Related Experiment Video
Updated: Oct 13, 2025
Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Kernelized k-Local Hyperplane Distance Nearest-Neighbor Model for Predicting Cerebrovascular Disease in Patients With
Xiaobin Liu1, Xiran Zhang1, Yi Zhang2
1Department of Nephrology, The Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi, China.
Insights
This study introduces a new machine learning model, the kernelized k-local hyperplane nearest-neighbor (KHKNN) model, to accurately predict stroke risk in patients with end-stage renal disease (ESRD). The KHKNN model demonstrates superior performance in classifying stroke risk for this vulnerable patient group.
Area of Science:
- Nephrology
- Neurology
- Data Science
Background:
- Cerebrovascular diseases pose a significant threat to patients with chronic kidney disease (CKD).
- Predicting stroke risk in end-stage renal disease (ESRD) patients is crucial for timely intervention.
- Data imbalance in risk levels can challenge accurate stroke risk classification.
Purpose of the Study:
- To develop and evaluate a novel machine learning model for predicting stroke risk in ESRD patients.
- To address the challenges posed by imbalanced datasets in stroke risk classification.
- To compare the proposed model's performance against conventional machine learning methods.
Main Methods:
- Development of a kernelized k-local hyperplane nearest-neighbor (KHKNN) model.
- Application of the KHKNN model to predict stroke risk in a cohort of ESRD patients.
- Comparative analysis of KHKNN against other standard machine learning algorithms for classification accuracy.
Main Results:
- The proposed KHKNN model effectively classified stroke risk in ESRD patients.
- KHKNN demonstrated superior performance compared to conventional machine learning methods in this classification task.
- The model's ability to handle imbalanced data contributed to its effectiveness.
Conclusions:
- The kernelized k-local hyperplane nearest-neighbor (KHKNN) model is a promising tool for predicting stroke risk in ESRD patients.
- Accurate stroke risk prediction can aid in the early detection and management of cerebrovascular diseases in CKD patients.
- Machine learning, particularly the KHKNN model, offers a viable approach to improve patient survival rates by addressing stroke risk.
Abstract:
Detecting and treating cerebrovascular diseases are essential for the survival of patients with chronic kidney disease (CKD). Machine learning algorithms can be used to effectively predict stroke risk in patients with end-stage renal disease (ESRD). An imbalance in the amount of collected data associated with different risk levels can influence the classification task. Therefore, we propose the use of a kernelized k-local hyperplane nearest-neighbor model (KHKNN) for the effective prediction of stroke risk in patients with ESRD. We compared our proposed method with other conventional machine learning methods, which revealed that our method could effectively perform the task of classifying stroke risk.
