Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning
Abstract The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Va...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85951-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544712312324096 |
|---|---|
| author | Jingjing Pan Tao Guo Haobo Kong Wei Bu Min Shao Zhi Geng |
| author_facet | Jingjing Pan Tao Guo Haobo Kong Wei Bu Min Shao Zhi Geng |
| author_sort | Jingjing Pan |
| collection | DOAJ |
| description | Abstract The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Variables were screened using the Recursive Feature Elimination method. Five machine learning algorithms were used to build predictive models. Models were evaluated through nested cross-validation to select the best one. The model was interpreted using Shapley Additive Explanations. We selected the optimal model to generate the web calculator. A total of 23 predictive features were selected. The Light Gradient Boosting Machine (LightGBM) model had an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CI: 0.757–0.927), with an external 5-fold cross-validation average AUC of 0.842 ± 0.038, which was superior to the other models. External validation results also demonstrated good performance by the LightGBM model with an AUC of 0.856 (95% CI: 0.792–0.921). Based on this, we generated a web calculator by combining five high importance predictive factors. The LightGBM model was confirmed to be efficient and stable in predicting the mortality risk of patients with SCAP admitted to the ICU. The web calculator based on the LightGBM model can provide clinicians with a prognostic evaluation tool. |
| format | Article |
| id | doaj-art-fddd1951a0f940f49cf3c434c1c09dda |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-fddd1951a0f940f49cf3c434c1c09dda2025-01-12T12:20:54ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-85951-xPrediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learningJingjing Pan0Tao Guo1Haobo Kong2Wei Bu3Min Shao4Zhi Geng5Department of Pulmonary and Critical Care Medicine, Anhui Chest HospitalCenter for Biomedical Imaging, University of Science and Technology of ChinaDepartment of Pulmonary and Critical Care Medicine, Anhui Chest HospitalDepartment of Critical Care Medicine, The First Affiliated Hospital of Anhui Medical UniversityDepartment of Critical Care Medicine, The First Affiliated Hospital of Anhui Medical UniversityDepartment of Neurology, The First Affiliated Hospital of Anhui Medical UniversityAbstract The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Variables were screened using the Recursive Feature Elimination method. Five machine learning algorithms were used to build predictive models. Models were evaluated through nested cross-validation to select the best one. The model was interpreted using Shapley Additive Explanations. We selected the optimal model to generate the web calculator. A total of 23 predictive features were selected. The Light Gradient Boosting Machine (LightGBM) model had an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CI: 0.757–0.927), with an external 5-fold cross-validation average AUC of 0.842 ± 0.038, which was superior to the other models. External validation results also demonstrated good performance by the LightGBM model with an AUC of 0.856 (95% CI: 0.792–0.921). Based on this, we generated a web calculator by combining five high importance predictive factors. The LightGBM model was confirmed to be efficient and stable in predicting the mortality risk of patients with SCAP admitted to the ICU. The web calculator based on the LightGBM model can provide clinicians with a prognostic evaluation tool.https://doi.org/10.1038/s41598-025-85951-xMachine learningSevere community-acquired pneumoniaMortality risk predictionIntensive care unit |
| spellingShingle | Jingjing Pan Tao Guo Haobo Kong Wei Bu Min Shao Zhi Geng Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning Scientific Reports Machine learning Severe community-acquired pneumonia Mortality risk prediction Intensive care unit |
| title | Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning |
| title_full | Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning |
| title_fullStr | Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning |
| title_full_unstemmed | Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning |
| title_short | Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning |
| title_sort | prediction of mortality risk in patients with severe community acquired pneumonia in the intensive care unit using machine learning |
| topic | Machine learning Severe community-acquired pneumonia Mortality risk prediction Intensive care unit |
| url | https://doi.org/10.1038/s41598-025-85951-x |
| work_keys_str_mv | AT jingjingpan predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning AT taoguo predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning AT haobokong predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning AT weibu predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning AT minshao predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning AT zhigeng predictionofmortalityriskinpatientswithseverecommunityacquiredpneumoniaintheintensivecareunitusingmachinelearning |