Miller Rebecca, Tumin Dmitry, Cooper Jennifer, Hayes Don, Tobias Joseph D
Department of Anesthesiology and Pain Medicine, Nationwide Children's Hospital, Columbus, Ohio.
Department of Pediatrics, Brody School of Medicine, East Carolina University, Greenville, North Carolina.
Pediatr Transplant. 2019 May;23(3):e13360. doi: 10.1111/petr.13360. Epub 2019 Jan 29.
Optimizing transplant candidates' priority for donor organs depends on the accurate assessment of post-transplant outcomes. Due to the complexity of transplantation and the wide range of possible serious complications, recipient outcomes are difficult to predict accurately using conventional multivariable regression. Therefore, we evaluated the utility of 3 ML algorithms for predicting mortality after pediatric HTx.
We identified patients <18 years of age receiving HTx in 2006-2015 in the UNOS Registry database. Mortality within 1, 3, or 5 years was predicted using classification and regression trees, RFs, and ANN. Each model was trained using cross-validation, then validated in a separate testing set. Model performance was primarily evaluated by the area under the receiver operating characteristic (AUC) curve.
The training set included 2802 patients, whereas 700 were included in the testing set. RF achieved the best fit to the training data with AUCs of 0.74, 0.68, and 0.64 for 1-, 3-, and 5-year mortality, respectively, and performed best in the testing data, with AUCs of 0.72, 0.61, and 0.60, respectively. Nevertheless, sensitivity was poor across models (training: 0.22-0.58; testing: 0.07-0.49).
ML algorithms demonstrated fair predictive utility in both training and testing data, but the sensitivity of these algorithms was generally poor. With the registry missing data on many determinants of long-term survival, the ability of ML methods to predict mortality after pediatric HTx may be fundamentally limited.
优化移植受者获得供体器官的优先级取决于对移植后结局的准确评估。由于移植的复杂性以及可能出现的严重并发症范围广泛，使用传统多变量回归难以准确预测受者结局。因此，我们评估了3种机器学习（ML）算法预测小儿心脏移植（HTx）后死亡率的效用。
我们在器官共享联合网络（UNOS）登记数据库中识别出2006 - 2015年接受HTx的18岁以下患者。使用分类与回归树、随机森林（RF）和人工神经网络（ANN）预测1年、3年或5年内的死亡率。每个模型均采用交叉验证进行训练，然后在单独的测试集中进行验证。模型性能主要通过受试者操作特征（AUC）曲线下面积进行评估。
训练集包括2802例患者，而测试集包括700例患者。RF对训练数据的拟合最佳，1年、3年和5年死亡率的AUC分别为0.74、0.68和0.64，在测试数据中表现最佳，AUC分别为0.72、0.61和0.60。然而，各模型的敏感性均较差（训练：0.22 - 0.58；测试：0.07 - 0.49）。
ML算法在训练和测试数据中均显示出一定的预测效用，但这些算法的敏感性普遍较差。由于登记处缺少许多长期生存决定因素的数据，ML方法预测小儿HTx后死亡率的能力可能从根本上受到限制。
