Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods

Authors

DOI:

https://doi.org/10.3991/ijoe.v19i15.42417

Keywords:

Diabetes, Decision trees, Machine learning, Diagnosis, Support Vector

Abstract


Detection and management of diabetes at an early stage is essential since it is rapidly becoming a global health crisis in many countries. Predictions of diabetes using machine learning algorithms have been promising. In this work, we use data collected from the Pima Indians to assess the performance of multiple machine-learning approaches to diabetes prediction. Ages, body mass indexes, and glucose levels for 768 patients are included in the data set. The methods evaluated are Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbors, Naive Bayes, Support Vector Machine, Gradient Boosting, and Neural Network. The findings indicate that the Logistic Regression and Neural Network models perform the best on most criteria when considering all classes together. The SVM, Random Forest, and Naive Bayes models also receive moderate to high scores, suggesting their strength as classification models. However, the kNN and Tree models show poorer scores on most criteria across all classes, making them less favorable choices for this dataset. The SGD, AdaBoost, and CN2 rule inducer models perform the poorest when comparing all models using a weighted average of class scores. The results of the study suggest that machine learning algorithms may help predict the onset of diabetes and for detecting the disease at an early stage.

Author Biographies

Mohammad Subhi Al-Batah

Mohammad Subhi Al-Batah holds a PhD in Computer Science with a specialization in Artificial Intelligence, which he received from the University of Science Malaysia in 2009. He currently serves as a lecturer at the Faculty of Sciences and Information Technology in Jadara University, Jordan. In 2018, he also served as the Director of the Academic Development and Quality Assurance Center at Jadara University. Dr. Al-Batah's research interests span a range of topics, including image processing, Artificial Intelligence, real-time classification, and software engineering. He may be contacted at the following email address: albatah@jadara.edu.jo

Muhyeeddin Alqaraleh

Muhyeeddin Alqaraleh is an Assistant Professor at Jadara University. Dr. Alqaraleh's areas of expertise include Computer Engineering, Information and Communication Technology, Computer Networking, Digital Signal Processing, Electronics and Communication Engineering, Signal, Image and Video Processing, Information Technology, Network Communication, Communication & Signal Processing, Networking, Cloud Computing, Network Security, Network Architecture, Wireless Computing, Network technology, Signal Processing, Signal Processing for Communication, Radio Communication, Information Theory, Discrete-Time Signal Processing, Computer Technology, IT Infrastructure, Hardware Troubleshooting, Computer Networks Security, Security, Network Management, IT Security, Network Administration, Network Configuration, Network Simulation, and Information Security. He is fluent in English, Arabic, and Russian. He may be contacted at the following email address: m.qaralleh@jadara.edu.jo

Ahmad Abuashour, Arab Open University

Ahmad Abuashour is a Professor Assistant in the Department of Information Technology and Computing at Arab Open University in Kuwait. He received his Bachelor of Engineering degree in Computer Engineering from Jordan University of Science and Technology and his Master of Engineering degree in Electrical Engineering from Concordia University. Currently, he is pursuing his PhD in Electrical Engineering at Ecole de Technologie Superieure (ETS), University of Quebec, Canada. His current research interests are focused on Intelligent Transportation Systems (ITS), Vehicular Ad-Hoc Networks (VANETs), cluster-based routing protocols, network management and monitoring, and quality of service. Specifically, he is concentrating on VANET routing protocols. The Faculty of Computer Studies at Arab Open University is in the Ardiya Industrial Area, Farwanya, with the Information Technology and Computing (ITC) department being assigned the postal code 13033. Postal correspondence may be addressed to P.O. Box 3322 Kuwait. To contact Ahmad Abuashour, please use the following email address: aabuashour@aou.edu.kw

Ahmad Fuad Hamadah Bader, Jadara University

Ahmad Fuad Hamadah Bader is an Assistant Professor at the Department of Communication and Computer Engineering in the Engineering College of Jadara University, located in Irbid, Jordan. He holds a Ph.D. in Engineering with a specialization in Computer Systems and Networks from Donetsk State Technical University in Donetsk, Ukraine, which he earned in 2007. He also holds a Master of Science in Engineering degree in Computer Systems Complexes and Networks from State Technical University named after Beruni in Tashkent, Uzbekistan, which he earned in 1992, and a Bachelor of Science in Engineering degree in Computer Systems Complexes and Networks from Donetsk State Technical University in Donetsk, Ukraine, which he earned in 1989. He may be contacted at the following email address: abader@jadara.edu.jo

Downloads

Published

2023-10-25

How to Cite

Salem Alzboon, M., Subhi Al-Batah, M. ., Alqaraleh, M. ., Abuashour, A. ., & Hamadah Bader, A. F. . (2023). Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods . International Journal of Online and Biomedical Engineering (iJOE), 19(15), pp. 144–165. https://doi.org/10.3991/ijoe.v19i15.42417

Issue

Section

Papers