Automated Diabetes Diagnosis Using Machine Learning: A Comprehensive Study

Zhiyuan Cao

2023

Abstract

Diabetes is a harmful illness that disturbed millions of patients around the globe. According to statistics, one out of every ten adults is diagnosed with diabetes in the near future. So it’s essential to take measures to prevent diabetes, but unfortunately, the current tools available for diagnosing this condition are not sufficiently efficient. However, with the development of artificial intelligence, machine learning has been introduced to human’s medical health system. In this study, a scientific test is conducted based on diabetes dataset. Machine learning models is applied to the dataset respectively and model’s accuracies are measured. The result shows that machine learning models perform well on diabetes dataset and GradientBoosting performs better than other algorithms. This research consists of 4 parts, data analysis, data pre-processing, model training and model evaluation. Initially, Exploratory Data Analysis (EDA) is shown to obtain an extensive knowledge of the information at hand, enabling researchers to make informed decisions during subsequent stages. Second, dataset is pre-processed for further research. Then, extensive model training is conducted, utilizing machine learning algorithms customized to the diabetes domain and finally various metrics are recorded to measure the effectiveness of the models.

Download


Paper Citation


in Harvard Style

Cao Z. (2023). Automated Diabetes Diagnosis Using Machine Learning: A Comprehensive Study. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 137-141. DOI: 10.5220/0012800900003885


in Bibtex Style

@conference{daml23,
author={Zhiyuan Cao},
title={Automated Diabetes Diagnosis Using Machine Learning: A Comprehensive Study},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={137-141},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012800900003885},
isbn={978-989-758-705-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Automated Diabetes Diagnosis Using Machine Learning: A Comprehensive Study
SN - 978-989-758-705-4
AU - Cao Z.
PY - 2023
SP - 137
EP - 141
DO - 10.5220/0012800900003885
PB - SciTePress