Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics
Abstract Introduction The outcome of maintenance hemodialysis (MHD) remains poor, with cardiovascular death accounting for more than half of all-cause death cases. In this study, cardiovascular mortality and all-cause mortality prediction models were developed to investigate the predictive role of m...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Nephrology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12882-025-04291-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849237617098358784 |
|---|---|
| author | Lian-Lian You Cui Dong Zhi-Hong Wang Shuang Zhang Yu Zhang Ting-Ting Kuai Jia Xiao Shu-Xin Liu Qing-Cheng Zeng |
| author_facet | Lian-Lian You Cui Dong Zhi-Hong Wang Shuang Zhang Yu Zhang Ting-Ting Kuai Jia Xiao Shu-Xin Liu Qing-Cheng Zeng |
| author_sort | Lian-Lian You |
| collection | DOAJ |
| description | Abstract Introduction The outcome of maintenance hemodialysis (MHD) remains poor, with cardiovascular death accounting for more than half of all-cause death cases. In this study, cardiovascular mortality and all-cause mortality prediction models were developed to investigate the predictive role of metabolites in MHD patients. Methods Clinical and metabolomics data of 135 hemodialysis patients from a single center were collected with a 6-year follow-up. Univariate Cox regression and random forest were respectively applied to preliminarily screen clinical and metabolomics characteristics, followed by multivariate Cox regression for identifying features predicting cardiovascular or all-cause mortality. Multivariate Cox proportional regression risk models were constructed using clinical, metabolomics, and combined features. Subgroup survival differences were compared via risk score stratification. Results The combined model showed significant superiority in predicting cardiovascular mortality (3-year AUC = 0.901, 5-year AUC = 0.876), surpassing the clinical-only model (0.868/0.826) and metabolomics-only model (0.659/0.641). For all-cause mortality, the combined model demonstrated modest improvement (0.859/0.834) but still outperformed the metabolomics model (0.534/0.653). Thirty 5-fold cross-validations confirmed stable performance. High-risk groups had significantly higher cumulative mortality than low-risk groups (p < 0.0001). Conclusion The metabolomics-alone model showed limited predictive performance, but its synergistic integration with clinical indicators further improved the predictive performance of mortality risk models, particularly for cardiovascular mortality. |
| format | Article |
| id | doaj-art-8f107d89d73d464cba6c41a2cafc9c73 |
| institution | Kabale University |
| issn | 1471-2369 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Nephrology |
| spelling | doaj-art-8f107d89d73d464cba6c41a2cafc9c732025-08-20T04:01:53ZengBMCBMC Nephrology1471-23692025-07-0126111210.1186/s12882-025-04291-0Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomicsLian-Lian You0Cui Dong1Zhi-Hong Wang2Shuang Zhang3Yu Zhang4Ting-Ting Kuai5Jia Xiao6Shu-Xin Liu7Qing-Cheng Zeng8School of Maritime Economics and Management, Dalian Maritime UniversityDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologyDepartment of Nephrology, Central Hospital of Dalian University of TechnologySchool of Maritime Economics and Management, Dalian Maritime UniversityAbstract Introduction The outcome of maintenance hemodialysis (MHD) remains poor, with cardiovascular death accounting for more than half of all-cause death cases. In this study, cardiovascular mortality and all-cause mortality prediction models were developed to investigate the predictive role of metabolites in MHD patients. Methods Clinical and metabolomics data of 135 hemodialysis patients from a single center were collected with a 6-year follow-up. Univariate Cox regression and random forest were respectively applied to preliminarily screen clinical and metabolomics characteristics, followed by multivariate Cox regression for identifying features predicting cardiovascular or all-cause mortality. Multivariate Cox proportional regression risk models were constructed using clinical, metabolomics, and combined features. Subgroup survival differences were compared via risk score stratification. Results The combined model showed significant superiority in predicting cardiovascular mortality (3-year AUC = 0.901, 5-year AUC = 0.876), surpassing the clinical-only model (0.868/0.826) and metabolomics-only model (0.659/0.641). For all-cause mortality, the combined model demonstrated modest improvement (0.859/0.834) but still outperformed the metabolomics model (0.534/0.653). Thirty 5-fold cross-validations confirmed stable performance. High-risk groups had significantly higher cumulative mortality than low-risk groups (p < 0.0001). Conclusion The metabolomics-alone model showed limited predictive performance, but its synergistic integration with clinical indicators further improved the predictive performance of mortality risk models, particularly for cardiovascular mortality.https://doi.org/10.1186/s12882-025-04291-0All-cause mortalityCardiovascular mortalityMaintenance hemodialysisMetabolomicsPrediction model |
| spellingShingle | Lian-Lian You Cui Dong Zhi-Hong Wang Shuang Zhang Yu Zhang Ting-Ting Kuai Jia Xiao Shu-Xin Liu Qing-Cheng Zeng Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics BMC Nephrology All-cause mortality Cardiovascular mortality Maintenance hemodialysis Metabolomics Prediction model |
| title | Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| title_full | Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| title_fullStr | Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| title_full_unstemmed | Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| title_short | Development of cardiovascular and all-cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| title_sort | development of cardiovascular and all cause mortality risk prediction models for maintenance hemodialysis patients based on metabolomics |
| topic | All-cause mortality Cardiovascular mortality Maintenance hemodialysis Metabolomics Prediction model |
| url | https://doi.org/10.1186/s12882-025-04291-0 |
| work_keys_str_mv | AT lianlianyou developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT cuidong developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT zhihongwang developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT shuangzhang developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT yuzhang developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT tingtingkuai developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT jiaxiao developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT shuxinliu developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics AT qingchengzeng developmentofcardiovascularandallcausemortalityriskpredictionmodelsformaintenancehemodialysispatientsbasedonmetabolomics |