Key result
The deep learning model accurately predicted the survival probability of ICU patients with a C-index of 0.868, outperforming traditional Cox regression and random survival forest models.
Why the study?
Accurately predicting survival in ICU patients is critical for timely care and resource allocation, but few deep learning algorithms have been validated for survival time or compared with traditional algorithms.
Does a deep learning model improve the prediction of survival probability in ICU patients compared to traditional algorithms?
Observational (n=83,943)
Yes
Does a deep learning model improve the prediction of survival probability in ICU patients compared to traditional algorithms?
A novel deep learning model provides more accurate, individualized survival probability prediction for ICU patients compared to traditional algorithms.
Answers are grounded in this paper and cite their sources.
May improve ICU survival stratification; hypothesis-generating and requires prospective validation before adoption.
BACKGROUND: 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. METHODS: 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). RESULTS: 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. CONCLUSIONS: 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.
No takes yet. Share an insight, caveat, or question.
Tang et al. (2022) conducted an observational in Intensive Care Unit (ICU) admission (n=83,943). Deep learning (New-DL) model vs. Cox regression and random survival forest models was evaluated on C-index for survival probability prediction (C-index 0.868, 95% CI 0.859-0.878). The deep learning model accurately predicted the survival probability of ICU patients with a C-index of 0.868, outperforming traditional Cox regression and random survival forest models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: