EUVIMEDEUVIMED entdecken
Crossref

Classification of Diabetes Mellitus: A Comparative Analysis of various Machine Learning Algorithms

Esha Nadeem, Rameez Asif, Ali Raza, Adil Mustafa

International Journal of Computer Applications · 28.07.2026 · 187 (129) · 1-9

DOI: 10.5120/ijca544d1849f443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Applications, online erschienen am 28.07.2026. Verfasst von Esha Nadeem und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetes Mellitus, a widespread metabolic disorder characterised by hyperglycaemia, poses a significant global health concern.Unfortunately, it is often diagnosed only after symptoms have developed, thereby reducing opportunities for early intervention.Traditional diagnostic methods primarily identify individuals who are already symptomatic, leaving many at-risk individuals undetected.By integrating machine learning models with Electronic Health Records, it may be possible to identify individuals at high risk during routine health assessments, enabling earlier intervention.This study aims to compare different machine learning algorithms to determine whether an individual has diabetes.Several performance metrics are used for comparison, including precision, accuracy, F1-score, recall, and computational efficiency.The methodology begins with the pre-processing of the Pima Indians Diabetes Dataset, followed by the training, testing, and validation of four machine learning algorithms: Support Vector Machine, Decision Tree, Artificial Neural Network, and Random Forest, implemented using Python.The process is then repeated in MATLAB using an augmented dataset, and the resulting performances are compared.The Random Forest algorithm achieved the highest prediction accuracy, with 75% accuracy on the original dataset and 100% accuracy on the augmented dataset.The findings suggest that machine learning approaches could support healthcare professionals in identifying individuals at risk of diabetes at an earlier stage, potentially enabling timely intervention and improving patient outcomes.

Zitieren

APA

Nadeem, E., Asif, R., Raza, A., & Mustafa, A. (2026). Classification of Diabetes Mellitus: A Comparative Analysis of various Machine Learning Algorithms. International Journal of Computer Applications, 187(129), 1-9. https://doi.org/10.5120/ijca544d1849f443

Vancouver

Nadeem E, Asif R, Raza A, Mustafa A. Classification of Diabetes Mellitus: A Comparative Analysis of various Machine Learning Algorithms. International Journal of Computer Applications. 2026;187(129):1-9. doi:10.5120/ijca544d1849f443

BibTeX
@article{Nadeem2026,
  author = {Nadeem, Esha and Asif, Rameez and Raza, Ali and Mustafa, Adil},
  title = {Classification of Diabetes Mellitus: A Comparative Analysis of various Machine Learning Algorithms},
  journal = {International Journal of Computer Applications},
  year = {2026},
  volume = {187},
  number = {129},
  pages = {1--9},
  doi = {10.5120/ijca544d1849f443}
}
Kostenlos starten →