📄 Sciences Methods and Technologies
International Journal (SciMeTech)

Volume 2 · Issue 2 · 2026
ISSN: 3085-5284
Improving Diabetes Prediction Using a Hybrid Model: Machine Learning and Rule-Based Logic
Chaimae LAHRIRE, Anas ABOU EL KALAM, Wissam ABBASS
Pages 192–196 · Cadi Ayyad University, National School of Applied Sciences, Marrakech, Research Laboratory for Smart and Sustainable Technologies, Marrakech, Morocco
⬇ PDF
Abstract
The objective of this paper is to propose a hybrid approach that combines machine learning techniques with predefined medical rules-based logic in order to improve prediction performance. The dataset used in this study concerning the pathology of diabetes is drawn from the Indian database Pima, in addition to several developed models namely: logistic regression, decision tree and random forest, are evaluated.

The results obtained show that the hybrid model is even more efficient in terms of patient identification, accuracy and memory retention. This proves the importance of combining data-driven methods with rules and medical knowledge to achieve increasingly reliable medical decision-making systems.
Keywords: Diabetes prediction, Hybrid model, Machine learning, Rule-based system

References

  1. World Health Organization. (2023). Diabetes.
  2. Dua, D., & Graff, C. (2020). UCI machine learning repository. University of California, Irvine.
  3. Samek, W., Wiegand, T., & Müller, K.-R. (2021). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296.
  4. American Diabetes Association. (2023). Standards of care in diabetes—2023. Diabetes Care.
  5. Goodfellow, I., Bengio, Y., & Courville, A. (2022). Deep learning. MIT Press.
  6. Chollet, F. (2021). Deep learning with Python (2nd ed.). Manning Publications.
  7. Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras & TensorFlow (3rd ed.). O'Reilly Media.
  8. Zhou, Z. (2021). Machine learning. Springer.
  9. Li, X., et al. (2022). Machine learning-based approaches for diabetes prediction: A systematic review. Computers in Biology and Medicine.
  10. Esteva, A., et al. (2021). A guide to deep learning in healthcare. Nature Medicine.
  11. Lundberg, S. M., et al. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence.
  12. Tjoa, E., & Guan, C. (2021). A survey on explainable artificial intelligence (XAI). IEEE Access.
  13. Ahmad, M., et al. (2021). Explainable AI in healthcare: Applications, challenges and future trends. Artificial Intelligence in Medicine.
SciMeTech · Volume 2, Issue 2 · 2026 · ISSN 3085-5284