Customized and Automated Machine Learning-Based Models for Diabetes Type 2 Classification

Farida Mohsen; Md Rafiul Biswas; Hazrat Ali; Tanvir Alam; Mowafa Househ; Zubair Shah

doi:10.3233/SHTI220779

Customized and Automated Machine Learning-Based Models for Diabetes Type 2 Classification

Stud Health Technol Inform. 2022 Jun 29:295:517-520. doi: 10.3233/SHTI220779.

Authors

Farida Mohsen¹, Md Rafiul Biswas¹, Hazrat Ali¹, Tanvir Alam¹, Mowafa Househ¹, Zubair Shah¹

Affiliation

¹ College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar.

PMID: 35773925
DOI: 10.3233/SHTI220779

Abstract

This study aims to develop models to accurately classify patients with type 2 diabetes using the Practice Fusion dataset. We use Random Forest (RF), Support Vector Classifier (SVC), AdaBoost classifier, an ensemble model, and automated machine learning (AutoML) model. We compare the performance of all models in a five-fold cross-validation scheme using four evaluation measures. Experimental results demonstrate that the AutoML model outperformed individual and ensemble models in all evaluation measures.

Keywords: AutoML; Diabetes classification; Ensemble model; Machine learning.

MeSH terms

Diabetes Mellitus, Type 2* / diagnosis
Humans
Machine Learning
Support Vector Machine