International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1720288

1720288PublishedVol 10 · Issue 2

A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment

Okwueze Chisom Nneoma MBA Chioma Juliet Agbo Chika

Subject area: Physical Sciences and Environment  ·  Area of research: Machine Learning, Health

DOI: https://doi.org/10.64388/IREV10I2-1720288

Abstract

Stroke remains a leading cause of death and disability worldwide, yet machine learning (ML) models capable of predicting risk are rarely trusted clinically due to their "black-box" nature. This study introduces an explainability-centered hybrid framework, ALE-SHAP, evaluated on 5,110 patient records. A class-weighted Random Forest classifier addressed severe class imbalance (4.9% stroke prevalence), achieving 86.89%accuracy and an AUC-ROC of 0.783. To open the black box, we paired Kernel SHAP which identified age and average glucose level as dominant risk drivers with a novel Enhanced Accumulated Local Effects (ALE) algorithm featuring adaptive binning, spline smoothing, and bootstrapped confidence intervals. Unlike traditional Partial Dependence Plots, which introduced extrapolation errors due to feature multi-collinearity (r=0.33 between age and BMI), our Enhanced ALE revealed clinically valid, non-linear risk thresholds: a sharp inflection point at age 50, an inverted U-shaped BMI curve peaking at 28.4〖" kg/m" 〗^2(mirroring the clinical "obesity paradox"), and a dual-peak glucose risk profile. The framework achieved high explanation fidelity (D=0.925) and stability (S=0.884), offering a reliable, clinically aligned tool for early stroke prevention.

Keywords

Accumulated Local Effects, Explainable Artificial Intelligence, Kernel SHAP, Machine Learning, Stroke Prediction.

How to cite this paper

Okwueze Chisom Nneoma, MBA Chioma Juliet, Agbo Chika "A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment" Iconic Research And Engineering Journals Volume 10 Issue 2 2026 Page 133-139 https://doi.org/10.64388/IREV10I2-1720288
Okwueze Chisom Nneoma, MBA Chioma Juliet, Agbo Chika "A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026, doi: https://doi.org/10.64388/IREV10I2-1720288
Okwueze Chisom Nneoma, MBA Chioma Juliet, Agbo Chika (2026). A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment. Iconic Research And Engineering Journals, 10(2). doi: https://doi.org/10.64388/IREV10I2-1720288
Okwueze Chisom Nneoma, MBA Chioma Juliet, Agbo Chika "A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026. Crossref, https://doi.org/10.64388/IREV10I2-1720288
@article{1720288,
      author = {Okwueze Chisom Nneoma, MBA Chioma Juliet, Agbo Chika},
      title = {A Hybrid Kernel SHAP and Enhanced ALE Framework for Explainable Stroke Risk Assessment},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {2},
      pages = {133-139},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1720288.pdf},
      abstract = {Stroke remains a leading cause of death and disability worldwide, yet machine learning (ML) models capable of predicting risk are rarely trusted clinically due to their "black-box" nature. This study introduces an explainability-centered hybrid framework, ALE-SHAP, evaluated on 5,110 patient records. A class-weighted Random Forest classifier addressed severe class imbalance (4.9% stroke prevalence), achieving 86.89%accuracy and an AUC-ROC of 0.783. To open the black box, we paired Kernel SHAP which identified age and average glucose level as dominant risk drivers with a novel Enhanced Accumulated Local Effects (ALE) algorithm featuring adaptive binning, spline smoothing, and bootstrapped confidence intervals. Unlike traditional Partial Dependence Plots, which introduced extrapolation errors due to feature multi-collinearity (r=0.33 between age and BMI), our Enhanced ALE revealed clinically valid, non-linear risk thresholds: a sharp inflection point at age 50, an inverted U-shaped BMI curve peaking at 28.4〖" kg/m" 〗^2(mirroring the clinical "obesity paradox"), and a dual-peak glucose risk profile. The framework achieved high explanation fidelity (D=0.925) and stability (S=0.884), offering a reliable, clinically aligned tool for early stroke prevention.},
      keywords = {Accumulated Local Effects, Explainable Artificial Intelligence, Kernel SHAP, Machine Learning, Stroke Prediction.},
      month = {August},
      doi = {https://doi.org/10.64388/IREV10I2-1720288}
  }