Clinical Research Center, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi 710061, China.
School of Public Health, Xi'an Jiaotong University Health Science Center, Xi'an, Shaanxi 710061, China.
Comput Math Methods Med. 2021 Dec 24;2021:5745304. doi: 10.1155/2021/5745304. eCollection 2021.
A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability. We collected information on patients with various diseases in coronary care units (CCUs) from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The purpose of this study was to use this information to construct a neural-network model based on deep learning to predict the survival probabilities of patients with conditions that are common in CCUs.
We collected information on patients in the United States with five common diseases in CCUs from 2001 to 2012. We randomly divided the patients into a training cohort and a testing cohort at a ratio of 7 : 3 and applied a survival prediction method based on deep learning to predict their survival probability. We compared our model with the Cox proportional-hazards regression (CPH) model and used the concordance indexes (C-indexes), receiver operating characteristic (ROC) curve, and calibration plots to evaluate the predictive performance of the model.
The 3,388 CCU patients included in the study were randomly divided into 2,371 in the training cohort and 1,017 in the testing cohort. The stepwise regression results showed that the important factors affecting patient survival were the type of disease, age, race, anion gap, glucose, neutrophils, white blood cells, potassium, creatine kinase, and blood urea nitrogen ( < 0.05). We used the training cohort to construct a deep-learning model, for which the C-index was 0.833, or about 5% higher than that for the CPH model (0.786). The C-index of the deep-learning model for the test cohort was 0.822, which was also higher than that for the CPH model (0.782). The areas under the ROC curve for the 28-day, 90-day, and 1-year survival probabilities were 0.875, 0.865, and 0.874, respectively, in the deep-learning model, respectively, and 0.830, 0.843, and 0.806 in the CPH model. These values indicate that the survival analysis model based on deep learning is better than the traditional CPH model in predicting the survival of CCU patients.
A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability.
基于深度学习的生存预测模型在预测 CCU 患者的生存率方面比 CPH 模型具有更高的准确性，并且具有更好的区分能力。我们从医疗信息重症监护 III （MIMIC-III）数据库中收集了来自冠心病监护病房（CCU）的各种疾病患者的信息。本研究的目的是使用这些信息构建基于深度学习的神经网络模型，以预测 CCU 中常见疾病患者的生存率。
我们从 2001 年至 2012 年收集了美国 CCU 中五种常见疾病患者的信息。我们将患者随机分为训练队列和测试队列，比例为 7:3，并应用基于深度学习的生存预测方法来预测他们的生存概率。我们将我们的模型与 Cox 比例风险回归（CPH）模型进行比较，并使用一致性指数（C 指数）、接收器操作特征（ROC）曲线和校准图来评估模型的预测性能。
研究中包括的 3388 例 CCU 患者被随机分为训练队列 2371 例和测试队列 1017 例。逐步回归结果表明，影响患者生存的重要因素是疾病类型、年龄、种族、阴离子间隙、血糖、中性粒细胞、白细胞、钾、肌酸激酶和血尿素氮（<0.05）。我们使用训练队列构建了深度学习模型，其 C 指数为 0.833，比 CPH 模型（0.786）高约 5%。测试队列的深度学习模型的 C 指数为 0.822，也高于 CPH 模型（0.782）。28 天、90 天和 1 年生存率的 ROC 曲线下面积分别为 0.875、0.865 和 0.874，在深度学习模型中，而在 CPH 模型中分别为 0.830、0.843 和 0.806。这些值表明，基于深度学习的生存分析模型在预测 CCU 患者的生存率方面优于传统的 CPH 模型。
基于深度学习的生存预测模型在预测 CCU 患者的生存率方面比 CPH 模型具有更高的准确性，并且具有更好的区分能力。
