Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study
BackgroundSepsis is a major cause of mortality in intensive care units (ICUs) and continues to pose a significant global health challenge, with sepsis-related deaths contributing substantially to the overall burden on healthcare systems worldwide. The primary objective was to construct and evaluate...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Cellular and Infection Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcimb.2024.1500326/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555057421582336 |
|---|---|
| author | Li Shen Li Shen Jiaqiang Wu Jianger Lan Chao Chen Yi Wang Zhiping Li |
| author_facet | Li Shen Li Shen Jiaqiang Wu Jianger Lan Chao Chen Yi Wang Zhiping Li |
| author_sort | Li Shen |
| collection | DOAJ |
| description | BackgroundSepsis is a major cause of mortality in intensive care units (ICUs) and continues to pose a significant global health challenge, with sepsis-related deaths contributing substantially to the overall burden on healthcare systems worldwide. The primary objective was to construct and evaluate a machine learning (ML) model for forecasting 28-day all-cause mortality among ICU sepsis patients.MethodsData for the study was sourced from the eICU Collaborative Research Database (eICU-CRD) (version 2.0). The main outcome was 28-day all-cause mortality. Predictor selection for the final model was conducted using the least absolute shrinkage and selection operator (LASSO) regression analysis and the Boruta feature selection algorithm. Five machine learning algorithms including logistic regression (LR), decision tree (DT), extreme gradient boosting (XGBoost), support vector machine (SVM), and light gradient boosting machine (lightGBM) were employed to construct models using 10-fold cross-validation. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, recall, and F1 score. Additionally, we performed an interpretability analysis on the model that showed the most stable performance.ResultsThe final study cohort comprised 4564 patients, among whom 568 (12.4%) died within 28 days of ICU admission. The XGBoost algorithm demonstrated the most reliable performance, achieving an AUC of 0.821, balancing sensitivity (0.703) and specificity (0.798). The top three risk predictors of mortality included APACHE score, serum lactate levels, and AST.ConclusionML models reliably predicted 28-day mortality in critically ill sepsis patients. Of the models evaluated, the XGBoost algorithm exhibited the most stable performance in identifying patients at elevated mortality risk. Model interpretability analysis identified crucial predictors, potentially informing clinical decisions for sepsis patients in the ICU. |
| format | Article |
| id | doaj-art-09040836baaa48549250394c60da9f9e |
| institution | Kabale University |
| issn | 2235-2988 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cellular and Infection Microbiology |
| spelling | doaj-art-09040836baaa48549250394c60da9f9e2025-01-08T06:12:08ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882025-01-011410.3389/fcimb.2024.15003261500326Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective studyLi Shen0Li Shen1Jiaqiang Wu2Jianger Lan3Chao Chen4Yi Wang5Zhiping Li6Department of Clinical Pharmacy, Children’s Hospital of Fudan University, National Children’s Medical Center, Shanghai, ChinaDepartment of Pharmacy, Suzhou Hospital, Affiliated Hospital of Medical School, Nanjing University, Suzhou, Jiangsu, ChinaSchool of Life Sciences and Biopharmaceutical Science, Shenyang Pharmaceutical University, Shenyang, ChinaDepartment of Clinical Pharmacy, Children’s Hospital of Fudan University, National Children’s Medical Center, Shanghai, ChinaDepartment of Neonatology, Children’s Hospital of Fudan University, National Children’s Medical Center, Shanghai, ChinaDepartment of Neurology, Children’s Hospital of Fudan University, National Children’s Medical Center, Shanghai, ChinaDepartment of Clinical Pharmacy, Children’s Hospital of Fudan University, National Children’s Medical Center, Shanghai, ChinaBackgroundSepsis is a major cause of mortality in intensive care units (ICUs) and continues to pose a significant global health challenge, with sepsis-related deaths contributing substantially to the overall burden on healthcare systems worldwide. The primary objective was to construct and evaluate a machine learning (ML) model for forecasting 28-day all-cause mortality among ICU sepsis patients.MethodsData for the study was sourced from the eICU Collaborative Research Database (eICU-CRD) (version 2.0). The main outcome was 28-day all-cause mortality. Predictor selection for the final model was conducted using the least absolute shrinkage and selection operator (LASSO) regression analysis and the Boruta feature selection algorithm. Five machine learning algorithms including logistic regression (LR), decision tree (DT), extreme gradient boosting (XGBoost), support vector machine (SVM), and light gradient boosting machine (lightGBM) were employed to construct models using 10-fold cross-validation. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, recall, and F1 score. Additionally, we performed an interpretability analysis on the model that showed the most stable performance.ResultsThe final study cohort comprised 4564 patients, among whom 568 (12.4%) died within 28 days of ICU admission. The XGBoost algorithm demonstrated the most reliable performance, achieving an AUC of 0.821, balancing sensitivity (0.703) and specificity (0.798). The top three risk predictors of mortality included APACHE score, serum lactate levels, and AST.ConclusionML models reliably predicted 28-day mortality in critically ill sepsis patients. Of the models evaluated, the XGBoost algorithm exhibited the most stable performance in identifying patients at elevated mortality risk. Model interpretability analysis identified crucial predictors, potentially informing clinical decisions for sepsis patients in the ICU.https://www.frontiersin.org/articles/10.3389/fcimb.2024.1500326/fullmachine learningsepsis28-day mortalitymulticenter retrospective studyXGBoost |
| spellingShingle | Li Shen Li Shen Jiaqiang Wu Jianger Lan Chao Chen Yi Wang Zhiping Li Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study Frontiers in Cellular and Infection Microbiology machine learning sepsis 28-day mortality multicenter retrospective study XGBoost |
| title | Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study |
| title_full | Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study |
| title_fullStr | Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study |
| title_full_unstemmed | Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study |
| title_short | Interpretable machine learning-based prediction of 28-day mortality in ICU patients with sepsis: a multicenter retrospective study |
| title_sort | interpretable machine learning based prediction of 28 day mortality in icu patients with sepsis a multicenter retrospective study |
| topic | machine learning sepsis 28-day mortality multicenter retrospective study XGBoost |
| url | https://www.frontiersin.org/articles/10.3389/fcimb.2024.1500326/full |
| work_keys_str_mv | AT lishen interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT lishen interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT jiaqiangwu interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT jiangerlan interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT chaochen interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT yiwang interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy AT zhipingli interpretablemachinelearningbasedpredictionof28daymortalityinicupatientswithsepsisamulticenterretrospectivestudy |