Division of Cardiac Sciences, Libin Cardiovascular Institute of Alberta, University of Calgary, Calgary, Canada.
KU Leuven Department of Cardiovascular Sciences, Research Unit Hypertension and Cardiovascular Epidemiology, University of Leuven, Leuven, Belgium.
J Heart Lung Transplant. 2022 Jul;41(7):928-936. doi: 10.1016/j.healun.2022.03.019. Epub 2022 Mar 31.
Outcome prediction following heart transplant is critical to explaining risks and benefits to patients and decision-making when considering potential organ offers. Given the large number of potential variables to be considered, this task may be most efficiently performed using machine learning (ML). We trained and tested ML and statistical algorithms to predict outcomes following cardiac transplant using the United Network of Organ Sharing (UNOS) database.
We included 59,590 adult and 8,349 pediatric patients enrolled in the UNOS database between January 1994 and December 2016 who underwent cardiac transplantation. We evaluated 3 classification and 3 survival methods. Algorithms were evaluated using shuffled 10-fold cross-validation (CV) and rolling CV. Predictive performance for 1 year and 90 days all-cause mortality was characterized using the area under the receiver-operating characteristic curve (AUC) with 95% confidence interval.
In total, 8,394 (12.4%) patients died within 1 year of transplant. For predicting 1-year survival, using the shuffled 10-fold CV, Random Forest achieved the highest AUC (0.893; 0.889-0.897) followed by XGBoost and logistic regression. In the rolling CV, prediction performance was more modest and comparable among the models with XGBoost and Logistic regression achieving the highest AUC 0.657 (0.647-0.667) and 0.641(0.631-0.651), respectively. There was a trend toward higher prediction performance in pediatric patients.
Our study suggests that ML and statistical models can be used to predict mortality post-transplant, but based on the results from rolling CV, the overall prediction performance will be limited by temporal shifts inpatient and donor selection.
心脏移植后的预后预测对于向患者解释风险和获益至关重要，并且在考虑潜在器官供体时也有助于决策。鉴于需要考虑的潜在变量众多，这项任务可能最有效地通过机器学习（ML）来完成。我们使用器官共享联合网络（UNOS）数据库来训练和测试 ML 和统计算法，以预测心脏移植后的结局。
我们纳入了 1994 年 1 月至 2016 年 12 月期间在 UNOS 数据库中登记的 59590 名成年患者和 8349 名儿科患者，这些患者接受了心脏移植。我们评估了 3 种分类和 3 种生存方法。算法使用随机洗牌 10 折交叉验证（CV）和滚动 CV 进行评估。使用受试者工作特征曲线下面积（AUC）评估 1 年和 90 天全因死亡率的预测性能，并给出 95%置信区间。
共有 8394 例（12.4%）患者在移植后 1 年内死亡。在预测 1 年生存率方面，随机森林在随机洗牌 10 折 CV 中获得了最高的 AUC（0.893；0.889-0.897），其次是 XGBoost 和逻辑回归。在滚动 CV 中，预测性能较为适中，各模型之间的差异不大，其中 XGBoost 和逻辑回归的 AUC 最高，分别为 0.657（0.647-0.667）和 0.641（0.631-0.651）。儿科患者的预测性能有升高的趋势。
我们的研究表明，ML 和统计模型可用于预测移植后的死亡率，但基于滚动 CV 的结果，患者和供者选择方面的时间变化将限制整体预测性能。
