Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors

Abstract Background Sepsis survivors face substantial risks of late mortality following discharge, underscoring the critical need for early prediction and targeted interventions for this vulnerable population. Early identification of those at high risk of mortality following discharge may optimize h...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Wei, Feihong Lin, Tian Jin, Qian Yao, Sheng Wang, Di Feng, Xin Lv, Wen He
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Big Data
Subjects:
Online Access:https://doi.org/10.1186/s40537-025-01234-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342215772438528
author Juan Wei
Feihong Lin
Tian Jin
Qian Yao
Sheng Wang
Di Feng
Xin Lv
Wen He
author_facet Juan Wei
Feihong Lin
Tian Jin
Qian Yao
Sheng Wang
Di Feng
Xin Lv
Wen He
author_sort Juan Wei
collection DOAJ
description Abstract Background Sepsis survivors face substantial risks of late mortality following discharge, underscoring the critical need for early prediction and targeted interventions for this vulnerable population. Early identification of those at high risk of mortality following discharge may optimize healthcare resource allocation. We sought to feed common clinical available data to a deep learning algorithm for predicting short to long-term mortality in sepsis survivors. Methods This retrospective study, using a real-world database (MIMIC-IV database), screened adult critically ill patients with sepsis (as defined by Sepsis-3) admitted to the ICU with stays exceeding four days and who were discharged alive. Static features including patient characteristics, comorbidities, laboratory tests at ICU admission, and each dynamic SOFA component score over the first four days post-ICU admission were collected. We developed a deep learning-based combined model (DL-CMT) for post-discharge mortality prediction using multidimensional and time-series data. Comparisons were made with a multilayer perceptron and two machine learning models of random forest and eXtreme Gradient Boosting (XGBoost). Results 7532 patients fulfilled the inclusion criteria, and the observed mortality rates were 30.7% at 28 days, 33.6% at 90 days, and 39.4% at one year post-ICU discharge. The proposed DL-CMT model achieved the best performance for mortality prediction at all the intervals, with area under the receiver operating characteristic curve of 0.95 (95% confidence interval [CI] 0.93–0.96), 0.92 (95% CI 0.90–0.94), and 0.90 (95% CI 0.87–0.92), respectively. Our model outperformed the multilayer perceptron, random forest, and XGBoost in all endpoints. Ablation experiments confirmed the model’s robustness, maintaining performance despite the absence of a specific physiological component. Conclusions Sepsis survivors have persistently high mortality risks post-discharge. The DL-CMT model, leveraging dynamic SOFA component scores and static features, demonstrated superior predictive performance for short to long-term mortality. This model has the potential to assist clinicians in optimizing post-discharge management and improving follow-up care.
format Article
id doaj-art-4243b542cdea4afab7a3801a20ec20a1
institution Kabale University
issn 2196-1115
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Big Data
spelling doaj-art-4243b542cdea4afab7a3801a20ec20a12025-08-20T03:43:27ZengSpringerOpenJournal of Big Data2196-11152025-07-0112111910.1186/s40537-025-01234-2Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivorsJuan Wei0Feihong Lin1Tian Jin2Qian Yao3Sheng Wang4Di Feng5Xin Lv6Wen He7Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityClinical Research Center, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityDepartment of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji UniversityAbstract Background Sepsis survivors face substantial risks of late mortality following discharge, underscoring the critical need for early prediction and targeted interventions for this vulnerable population. Early identification of those at high risk of mortality following discharge may optimize healthcare resource allocation. We sought to feed common clinical available data to a deep learning algorithm for predicting short to long-term mortality in sepsis survivors. Methods This retrospective study, using a real-world database (MIMIC-IV database), screened adult critically ill patients with sepsis (as defined by Sepsis-3) admitted to the ICU with stays exceeding four days and who were discharged alive. Static features including patient characteristics, comorbidities, laboratory tests at ICU admission, and each dynamic SOFA component score over the first four days post-ICU admission were collected. We developed a deep learning-based combined model (DL-CMT) for post-discharge mortality prediction using multidimensional and time-series data. Comparisons were made with a multilayer perceptron and two machine learning models of random forest and eXtreme Gradient Boosting (XGBoost). Results 7532 patients fulfilled the inclusion criteria, and the observed mortality rates were 30.7% at 28 days, 33.6% at 90 days, and 39.4% at one year post-ICU discharge. The proposed DL-CMT model achieved the best performance for mortality prediction at all the intervals, with area under the receiver operating characteristic curve of 0.95 (95% confidence interval [CI] 0.93–0.96), 0.92 (95% CI 0.90–0.94), and 0.90 (95% CI 0.87–0.92), respectively. Our model outperformed the multilayer perceptron, random forest, and XGBoost in all endpoints. Ablation experiments confirmed the model’s robustness, maintaining performance despite the absence of a specific physiological component. Conclusions Sepsis survivors have persistently high mortality risks post-discharge. The DL-CMT model, leveraging dynamic SOFA component scores and static features, demonstrated superior predictive performance for short to long-term mortality. This model has the potential to assist clinicians in optimizing post-discharge management and improving follow-up care.https://doi.org/10.1186/s40537-025-01234-2SepsisDeep learningSequential organ failure assessment
spellingShingle Juan Wei
Feihong Lin
Tian Jin
Qian Yao
Sheng Wang
Di Feng
Xin Lv
Wen He
Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
Journal of Big Data
Sepsis
Deep learning
Sequential organ failure assessment
title Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
title_full Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
title_fullStr Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
title_full_unstemmed Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
title_short Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors
title_sort dynamic sofa component scores based deep learning for short to long term mortality prediction in sepsis survivors
topic Sepsis
Deep learning
Sequential organ failure assessment
url https://doi.org/10.1186/s40537-025-01234-2
work_keys_str_mv AT juanwei dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT feihonglin dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT tianjin dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT qianyao dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT shengwang dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT difeng dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT xinlv dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors
AT wenhe dynamicsofacomponentscoresbaseddeeplearningforshorttolongtermmortalitypredictioninsepsissurvivors