A dynamic stacking machine learning framework and prototype software module for real-time hemodialysis hypotension monitoring
Abstract
Background: Intradialytic hypotension (IDH) remains a critical complication in hemodialysis (HD). While machine learning offers predictive potential, a significant gap remains between theoretical algorithms and clinical deployment. This research develops a dynamic stacking machine learning framework and an embedded software module for real-time IDH monitoring. Materials and Methods: Data comprising 2,228,650 HD sessions were gathered from a cohort of 1075 HD patients. Thirteen critical feature parameters were dynamically extracted to capture physiological changes during dialysis. We constructed a stacking ensemble model by amalgamating multiple base learners, linking the model’s findings to established physiological science. To translate this algorithm into practice, we engineered an prototype software module designed to interface seamlessly with HD Information Systems. This module integrates real-time data ingestion, dynamic feature processing, and visual prediction. Results: Physiological analysis identified HD duration and predialysis mean arterial pressure as pivotal risk indicators, consistent with clinical mechanisms. The binary effect of diabetes further highlighted the model’s ability to capture nonlinear interactions. The proposed stacking model achieved a precision of 0.89 (95% confidence interval [CI]: 0.87–0.91) and AUC of 0.94 (95% CI: 0.92–0.95). Crucially, the prototype simulation of the module demonstrated successful offline tracking of physiological trends and provided risk stratification, converting complex algorithmic outputs into actionable clinical alerts. Conclusion: The developed stacking machine learning framework, encapsulated within an embedded software module, offers an effective solution for predicting IDH events during HD treatment. It can enhance monitoring efficiency and facilitate timely prevention strategies, although external validation is necessary before considering any real-world clinical implementation.
Related
- Continuous intra-arterial versus noninvasive blood pressure monitoring for preventing hypotension during anesthesia induction in patients aged ≥ 75 years undergoing noncardiac surgery: a randomized controlled trial.
- CO039 | CLINICAL SAFETY AND MONITORING OF APIXABAN IN HEMODIALYSIS PATIENTS: A PROSPECTIVE STUDY
- A hybrid car-following behavior prediction framework for snowy weather based on stacking ensemble learning
- Beyond solute clearance: the kidney–gut–immune–nutrition axis in hemodialysis and peritoneal dialysis and a proposed framework for integrated risk stratification
- Athlete-AI: a multi-modal artificial intelligence framework for personalized athlete monitoring and injury risk forecasting
BibTeX
@article{ji2026dynamic,
title = {{A dynamic stacking machine learning framework and prototype software module for real-time hemodialysis hypotension monitoring}},
author = {Bin Ji and Jianhua Dong and Minghong Zhang and Yunzhang Cheng and Tianyi Zhang and Mingwei Zhang},
journal = {Journal of Research in Medical Sciences},
year = {2026},
month = jul,
doi = {10.4103/jrms.jrms_216_25},
url = {https://doi.org/10.4103/jrms.jrms_216_25},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - JOUR
TI - A dynamic stacking machine learning framework and prototype software module for real-time hemodialysis hypotension monitoring
AU - Bin Ji
AU - Jianhua Dong
AU - Minghong Zhang
AU - Yunzhang Cheng
AU - Tianyi Zhang
AU - Mingwei Zhang
PY - 2026
DA - 2026/07/01
JO - Journal of Research in Medical Sciences
DO - 10.4103/jrms.jrms_216_25
UR - https://doi.org/10.4103/jrms.jrms_216_25
AB - Background: Intradialytic hypotension (IDH) remains a critical complication in hemodialysis (HD). While machine learning offers predictive potential, a significant gap remains between theoretical algorithms and clinical deployment. This research develops a dynamic stacking machine learning framework and an embedded software module for real-time IDH monitoring. Materials and Methods: Data comprising 2,228,650 HD sessions were gathered from a cohort of 1075 HD patients. Thirteen critical feature parameters were dynamically extracted to capture physiological changes during dialysis. We constructed a stacking ensemble model by amalgamating multiple base learners, linking the model’s findings to established physiological science. To translate this algorithm into practice, we engineered an prototype software module designed to interface seamlessly with HD Information Systems. This module integrates real-time data ingestion, dynamic feature processing, and visual prediction. Results: Physiological analysis identified HD duration and predialysis mean arterial pressure as pivotal risk indicators, consistent with clinical mechanisms. The binary effect of diabetes further highlighted the model’s ability to capture nonlinear interactions. The proposed stacking model achieved a precision of 0.89 (95% confidence interval [CI]: 0.87–0.91) and AUC of 0.94 (95% CI: 0.92–0.95). Crucially, the prototype simulation of the module demonstrated successful offline tracking of physiological trends and provided risk stratification, converting complex algorithmic outputs into actionable clinical alerts. Conclusion: The developed stacking machine learning framework, encapsulated within an embedded software module, offers an effective solution for predicting IDH events during HD treatment. It can enhance monitoring efficiency and facilitate timely prevention strategies, although external validation is necessary before considering any real-world clinical implementation.
SN - 1735-1995
SN - 1735-7136
ER -