Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism
Abstract Objectives We aimed to use machine learning (ML) algorithms to risk stratify the prognosis of critical pulmonary embolism (PE). Material and methods In total, 1229 patients were obtained from MIMIC-IV database. Main outcomes were set as all-cause mortality within 30 days. Logistic regressio...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-08-01
|
| Series: | BMC Cardiovascular Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12872-023-03363-z |
| _version_ | 1797752876227887104 |
|---|---|
| author | Geng Wang Jiatang Xu Xixia Lin Weijie Lai Lin Lv Senyi Peng Kechen Li Mingli Luo Jiale Chen Dongxi Zhu Xiong Chen Chen Yao Shaoxu Wu Kai Huang |
| author_facet | Geng Wang Jiatang Xu Xixia Lin Weijie Lai Lin Lv Senyi Peng Kechen Li Mingli Luo Jiale Chen Dongxi Zhu Xiong Chen Chen Yao Shaoxu Wu Kai Huang |
| author_sort | Geng Wang |
| collection | DOAJ |
| description | Abstract Objectives We aimed to use machine learning (ML) algorithms to risk stratify the prognosis of critical pulmonary embolism (PE). Material and methods In total, 1229 patients were obtained from MIMIC-IV database. Main outcomes were set as all-cause mortality within 30 days. Logistic regression (LR) and simplified eXtreme gradient boosting (XGBoost) were applied for model constructions. We chose the final models based on their matching degree with data. To simplify the model and increase its usefulness, finally simplified models were built based on the most important 8 variables. Discrimination and calibration were exploited to evaluate the prediction ability. We stratified the risk groups based on risk estimate deciles. Results The simplified XGB model performed better in model discrimination, which AUC were 0.82 (95% CI: 0.78–0.87) in the validation cohort, compared with the AUC of simplified LR model (0.75 [95% CI: 0.69—0.80]). And XGB performed better than sPESI in the validation cohort. A new risk-classification based on XGB could accurately predict low-risk of mortality, and had high consistency with acknowledged risk scores. Conclusions ML models can accurately predict the 30-day mortality of critical PE patients, which could further be used to reduce the burden of ICU stay, decrease the mortality and improve the quality of life for critical PE patients. |
| first_indexed | 2024-03-12T17:10:51Z |
| format | Article |
| id | doaj.art-fcb07bdca0434adc8f4096c85eba68ae |
| institution | Directory Open Access Journal |
| issn | 1471-2261 |
| language | English |
| last_indexed | 2024-03-12T17:10:51Z |
| publishDate | 2023-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cardiovascular Disorders |
| spelling | doaj.art-fcb07bdca0434adc8f4096c85eba68ae2023-08-06T11:06:16ZengBMCBMC Cardiovascular Disorders1471-22612023-08-0123111210.1186/s12872-023-03363-zMachine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolismGeng Wang0Jiatang Xu1Xixia Lin2Weijie Lai3Lin Lv4Senyi Peng5Kechen Li6Mingli Luo7Jiale Chen8Dongxi Zhu9Xiong Chen10Chen Yao11Shaoxu Wu12Kai Huang13Department of Vascular Interventional Radiology, Zhongshan Hospital of Traditional Chinese MedicineDepartment of Cardiovascular Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen UniversityDepartment of Medicine, Sun Yat-Sen Memorial Hospital South Campus ClinicZhongshan School of Medicine, Sun Yat-Sen UniversityZhongshan School of Medicine, Sun Yat-Sen UniversityZhongshan School of Medicine, Sun Yat-Sen UniversityHospital of Stomatology, Guanghua School of Stomatology, Sun Yat-Sen UniversityZhongshan School of Medicine, Sun Yat-Sen UniversityZhongshan School of Medicine, Sun Yat-Sen UniversityZhongshan School of Medicine, Sun Yat-Sen UniversityDepartment of Urology, SunYat-Sen Memorial Hospital, SunYat-Sen UniversityDepartment of Vascular Surgery, First Affiliated Hospital of Sun Yat-Sen UniversityDepartment of Urology, SunYat-Sen Memorial Hospital, SunYat-Sen UniversityDepartment of Cardiovascular Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen UniversityAbstract Objectives We aimed to use machine learning (ML) algorithms to risk stratify the prognosis of critical pulmonary embolism (PE). Material and methods In total, 1229 patients were obtained from MIMIC-IV database. Main outcomes were set as all-cause mortality within 30 days. Logistic regression (LR) and simplified eXtreme gradient boosting (XGBoost) were applied for model constructions. We chose the final models based on their matching degree with data. To simplify the model and increase its usefulness, finally simplified models were built based on the most important 8 variables. Discrimination and calibration were exploited to evaluate the prediction ability. We stratified the risk groups based on risk estimate deciles. Results The simplified XGB model performed better in model discrimination, which AUC were 0.82 (95% CI: 0.78–0.87) in the validation cohort, compared with the AUC of simplified LR model (0.75 [95% CI: 0.69—0.80]). And XGB performed better than sPESI in the validation cohort. A new risk-classification based on XGB could accurately predict low-risk of mortality, and had high consistency with acknowledged risk scores. Conclusions ML models can accurately predict the 30-day mortality of critical PE patients, which could further be used to reduce the burden of ICU stay, decrease the mortality and improve the quality of life for critical PE patients.https://doi.org/10.1186/s12872-023-03363-zPulmonary embolism (PE)Machine learning (ML)PrognosisMortalityIntensive care unit |
| spellingShingle | Geng Wang Jiatang Xu Xixia Lin Weijie Lai Lin Lv Senyi Peng Kechen Li Mingli Luo Jiale Chen Dongxi Zhu Xiong Chen Chen Yao Shaoxu Wu Kai Huang Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism BMC Cardiovascular Disorders Pulmonary embolism (PE) Machine learning (ML) Prognosis Mortality Intensive care unit |
| title | Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| title_full | Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| title_fullStr | Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| title_full_unstemmed | Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| title_short | Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| title_sort | machine learning based models for predicting mortality and acute kidney injury in critical pulmonary embolism |
| topic | Pulmonary embolism (PE) Machine learning (ML) Prognosis Mortality Intensive care unit |
| url | https://doi.org/10.1186/s12872-023-03363-z |
| work_keys_str_mv | AT gengwang machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT jiatangxu machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT xixialin machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT weijielai machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT linlv machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT senyipeng machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT kechenli machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT mingliluo machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT jialechen machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT dongxizhu machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT xiongchen machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT chenyao machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT shaoxuwu machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism AT kaihuang machinelearningbasedmodelsforpredictingmortalityandacutekidneyinjuryincriticalpulmonaryembolism |