EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Study on Adopting Machine Learning to Develop Predictive Models for Diabetes

Nafees Akhter Farooqui, Saquib Ali, Raza Abbas Haidri, Mazhar Khaliq

Revolutionary Advances in Computing and Electronics: An International Journal · 11.08.2026 · 2 (2) · 40-55

DOI: 10.65890/race.v2i2.195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Revolutionary Advances in Computing and Electronics: An International Journal, online erschienen am 11.08.2026. Verfasst von Nafees Akhter Farooqui und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High blood sugar can harm the body's organs over time. In addition to issues with the kidneys, eyes, mouth, feet, and nerves, blood vessel damage can lead to heart attacks and strokes. Therefore, using machine learning to anticipate diabetes can assist physicians in making final decisions and initiating therapy. Models such as LightGBM, LDA, KNN, and neural networks were developed during this study. After evaluation, the neural network model performed well, achieving 90% accuracy, a balanced F1 score, and the maximum possible KS statistic of 0.8074. The dataset was pre-processed using techniques such as PCA, random undersampling, standard scaling, label encoding, and manual encoding. GridSearchCV was used to tune the models during training. In addition, the study underscores the real-world implications of implementing machine-learning-based diabetes prediction models in healthcare settings. These models can be trained using various preprocessing techniques, feature selection, and hyperparameter optimization methods, which further improve prediction accuracy and create a scalable framework for clinical decision support systems. The evaluation shows that neural networks can learn the complex, non-linear relationships present in patient data and have demonstrated greater sensitivity to early signs of diabetes. The integration can help healthcare providers to monitor patients in a more proactive way, create more customized treatment plans, and intervene on time, all of which will lead to better health outcomes and minimize the possibility of long-term diabetes complications.

Zitieren

APA

Farooqui, N. A., Ali, S., Haidri, R. A., & Khaliq, M. (2026). A Study on Adopting Machine Learning to Develop Predictive Models for Diabetes. Revolutionary Advances in Computing and Electronics: An International Journal, 2(2), 40-55. https://doi.org/10.65890/race.v2i2.195

Vancouver

Farooqui NA, Ali S, Haidri RA, Khaliq M. A Study on Adopting Machine Learning to Develop Predictive Models for Diabetes. Revolutionary Advances in Computing and Electronics: An International Journal. 2026;2(2):40-55. doi:10.65890/race.v2i2.195

BibTeX
@article{Farooqui2026,
  author = {Farooqui, Nafees Akhter and Ali, Saquib and Haidri, Raza Abbas and Khaliq, Mazhar},
  title = {A Study on Adopting Machine Learning to Develop Predictive Models for Diabetes},
  journal = {Revolutionary Advances in Computing and Electronics: An International Journal},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {40--55},
  doi = {10.65890/race.v2i2.195}
}
Kostenlos starten →