Predicting Diabetes in United Arab Emirates Healthcare: Artificial Intelligence and Data Mining Case Study
DOI:
https://doi.org/10.70135/seejph.vi.406Keywords:
Artificial Intelligence, Data mining, Decision Tree algorithm, Diabetes, Healthcare industry, Medical Center Data, Patient attributes, Predictive Modeling, Risk factors.Abstract
Aim: The primary aim of this article is to address the scarcity of tools available to examine the relationships between different attributes in medical datasets within the healthcare industry. Specifically, the focus is on developing a predictive model for diabetes using Artificial Intelligence and Data Mining techniques in the United Arab Emirates healthcare sector.
Methods: The paper follows a comprehensive approach, employing the four data mining steps: data preprocessing, data exploration, model building, and model evaluation. To build the predictive model, the decision tree algorithm is utilized. Data from 2856 patients, collected from prime hospitals in Dubai, United Arab Emirates, are analyzed and used as the basis for model development.
Results: The research findings indicate that several factors significantly influence the likelihood of developing diabetes. Specifically, age, gender, and genetics emerge as critical determinants in predicting the onset of diabetes. The developed predictive model demonstrates the potential to provide accurate and easy-to-understand results regarding the likelihood of diabetes in the future.
Conclusion: This study highlights the importance of Artificial Intelligence and Data Mining techniques in predicting diabetes within the United Arab Emirates healthcare sector. The findings emphasize the significance of age, gender, and genetics in diabetes prediction. This research addresses the current data scarcity and offers valuable insights for healthcare professionals. Furthermore, the study recommends further research to enhance diabetes prediction models and their application in clinical settings.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.