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

Na minha lista:
Detalhes bibliográficos
Publicado no:Journal of Big Data vol. 12, no. 1 (Jul 2025), p. 165
Autor principal: Wei, Juan
Outros Autores: Lin, Feihong, Jin, Tian, Yao, Qian, Wang, Sheng, Feng, Di, Lv, Xin, He, Wen
Publicado em:
Springer Nature B.V.
Assuntos:
Acesso em linha:Citation/Abstract
Full Text
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

MARC

LEADER 00000nab a2200000uu 4500
001 3229357675
003 UK-CbPIL
022 |a 2196-1115 
024 7 |a 10.1186/s40537-025-01234-2  |2 doi 
035 |a 3229357675 
045 2 |b d20250701  |b d20250731 
100 1 |a Wei, Juan  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
245 1 |a Dynamic SOFA component scores-based deep learning for short to long-term mortality prediction in sepsis survivors 
260 |b Springer Nature B.V.  |c Jul 2025 
513 |a Journal Article 
520 3 |a BackgroundSepsis 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.MethodsThis 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).Results7532 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.ConclusionsSepsis 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. 
653 |a Patients 
653 |a Electronic health records 
653 |a Deep learning 
653 |a Sepsis 
653 |a Mortality 
653 |a Multilayer perceptrons 
653 |a Neural networks 
653 |a Survival 
653 |a Ablation 
653 |a Optimization 
653 |a Resource allocation 
653 |a Hospitals 
653 |a Data processing 
653 |a Machine learning 
653 |a Time series 
653 |a Intensive care 
653 |a Global health 
653 |a Survival analysis 
653 |a Critical care 
653 |a Hematology 
653 |a Big Data 
653 |a Databases 
653 |a Experiments 
653 |a Long term 
653 |a Robustness 
653 |a Survivor 
653 |a Mortality rates 
653 |a Anatomical systems 
653 |a Discharge 
653 |a Predictions 
653 |a Vulnerability 
653 |a High risk 
653 |a Health services 
653 |a Health care 
700 1 |a Lin, Feihong  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a Jin, Tian  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a Yao, Qian  |u Tongji University, Clinical Research Center, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a Wang, Sheng  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a Feng, Di  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a Lv, Xin  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535) 
700 1 |a He, Wen  |u Tongji University, Department of Anesthesiology, Shanghai Pulmonary Hospital, School of Medicine, Shanghai, China (GRID:grid.24516.34) (ISNI:0000000123704535); The Quzhou Affiliated Hospital of Wenzhou Medical University, Reproductive Medicine Center, Quzhou People’s Hospital, Quzhou, China (GRID:grid.268099.c) (ISNI:0000 0001 0348 3990) 
773 0 |t Journal of Big Data  |g vol. 12, no. 1 (Jul 2025), p. 165 
786 0 |d ProQuest  |t ABI/INFORM Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3229357675/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3229357675/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3229357675/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch