Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure
<b>Background:</b> Heart failure (HF) ranks among the foremost causes of mortality globally, exhibiting particularly high prevalence and significant impact within intensive care units (ICUs). This study sought to develop, validate, and deploy a time-dependent machine learning model aimed...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/5/511 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711007367168000 |
|---|---|
| author | Jiuyi Wang Qingxia Kang Shiqi Tian Shunli Zhang Kai Wang Guibo Feng |
| author_facet | Jiuyi Wang Qingxia Kang Shiqi Tian Shunli Zhang Kai Wang Guibo Feng |
| author_sort | Jiuyi Wang |
| collection | DOAJ |
| description | <b>Background:</b> Heart failure (HF) ranks among the foremost causes of mortality globally, exhibiting particularly high prevalence and significant impact within intensive care units (ICUs). This study sought to develop, validate, and deploy a time-dependent machine learning model aimed at predicting the one-year all-cause mortality risk in ICU patients diagnosed with HF, thereby facilitating precise prognostic evaluation and risk stratification. <b>Methods:</b> This study encompassed a cohort of 8960 ICU patients with HF sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database (version 3.1). This latest version of the database added data from 2020 to 2022 on the basis of version 2.2 (covering data from 2008 to 2019); therefore, data spanning 2008 to 2019 (<i>n</i> = 5748) were designated for the training set, while data from 2020 to 2022 (<i>n</i> = 3212) were reserved for the test set. The primary endpoint of interest was one-year all-cause mortality. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to select predictive features from an initial pool of 64 candidate variables (including demographic characteristics, vital signs, comorbidities and complications, therapeutic interventions, routine laboratory data, and disease severity scores). Four predictive models were developed and compared: Cox proportional hazards, random survival forest (RSF), Cox proportional hazards deep neural network (DeepSurv), and eXtreme Gradient Boosting (XGBoost). Model performance was assessed using the concordance index (C-index) and Brier score, with model interpretability addressed through SHapley Additive exPlanations (SHAP) and time-dependent Survival SHapley Additive exPlanations (SurvSHAP(t)). <b>Results:</b> This study revealed a one-year mortality rate of 46.1% within the population under investigation. In the training set, LASSO effectively identified 24 features in the model. In the test set, the XGBoost model exhibited superior predictive performance, as evidenced by a C-index of 0.772 and a Brier score of 0.161, outperforming the Cox model (C-index: 0.740, Brier score: 0.175), the RSF model (C-index: 0.747, Brier score: 0.178), and the DeepSur model (C-index: 0.723, Brier score: 0.183). Decision curve analysis validated the clinical utility of the XGBoost model across a broad spectrum of risk thresholds. Feature importance analysis identified the red cell distribution width-to-albumin ratio (RAR), Charlson Comorbidity Index, Simplified Acute Physiology Score II (SAPS II), Acute Physiology Score III (APS III), and the age–bilirubin–INR–creatinine (ABIC) score as the top five predictive factors. Consequently, an online risk prediction tool based on this model has been developed and is publicly accessible. <b>Conclusions:</b> The time-dependent XGBoost model demonstrated robust predictive capability in evaluating the one-year all-cause mortality risk in critically ill HF patients. This model offered a useful tool for early risk identification and supported timely interventions. |
| format | Article |
| id | doaj-art-a877e0fd076045e5b4eafc5efea36855 |
| institution | DOAJ |
| issn | 2306-5354 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-a877e0fd076045e5b4eafc5efea368552025-08-20T03:14:45ZengMDPI AGBioengineering2306-53542025-05-0112551110.3390/bioengineering12050511Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart FailureJiuyi Wang0Qingxia Kang1Shiqi Tian2Shunli Zhang3Kai Wang4Guibo Feng5Department of General Medicine, The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing 402160, ChinaDepartment of Cardiology, The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing 402160, ChinaDepartment of General Medicine, The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing 402160, ChinaDepartment of General Medicine, The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing 402160, ChinaDepartment of Cardiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing 401336, ChinaDepartment of General Medicine, The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing 402160, China<b>Background:</b> Heart failure (HF) ranks among the foremost causes of mortality globally, exhibiting particularly high prevalence and significant impact within intensive care units (ICUs). This study sought to develop, validate, and deploy a time-dependent machine learning model aimed at predicting the one-year all-cause mortality risk in ICU patients diagnosed with HF, thereby facilitating precise prognostic evaluation and risk stratification. <b>Methods:</b> This study encompassed a cohort of 8960 ICU patients with HF sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database (version 3.1). This latest version of the database added data from 2020 to 2022 on the basis of version 2.2 (covering data from 2008 to 2019); therefore, data spanning 2008 to 2019 (<i>n</i> = 5748) were designated for the training set, while data from 2020 to 2022 (<i>n</i> = 3212) were reserved for the test set. The primary endpoint of interest was one-year all-cause mortality. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to select predictive features from an initial pool of 64 candidate variables (including demographic characteristics, vital signs, comorbidities and complications, therapeutic interventions, routine laboratory data, and disease severity scores). Four predictive models were developed and compared: Cox proportional hazards, random survival forest (RSF), Cox proportional hazards deep neural network (DeepSurv), and eXtreme Gradient Boosting (XGBoost). Model performance was assessed using the concordance index (C-index) and Brier score, with model interpretability addressed through SHapley Additive exPlanations (SHAP) and time-dependent Survival SHapley Additive exPlanations (SurvSHAP(t)). <b>Results:</b> This study revealed a one-year mortality rate of 46.1% within the population under investigation. In the training set, LASSO effectively identified 24 features in the model. In the test set, the XGBoost model exhibited superior predictive performance, as evidenced by a C-index of 0.772 and a Brier score of 0.161, outperforming the Cox model (C-index: 0.740, Brier score: 0.175), the RSF model (C-index: 0.747, Brier score: 0.178), and the DeepSur model (C-index: 0.723, Brier score: 0.183). Decision curve analysis validated the clinical utility of the XGBoost model across a broad spectrum of risk thresholds. Feature importance analysis identified the red cell distribution width-to-albumin ratio (RAR), Charlson Comorbidity Index, Simplified Acute Physiology Score II (SAPS II), Acute Physiology Score III (APS III), and the age–bilirubin–INR–creatinine (ABIC) score as the top five predictive factors. Consequently, an online risk prediction tool based on this model has been developed and is publicly accessible. <b>Conclusions:</b> The time-dependent XGBoost model demonstrated robust predictive capability in evaluating the one-year all-cause mortality risk in critically ill HF patients. This model offered a useful tool for early risk identification and supported timely interventions.https://www.mdpi.com/2306-5354/12/5/511heart failureintensive care unitmachine learningtime-dependentrandom survival forestXGBoost |
| spellingShingle | Jiuyi Wang Qingxia Kang Shiqi Tian Shunli Zhang Kai Wang Guibo Feng Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure Bioengineering heart failure intensive care unit machine learning time-dependent random survival forest XGBoost |
| title | Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure |
| title_full | Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure |
| title_fullStr | Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure |
| title_full_unstemmed | Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure |
| title_short | Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure |
| title_sort | development validation and deployment of a time dependent machine learning model for predicting one year mortality risk in critically ill patients with heart failure |
| topic | heart failure intensive care unit machine learning time-dependent random survival forest XGBoost |
| url | https://www.mdpi.com/2306-5354/12/5/511 |
| work_keys_str_mv | AT jiuyiwang developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure AT qingxiakang developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure AT shiqitian developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure AT shunlizhang developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure AT kaiwang developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure AT guibofeng developmentvalidationanddeploymentofatimedependentmachinelearningmodelforpredictingoneyearmortalityriskincriticallyillpatientswithheartfailure |