EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Data-Driven Stroke Prediction: Leveraging KNN for Early Detection in Clinical Datasets

Junna Mae Guilao, Arlah Licay, Jheanne Salan, Jose Agoylo

Journal of Engineering Advancements · 09.07.2026 · 7 (02) · 58-64

DOI: 10.38032/jea.2026.02.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Engineering Advancements, online erschienen am 09.07.2026. Verfasst von Junna Mae Guilao und 3 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explores the application of the K-Nearest Neighbors (KNN) algorithm in predicting stroke risk using a healthcare dataset from Kaggle containing 5,110 patient records with demographic and clinical attributes. Preprocessing steps included categorical encoding, normalization, and feature engineering, followed by model training using a pipeline that incorporated SMOTE to address class imbalance. Hyperparameter tuning via GridSearchCV improved model performance. The final KNN model achieved an accuracy of 84%, with a recall of 0.64 and precision of 0.18 for the stroke class, indicating moderate sensitivity but significant false positive rates typical of imbalanced medical datasets. Evaluation metrics included the confusion matrix, ROC curve (AUC = 0.82), and precision-recall curve (AP = 0.19). While the model demonstrates reasonable discriminative ability, the low precision suggests limited utility as a standalone diagnostic tool. These findings contribute to the growing body of research on machine learning for clinical decision support, emphasizing the need for balanced performance metrics in imbalanced datasets and highlighting KNN's potential as a preliminary screening instrument when combined with clinical judgment.

Zitieren

APA

Guilao, J. M., Licay, A., Salan, J., & Agoylo, J. (2026). Data-Driven Stroke Prediction: Leveraging KNN for Early Detection in Clinical Datasets. Journal of Engineering Advancements, 7(02), 58-64. https://doi.org/10.38032/jea.2026.02.002

Vancouver

Guilao JM, Licay A, Salan J, Agoylo J. Data-Driven Stroke Prediction: Leveraging KNN for Early Detection in Clinical Datasets. Journal of Engineering Advancements. 2026;7(02):58-64. doi:10.38032/jea.2026.02.002

BibTeX
@article{Guilao2026,
  author = {Guilao, Junna Mae and Licay, Arlah and Salan, Jheanne and Agoylo, Jose},
  title = {Data-Driven Stroke Prediction: Leveraging KNN for Early Detection in Clinical Datasets},
  journal = {Journal of Engineering Advancements},
  year = {2026},
  volume = {7},
  number = {02},
  pages = {58--64},
  doi = {10.38032/jea.2026.02.002}
}
Kostenlos starten →