Tang W, Gao J Y, Ma X Y, Zhang C H, Ma L T, Wang Y S
Department of Nephrology, Peking University Third Hospital, Beijing 100191, China.
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871, China.
Beijing Da Xue Xue Bao Yi Xue Ban. 2019 Jun 18;51(3):602-608. doi: 10.19723/j.issn.1671-167X.2019.03.034.
Deep learning models, including recurrent neural network (RNN) and gated recurrent unit (GRU), were used to construct the clinical prognostic prediction models for peritoneal dialysis (PD) patients based on routine clinical data. The performance of the RNN and GRU were compared with logistic regression (LR), which is commonly used in medical researches. The possible underlining clinical implications based on the result from the GRU model were also investigated.
We used the clinical data from the PD center of Peking University Third Hospital as the data source. Both the baseline data at the beginning of dialysis, and the follow-up and prognostic data of the patients were used by the RNN and GRU prediction models. The hyper-parameters were tuned based on the 10-fold cross-validation. The risk prediction performance of each model was evaluated via area under the receiver operation characteristic curve (AUROC), recall rate and F1-score on the testset.
A total of 656 patients with the 261 occurrences of death were included in the experiment. The total number of all diagnostic records were 13 091. The results on the testset showed that the AUROC of the LR model, RNN model, and GRU model was 0.701 4, 0.786 0, and 0.814 7, respectively. The predictive performances of the GRU and RNN models were significantly better than that of the LR model. The performances of the GRU and RNN models assessed by recall rate and F1-score were also significantly better than that of the LR model, in which the GRU model reached the best performance. In addition, the recall rates were different among different causes of death or by different prediction time windows.
The recurrent neural network model, especially the GRU model, is more effective in predicting PD patients' prognosis as compared with the LR model. This new model may be helpful for clinicians to provide timely intervention, thus improving the quality of care of PD.
利用深度学习模型，包括循环神经网络（RNN）和门控循环单元（GRU），基于常规临床数据构建腹膜透析（PD）患者的临床预后预测模型。将RNN和GRU的性能与医学研究中常用的逻辑回归（LR）进行比较。还基于GRU模型的结果研究了可能的潜在临床意义。
我们使用北京大学第三医院PD中心的临床数据作为数据源。RNN和GRU预测模型使用透析开始时的基线数据以及患者的随访和预后数据。基于10折交叉验证对超参数进行调整。通过测试集上的受试者操作特征曲线下面积（AUROC）、召回率和F1分数评估每个模型的风险预测性能。
实验共纳入656例患者，其中死亡261例。所有诊断记录总数为13091条。测试集结果显示，LR模型、RNN模型和GRU模型的AUROC分别为0.7014、0.7860和0.8147。GRU和RNN模型的预测性能明显优于LR模型。通过召回率和F1分数评估的GRU和RNN模型的性能也明显优于LR模型，其中GRU模型达到最佳性能。此外，不同死因或不同预测时间窗的召回率不同。
与LR模型相比，循环神经网络模型，尤其是GRU模型，在预测PD患者预后方面更有效。这种新模型可能有助于临床医生提供及时干预，从而提高PD的护理质量。
