACS 患者被纳入瑞士 SPUM-ACS 队列。在 1,892 名患者中确定了生物标志物,并在 95.8% 的患者中进行了随访。1 年全因死亡率为 4.3%(n = 80)。在我们的分析中,我们考虑使用 56 个变量中的 8 个组合来预测 1 年全因死亡率并得出变量排名的所有线性模型。结果 1'420'494'075 模型中有 1.3% 的表现优于 GRACE 2.0 分数。SPUM-ACS 评分包括年龄、血浆葡萄糖、NT-proBNP、左心室射血分数 (LVEF)、Killip 类、外周动脉疾病 (PAD)、恶性肿瘤和心肺复苏史。对于 ACS 后 1 年死亡率的预测,SPUM-ACS 评分优于 GRACE 2.0 评分,其达到 5 倍交叉验证的 AUC 为 0.81 (95% CI 0.78–0.84)。根据其在所有多变量模型中的重要性对个体特征进行排名显示,年龄、三甲胺 N-氧化物、肌酐、PAD 或恶性肿瘤病史、LVEF 和血红蛋白是预测 1 年死亡率的最相关变量。结论 SPUM-ACS 评分的变量排名和选择突出了年龄、心力衰竭标志物和合并症与预测全因死亡的相关性。在应用之前,该分数需要在更大的群组中进行外部验证和完善。临床试验注册 NCT01000701。外周动脉疾病 (PAD)、恶性肿瘤和心肺复苏史。对于 ACS 后 1 年死亡率的预测,SPUM-ACS 评分优于 GRACE 2.0 评分,其达到 5 倍交叉验证的 AUC 为 0.81 (95% CI 0.78–0.84)。根据其在所有多变量模型中的重要性对个体特征进行排名显示,年龄、三甲胺 N-氧化物、肌酐、PAD 或恶性肿瘤病史、LVEF 和血红蛋白是预测 1 年死亡率的最相关变量。结论 SPUM-ACS 评分的变量排名和选择突出了年龄、心力衰竭标志物和合并症与预测全因死亡的相关性。在应用之前,该分数需要在更大的群组中进行外部验证和完善。临床试验注册 NCT01000701。外周动脉疾病 (PAD)、恶性肿瘤和心肺复苏史。对于 ACS 后 1 年死亡率的预测,SPUM-ACS 评分优于 GRACE 2.0 评分,其达到 5 倍交叉验证的 AUC 为 0.81 (95% CI 0.78–0.84)。根据其在所有多变量模型中的重要性对个体特征进行排名显示,年龄、三甲胺 N-氧化物、肌酐、PAD 或恶性肿瘤病史、LVEF 和血红蛋白是预测 1 年死亡率的最相关变量。结论 SPUM-ACS 评分的变量排名和选择突出了年龄、心力衰竭标志物和合并症与预测全因死亡的相关性。在应用之前,该分数需要在更大的群组中进行外部验证和完善。临床试验注册 NCT01000701。
更新日期:2021-04-22
down
wechat
bug