Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China.
Shanghai Engineering Research Center of Lung Transplantation, Shanghai, China.
J Am Med Inform Assoc. 2022 Aug 16;29(9):1567-1576. doi: 10.1093/jamia/ocac098.
Patients in the intensive care unit (ICU) are often in critical condition and have a high mortality rate. Accurately predicting the survival probability of ICU patients is beneficial to timely care and prioritizing medical resources to improve the overall patient population survival. Models developed by deep learning (DL) algorithms show good performance on many models. However, few DL algorithms have been validated in the dimension of survival time or compared with traditional algorithms.
Variables from the Early Warning Score, Sequential Organ Failure Assessment Score, Simplified Acute Physiology Score II, Acute Physiology and Chronic Health Evaluation (APACHE) II, and APACHE IV models were selected for model development. The Cox regression, random survival forest (RSF), and DL methods were used to develop prediction models for the survival probability of ICU patients. The prediction performance was independently evaluated in the MIMIC-III Clinical Database (MIMIC-III), the eICU Collaborative Research Database (eICU), and Shanghai Pulmonary Hospital Database (SPH).
Forty variables were collected in total for model development. 83 943 participants from 3 databases were included in the study. The New-DL model accurately stratified patients into different survival probability groups with a C-index of >0.7 in the MIMIC-III, eICU, and SPH, performing better than the other models. The calibration curves of the models at 3 and 10 days indicated that the prediction performance was good. A user-friendly interface was developed to enable the model's convenience.
Compared with traditional algorithms, DL algorithms are more accurate in predicting the survival probability during ICU hospitalization. This novel model can provide reliable, individualized survival probability prediction.
重症监护病房（ICU）的患者通常病情危急，死亡率高。准确预测 ICU 患者的生存率有助于及时进行护理和优先分配医疗资源，从而提高整体患者群体的生存率。深度学习（DL）算法开发的模型在许多模型上表现出良好的性能。然而，很少有 DL 算法在生存时间维度上得到验证或与传统算法进行比较。
从早期预警评分、序贯器官衰竭评估评分、简化急性生理学评分 II、急性生理学和慢性健康评估（APACHE）II 和 APACHE IV 模型中选择变量用于模型开发。使用 Cox 回归、随机生存森林（RSF）和 DL 方法为 ICU 患者的生存率开发预测模型。在 MIMIC-III 临床数据库（MIMIC-III）、eICU 协作研究数据库（eICU）和上海肺科医院数据库（SPH）中独立评估预测性能。
共收集了 40 个变量用于模型开发。来自 3 个数据库的 83943 名参与者被纳入研究。新的 DL 模型在 MIMIC-III、eICU 和 SPH 中准确地将患者分为不同的生存率组，C 指数>0.7，优于其他模型。模型在 3 天和 10 天的校准曲线表明预测性能良好。开发了一个用户友好的界面，使模型更便于使用。
与传统算法相比，DL 算法在预测 ICU 住院期间的生存率方面更准确。该新型模型可提供可靠的个体化生存率预测。
