EUVIMEDEUVIMED entdecken
Crossref

A Machine Learning-Based Chatbot for Diabetes Diagnosis

Abubakar Abdulazeez, Yahaya Zakariyau Bala

International Journal of Innovation in Science and Technology (IJIST) · 30.05.2026 · 1 (1) · 95-117

DOI: 10.64290/ijsat.v1i1.8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovation in Science and Technology (IJIST), online erschienen am 30.05.2026. Verfasst von Abubakar Abdulazeez und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents the development of a machine learning-based system for diabetes diagnosis, integrated with a self-interactive artificial intelligence chatbot to enhance user engagement and decision support. The Pima Indians Diabetes dataset (768 records) was used, with a 70:30 split for training and testing. Four models; Decision Tree (DT), Support Vector Classifier (SVC), Extreme Gradient Boosting (XGBoost), and Explainable Boosting Machine (EBM) were implemented and evaluated using accuracy, precision, recall, F1-score, and AUC. Results show that all models achieved strong predictive performance, with training accuracy above 85% and testing accuracy exceeding 67%. Among them, EBM outperformed others, achieving the highest predictive performance and demonstrating superior stability and generalization. XGBoost and SVC showed competitive performance, they exhibited slight overfitting, whereas DT recorded comparatively lower recall. To improve transparency, explainable AI techniques were applied, revealing glucose, BMI, and age as the most significant predictors, consistent with clinical knowledge. The integration of these insights into a Streamlit-based chatbot using Python, enables real-time interaction, prediction, and explanation. Overall, the proposed system enhances accuracy, interpretability, and accessibility, supporting early detection and informed healthcare decisions. The study can be enhanced using larger and real-time hospital datasets, incorporating deep learning models and Integrating IoT-based health monitoring systems.

Zitieren

APA

Abdulazeez, A., & Bala, Y. Z. (2026). A Machine Learning-Based Chatbot for Diabetes Diagnosis. International Journal of Innovation in Science and Technology (IJIST), 1(1), 95-117. https://doi.org/10.64290/ijsat.v1i1.8

Vancouver

Abdulazeez A, Bala YZ. A Machine Learning-Based Chatbot for Diabetes Diagnosis. International Journal of Innovation in Science and Technology (IJIST). 2026;1(1):95-117. doi:10.64290/ijsat.v1i1.8

BibTeX
@article{Abdulazeez2026,
  author = {Abdulazeez, Abubakar and Bala, Yahaya Zakariyau},
  title = {A Machine Learning-Based Chatbot for Diabetes Diagnosis},
  journal = {International Journal of Innovation in Science and Technology (IJIST)},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {95--117},
  doi = {10.64290/ijsat.v1i1.8}
}
Kostenlos starten →