Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 17, 2025Frontiers in NeurologyOpen Access

Evaluating machine learning models for stroke prediction based on clinical variables

View Full Paper
Ask AI
Bookmark
Share

Authors

PAPatrick O. AkinwumiSOStephen OjoTNThomas I. Nathaniel

Discussion

Loading...

Member takes

Overview

Analysis shows machine learning techniques improve stroke prediction accuracy using clinical variables, suggesting better risk assessment methods.

Key Points

  • Machine learning models demonstrated high accuracy in stroke prediction, achieving a maximum accuracy of 95.11%.
  • Logistic Regression and Gradient Boosting yielded the highest ROC-AUC score of 0.836, indicating good model performance.
  • Feature analysis revealed age, average glucose level, and BMI as key predictors of stroke risk in evaluated models.
  • Results highlight the need for enhanced machine learning methods to improve sensitivity and clinical utility in stroke prediction.

Cite This Study

Akinwumi et al. (2025) studied this question.

synapsesocial.com/papers/68d43285713b0b5dfea719f9https://doi.org/10.3389/fneur.2025.1668420
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Predicting Stroke Risk Based on an Optimized Machine Learning Model2025
  2. 2Abstract 204: Machine Learning for Young Stroke Risk Prediction: An Analysis of Clinical and Biochemical Predictors2025
  3. 3Machine Learning Techniques for Predicting Brain Stroke Risk: Addressing Data Imbalance2025
  4. 4Machine learning techniques for stroke prediction: A systematic review of algorithms, datasets, and regional gaps2025 · 23 citations
  5. 5An Evaluation of Machine Learning Algorithms for an Enhanced Precision Healthcare in Stroke Prediction2024