Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling
Abstract Sepsis is a life-threatening condition that presents substantial challenges to healthcare and pharmacological management due to its high mortality rates and complex patient responses. Accurately predicting patient outcomes is essential for optimizing therapeutic interventions and improving...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-05876-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334954498981888 |
|---|---|
| author | Kaida Cai Xiaofang Yang Zhengyan Wang Wenzhi Fu Hanwen Liu Fatemeh Mahmoudi |
| author_facet | Kaida Cai Xiaofang Yang Zhengyan Wang Wenzhi Fu Hanwen Liu Fatemeh Mahmoudi |
| author_sort | Kaida Cai |
| collection | DOAJ |
| description | Abstract Sepsis is a life-threatening condition that presents substantial challenges to healthcare and pharmacological management due to its high mortality rates and complex patient responses. Accurately predicting patient outcomes is essential for optimizing therapeutic interventions and improving clinical decision-making. This study evaluates the predictive performance of the Cox proportional hazards model and advanced machine learning techniques, such as extreme gradient boosting (XGBoost), gradient boosting machine (GBM), and random survival forests (RSF), in forecasting survival outcomes for sepsis patients. Feature selection methods, including adaptive elastic net (AEN), smoothly clipped absolute deviation (SCAD), minimax concave penalty (MCP), and information gain (IG), were employed to refine model performance by identifying the most relevant clinical features. The results demonstrate that XGBoost consistently outperforms the Cox model, achieving a higher concordance index and demonstrating superior accuracy in handling complex, non-linear clinical interactions. The integration of feature selection further enhanced the machine learning models’ predictive capabilities. These findings emphasize the potential of machine learning techniques to improve outcome prediction and guide personalized treatment strategies, offering valuable tools for critical care settings. |
| format | Article |
| id | doaj-art-7dc63f0d73be4a45b2c11a7487fd4e3c |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7dc63f0d73be4a45b2c11a7487fd4e3c2025-08-20T03:45:26ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-05876-3Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modelingKaida Cai0Xiaofang Yang1Zhengyan Wang2Wenzhi Fu3Hanwen Liu4Fatemeh Mahmoudi5School of Public Health, Southeast UniversitySchool of Mathematics, Southeast UniversitySchool of Mathematics, Southeast UniversitySchool of Mathematics, Southeast UniversitySchool of Mathematics, Southeast UniversityDepartment of Mathematics and Computing, Faculty of Science and Technology, Mount Royal UniversityAbstract Sepsis is a life-threatening condition that presents substantial challenges to healthcare and pharmacological management due to its high mortality rates and complex patient responses. Accurately predicting patient outcomes is essential for optimizing therapeutic interventions and improving clinical decision-making. This study evaluates the predictive performance of the Cox proportional hazards model and advanced machine learning techniques, such as extreme gradient boosting (XGBoost), gradient boosting machine (GBM), and random survival forests (RSF), in forecasting survival outcomes for sepsis patients. Feature selection methods, including adaptive elastic net (AEN), smoothly clipped absolute deviation (SCAD), minimax concave penalty (MCP), and information gain (IG), were employed to refine model performance by identifying the most relevant clinical features. The results demonstrate that XGBoost consistently outperforms the Cox model, achieving a higher concordance index and demonstrating superior accuracy in handling complex, non-linear clinical interactions. The integration of feature selection further enhanced the machine learning models’ predictive capabilities. These findings emphasize the potential of machine learning techniques to improve outcome prediction and guide personalized treatment strategies, offering valuable tools for critical care settings.https://doi.org/10.1038/s41598-025-05876-3Machine learningSurvival analysisFeature selectionMissing data imputationSepsis |
| spellingShingle | Kaida Cai Xiaofang Yang Zhengyan Wang Wenzhi Fu Hanwen Liu Fatemeh Mahmoudi Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling Scientific Reports Machine learning Survival analysis Feature selection Missing data imputation Sepsis |
| title | Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling |
| title_full | Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling |
| title_fullStr | Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling |
| title_full_unstemmed | Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling |
| title_short | Survival analysis for sepsis patients: A machine learning approach to feature selection and predictive modeling |
| title_sort | survival analysis for sepsis patients a machine learning approach to feature selection and predictive modeling |
| topic | Machine learning Survival analysis Feature selection Missing data imputation Sepsis |
| url | https://doi.org/10.1038/s41598-025-05876-3 |
| work_keys_str_mv | AT kaidacai survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling AT xiaofangyang survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling AT zhengyanwang survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling AT wenzhifu survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling AT hanwenliu survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling AT fatemehmahmoudi survivalanalysisforsepsispatientsamachinelearningapproachtofeatureselectionandpredictivemodeling |