单中心使用随机森林分类算法预测腹主动脉瘤择期修复术后两年生存
该研究基于2008年1月1日至2021年3月31日单中心择期开放或腔内修复腹主动脉瘤的925例患者,用70%数据构建、30%数据验证随机森林分类器预测术后两年生存。两年内死亡126例(13.6%),围手术期死亡11例(1.2%);预测两年生存的敏感度96.7%、特异度67.1%、总体准确率92.6%,10折交叉验证的受试者工作特征曲线下面积为0.88。作者认为基于常规临床数据的随机森林分类器可成功预测择期腹主动脉瘤修复术后两年生存。
要点
- 随机森林分类器预测择期腹主动脉瘤修复术后两年生存的敏感度96.7%、特异度67.1%、总体准确率92.6%。
- 变量重要性分析提示无氧阈、术前血红蛋白、最大氧耗量、体重指数、风险分级和第一秒用力呼气容积与用力肺活量比值为模型最重要贡献因素。
- 作者认为该信息可助力择期腹主动脉瘤修复决策中的风险获益评估。
核心结论
- 基于常规可得临床数据的随机森林分类器可成功预测择期腹主动脉瘤修复术后两年内生存。
- 作者认为该信息可助力择期腹主动脉瘤修复决策中的风险获益评估。
研究设计与样本
- 回顾性分析2008年1月1日至31 March 2021期间接受择期开放或腔内修复腹主动脉瘤的全部患者。
- 患者经血管服务质量改进项目路径评估,包括心肺运动试验、增强计算机断层扫描和多学科评估,随访至少两年。
- 随机森林分类器用70%数据集构建、30%数据集验证,用于预测腹主动脉瘤修复术后至少两年生存。
- 共925例患者(男836例、女89例)接受择期腹主动脉瘤修复。
主要发现
- 925例中126例(13.6%)在最初两年内死亡,11例(1.2%)围手术期死亡。
- 变量重要性分析提示无氧阈、术前血红蛋白、最大氧耗量、体重指数、风险分级和第一秒用力呼气容积与用力肺活量比值是模型最重要贡献因素。
- 随机森林分类器预测术后两年生存的敏感度为96.7%(95%CI 94.4-99%),特异度为67.1%(95%CI 61-72%)。
- 总体准确率为92.6%(95%CI 88-95%),阳性预测值0.93,阴性预测值0.80。
- 10折交叉验证显示受试者工作特征曲线下面积为0.88。
临床怎么用
- 作者认为该随机森林分类器预测的两年生存信息可助力择期腹主动脉瘤修复决策中的风险获益评估。
局限性
- 原文未报告局限性
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
OBJECTIVE: The decision to electively repair an abdominal aortic aneurysm (AAA) involves balancing the risk of rupture, peri-procedural death, and life expectancy. Random forest classifiers (RFCs) are powerful machine learning algorithms. The aim of this study was to construct and validate a random forest machine learning tool to predict two year survival following elective AAA repair. METHODS: All patients who underwent elective open or endovascular repair of AAA from 1 January 2008 to 31 March 2021 were reviewed. They were assessed using the Vascular Services Quality Improvement Program pathway involving cardiopulmonary exercise testing, contrast enhanced computerised tomography scan, and multidisciplinary assessment. Patients were followed up for at least two years. A RFC was developed using 70% of the dataset and validated using 30% to predict survival for at least two years following AAA repair. RESULTS: Nine hundred and twenty five patients (n = 836 men; n = 89 women) underwent elective AAA repair; 126 (13.6%) died during the first two years; 11 (1.2%) died peri-procedurally. Variable importance analysis suggested that anaerobic threshold, pre-operative haemoglobin, maximal O2 consumption, body mass index, risk category, and forced expiratory volume in 1 second - forced vital capacity ratio were the most important contributors to the model. Sensitivity and specificity of the RFC for prediction of two year survival following surgery was 96.7% (95% CI 94.4 - 99%) and 67.1% (95% CI 61 - 72%); overall accuracy: 92.6% (95% CI 88 - 95%) (positive predictive value: 0.93, negative predictive value: 0.80); 10 fold cross validation revealed area under the receiver operator characteristic curve of 0.88. CONCLUSION: RFCs based on readily available clinical data can successfully predict survival in the first two years following elective AAA repair. Such information can contribute to the risk benefit assessment when deciding to electively repair AAAs.
引用
- Thompson DC, Hackett R, Wong PF, et al. Prediction of Two Year Survival Following Elective Repair of Abdominal Aortic Aneurysms at A Single Centre Using A Random Forest Classification Algorithm. Eur J Vasc Endovasc Surg. 2024. PMID: 39638233. doi:10.1016/j.ejvs.2024.11.357
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。