Training and Validation of Deep Neural Networks for the Prediction of 90-Day Post-Liver Transplant Mortality Using UNOS Registry Data.
Training and Validation of Deep Neural Networks for the Prediction of 90-Day Post-Liver Transplant Mortality Using UNOS Registry Data.
复制标题
DOI：
10.1016/j.transproceed.2019.10.019
复制
发表时间：
2020-01
影响因子：
0.9
通讯作者：
Cannesson M
中科院分区：
文献类型：
--
作者：
Ershoff BD;Lee CK;Wray CL;Agopian VG;Urban G;Baldi P;Cannesson M
肝移植后死亡率的预测模型是至关重要的，这样供体器官就不会被分配给死亡率不合理的高概率受体。机器学习算法，特别是深度神经网络（DNN），通常可以实现比传统模型更高的预测性能。在这项研究中，我们使用术前变量训练DNN来预测移植后90天的死亡率，并将其性能与肝移植后生存结局（SOFT）和风险平衡（BAR）评分进行比较，使用器官共享联合网络数据，这些数据来自2005年至2015年期间接受死亡供体肝移植的成年患者（n = 57，544）。DNN使用202个特征进行训练，最好的DNN架构由5个隐藏层组成，每个隐藏层有110个神经元。最佳DNN模型的受试者工作特征曲线下面积（AUC）为0.703（95% CI：0.682-0.726），而BAR评分和SOFT评分分别为0.655（95% CI：0.633-0.678）和0.688（95% CI：0.667-0.711）。总之，尽管DNN的复杂性，它并没有达到比SOFT分数更高的区分性能。未来的风险模型可能会受益于包含其他数据源，包括DNN特别倾向于优于传统统计方法的高分辨率临床特征。
Prediction models of post-liver transplant mortality are crucial so that donor organs are not allocated to recipients with unreasonably high probabilities of mortality. Machine learning algorithms, particularly deep neural networks (DNNs), can often achieve higher predictive performance than conventional models. In this study, we trained a DNN to predict 90-day post-transplant mortality using preoperative variables and compared the performance to that of the Survival Outcomes Following Liver Transplantation (SOFT) and Balance of Risk (BAR) scores, using United Network of Organ Sharing data on adult patients who received a deceased donor liver transplant between 2005 and 2015 (n = 57,544). The DNN was trained using 202 features, and the best DNN’s architecture consisted of 5 hidden layers with 110 neurons each. The area under the receiver operating characteristics curve (AUC) of the best DNN model was 0.703 (95% CI: 0.682-0.726) as compared to 0.655 (95% CI: 0.633-0.678) and 0.688 (95% CI: 0.667-0.711) for the BAR score and SOFT score, respectively. In conclusion, despite the complexity of DNN, it did not achieve a significantly higher discriminative performance than the SOFT score. Future risk models will likely benefit from the inclusion of other data sources, including high-resolution clinical features for which DNNs are particularly apt to outperform conventional statistical methods.
登录
查看更多内容
影响因子：
8.8
作者：
Lee CK;Hofer I;Gabel E;Baldi P;Cannesson M
通讯作者：
Cannesson M
影响因子：
5.8
作者：
Di Lena, Pietro;Nagata, Ken;Baldi, Pierre
通讯作者：
Baldi, Pierre
影响因子：
14.4
作者：
Baldi, Pierre;Sadowski, Peter
通讯作者：
Sadowski, Peter
影响因子：
4.6
作者：
Dutkowski, Phillip;Clavien, Pierre A.
通讯作者：
Clavien, Pierre A.
影响因子：
24.5
作者：
Cucchetti, A.;Vivarelli, M.;Pinna, A. D.
通讯作者：
Pinna, A. D.