EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of long-term mortality in maintenance hemodialysis patients using machine learning survival models: a prospective multicenter study with SHAP-based interpretation

Xiao Tian, Yaya Yang, Zhiqiang Peng, Yu Wang, Ziyang You, Shenglin Yang, Yumin Li, Yongxin Lu, Yanhong Zhao, Yaozhong Kong, Qijun Wan, Sheng Huang und 4 weitere

Frontiers in Nutrition · 11.11.2026 · 13

DOI: 10.3389/fnut.2026.1956147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Nutrition, online erschienen am 11.11.2026. Verfasst von Xiao Tian und 15 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate and interpretable prediction of long-term mortality in maintenance hemodialysis (MHD) patients remains challenging. This study aimed to develop and externally validate machine learning survival models integrating clinical, nutritional, inflammatory, and anthropometric predictors.

Methods

This prospective multicenter cohort included 1,129 MHD patients from eight dialysis centers in China. Patients were allocated to training ( n = 645), internal validation ( n = 274), and independent external test ( n = 210) cohorts. Predictors were selected using LASSO–Cox regression and Survival Boruta. Five survival machine learning models were developed and evaluated for discrimination, prediction error, calibration, and clinical utility. SHapley Additive exPlanations (SHAP) were used to interpret model predictions.

Results

During a median follow-up of 4.53 years, 603 patients died. 14 predictors were selected for model development. In the external test cohort, gradient boosting survival analysis (GBS) achieved a C-index of 0.748 (95% CI, 0.705–0.790), a 5-year time-dependent AUC of 0.799 (95% CI, 0.726–0.861) and the lowest integrated Brier score (0.141) among the five models. GBS also demonstrated reasonable calibration, although its discrimination was not significantly superior to that of random survival forest. SHAP analysis identified age, prealbumin and diabetes mellitus as the leading contributors to model predictions.

Conclusion

An interpretable GBS model integrating routinely available clinical, nutritional, inflammatory, and anthropometric predictors demonstrated promising performance for long-term mortality risk stratification in MHD patients. Further external validation and prospective clinical evaluation are warranted.

Zitieren

APA

Tian, X., Yang, Y., Peng, Z., Wang, Y., You, Z., Yang, S., Li, Y., Lu, Y., Zhao, Y., Kong, Y., Wan, Q., Huang, S., Liu, Y., Liu, A., Liu, F., & Liang, M. (2026). Prediction of long-term mortality in maintenance hemodialysis patients using machine learning survival models: a prospective multicenter study with SHAP-based interpretation. Frontiers in Nutrition, 13. https://doi.org/10.3389/fnut.2026.1956147

Vancouver

Tian X, Yang Y, Peng Z, Wang Y, You Z, Yang S, et al. Prediction of long-term mortality in maintenance hemodialysis patients using machine learning survival models: a prospective multicenter study with SHAP-based interpretation. Frontiers in Nutrition. 2026;13. doi:10.3389/fnut.2026.1956147

BibTeX
@article{Tian2026,
  author = {Tian, Xiao and Yang, Yaya and Peng, Zhiqiang and Wang, Yu and You, Ziyang and Yang, Shenglin and Li, Yumin and Lu, Yongxin and Zhao, Yanhong and Kong, Yaozhong and Wan, Qijun and Huang, Sheng and Liu, Yan and Liu, Aiqun and Liu, Fanna and Liang, Min},
  title = {Prediction of long-term mortality in maintenance hemodialysis patients using machine learning survival models: a prospective multicenter study with SHAP-based interpretation},
  journal = {Frontiers in Nutrition},
  year = {2026},
  volume = {13},
  doi = {10.3389/fnut.2026.1956147}
}
Kostenlos starten →