用于预测当代心脏移植后结局的最先进机器学习算法：来自 UNOS 数据库的结果。
State-of-the-art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database.
机构信息
Division of Cardiology, New York University Langone Medical Center, New York, New York, USA.
Brigham and Women's Hospital Heart and Vascular Center, Harvard Medical School, Boston, Massachusetts, USA.
出版信息
Clin Transplant. 2021 Aug;35(8):e14388. doi: 10.1111/ctr.14388. Epub 2021 Jun 29.
PURPOSE
We sought to develop and validate machine learning (ML) models to increase the predictive accuracy of mortality after heart transplantation (HT).
METHODS AND RESULTS
We included adult HT recipients from the United Network for Organ Sharing (UNOS) database between 2010 and 2018 using solely pre-transplant variables. The study cohort comprised 18 625 patients (53 ± 13 years, 73% males) and was randomly split into a derivation and a validation cohort with a 3:1 ratio. At 1-year after HT, there were 2334 (12.5%) deaths. Out of a total of 134 pre-transplant variables, 39 were selected as highly predictive of 1-year mortality via feature selection algorithm and were used to train five ML models. AUC for the prediction of 1-year survival was .689, .642, .649, .637, .526 for the Adaboost, Logistic Regression, Decision Tree, Support Vector Machine, and K-nearest neighbor models, respectively, whereas the Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score had an AUC of .569. Local interpretable model-agnostic explanations (LIME) analysis was used in the best performing model to identify the relative impact of key predictors. ML models for 3- and 5-year survival as well as acute rejection were also developed in a secondary analysis and yielded AUCs of .629, .609, and .610 using 27, 31, and 91 selected variables respectively.
CONCLUSION
Machine learning models showed good predictive accuracy of outcomes after heart transplantation.
目的
我们旨在开发和验证机器学习（ML）模型，以提高心脏移植（HT）后死亡率的预测准确性。
方法和结果
我们仅使用移植前变量，纳入了 2010 年至 2018 年间美国器官共享网络（UNOS）数据库中的成年 HT 受者。研究队列包括 18625 名患者（53±13 岁，73%为男性），并按照 3:1 的比例随机分为推导队列和验证队列。在 HT 后 1 年，有 2334 名（12.5%）患者死亡。在总共 134 个移植前变量中，通过特征选择算法选择了 39 个对 1 年死亡率具有高度预测性的变量，并用于训练 5 个 ML 模型。Adaboost、Logistic Regression、Decision Tree、Support Vector Machine 和 K-nearest neighbor 模型预测 1 年生存率的 AUC 分别为 0.689、0.642、0.649、0.637 和 0.526，而心脏移植后死亡率预测指数（IMPACT）评分的 AUC 为 0.569。在表现最佳的模型中使用局部可解释模型不可知解释（LIME）分析来确定关键预测因素的相对影响。在二次分析中还开发了用于 3 年和 5 年生存率以及急性排斥反应的 ML 模型，分别使用 27、31 和 91 个选定变量，其 AUC 为 0.629、0.609 和 0.610。
结论
机器学习模型对心脏移植后结局具有良好的预测准确性。
Zotero 插件