A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning

Md Rifatul Islam; Semonti Banik; Kazi Naimur Rahman; Mohammad Mizanur Rahman

doi:10.1016/j.cmpbup.2023.100113

A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning

Md Rifatul Islam
, Semonti Banik
, Kazi Naimur Rahman
, Mohammad Mizanur Rahman

Chittagong University of Engineering and Technology

Research output: Contribution to journal › Article › peer-review

23 Citations (Scopus)

4 Downloads (Pure)

Abstract

Diabetes mellitus, a metabolic disease with elevated blood sugar levels, is a significant global public health concern. Identification of diabetes at its very early stage can reduce the prevalence of cases. This work focuses on developing a machine learning-based system that will have a significant impact on diabetic patient identification. To develop such a system we utilized a dataset made up by acquiring direct questionnaires from Sylhet Diabetic Hospital patients. The dataset contains information about the signs and symptoms of patients who are new or likely to have diabetes. We applied 14 different machine-learning techniques where the Gradient Boosting Machine (GBM) outperformed other algorithms with the highest F1 and ROC scores of 99.37%, and 99.92% respectively. We also employed various ensemble-based approaches that show competitive performance to the individual model's performance.

Original language	English
Article number	100113
Number of pages	10
Journal	Computer Methods and Programs in Biomedicine Update
Volume	4
DOIs	https://doi.org/10.1016/j.cmpbup.2023.100113
Publication status	Published - Jan 2023
Externally published	Yes

Open Access - Access Right Statement

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/bync-nd/4.0/).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Data mining
Diabetes mellitus
Early stage prediction
Gradient Boosting Machine
Machine learning

Access to Document

10.1016/j.cmpbup.2023.100113Licence: CC BY-NC-ND

Full textFinal published version, 1.45 MBLicence: CC BY-NC-ND

Cite this

@article{7103d8008dec415da895bf83381af2b1,

title = "A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning",

abstract = "Diabetes mellitus, a metabolic disease with elevated blood sugar levels, is a significant global public health concern. Identification of diabetes at its very early stage can reduce the prevalence of cases. This work focuses on developing a machine learning-based system that will have a significant impact on diabetic patient identification. To develop such a system we utilized a dataset made up by acquiring direct questionnaires from Sylhet Diabetic Hospital patients. The dataset contains information about the signs and symptoms of patients who are new or likely to have diabetes. We applied 14 different machine-learning techniques where the Gradient Boosting Machine (GBM) outperformed other algorithms with the highest F1 and ROC scores of 99.37\%, and 99.92\% respectively. We also employed various ensemble-based approaches that show competitive performance to the individual model's performance.",

keywords = "Data mining, Diabetes mellitus, Early stage prediction, Gradient Boosting Machine, Machine learning",

author = "Islam, \{Md Rifatul\} and Semonti Banik and Rahman, \{Kazi Naimur\} and Rahman, \{Mohammad Mizanur\}",

year = "2023",

month = jan,

doi = "10.1016/j.cmpbup.2023.100113",

language = "English",

volume = "4",

journal = "Computer Methods and Programs in Biomedicine Update",

issn = "2666-9900",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning

AU - Islam, Md Rifatul

AU - Banik, Semonti

AU - Rahman, Kazi Naimur

AU - Rahman, Mohammad Mizanur

PY - 2023/1

Y1 - 2023/1

N2 - Diabetes mellitus, a metabolic disease with elevated blood sugar levels, is a significant global public health concern. Identification of diabetes at its very early stage can reduce the prevalence of cases. This work focuses on developing a machine learning-based system that will have a significant impact on diabetic patient identification. To develop such a system we utilized a dataset made up by acquiring direct questionnaires from Sylhet Diabetic Hospital patients. The dataset contains information about the signs and symptoms of patients who are new or likely to have diabetes. We applied 14 different machine-learning techniques where the Gradient Boosting Machine (GBM) outperformed other algorithms with the highest F1 and ROC scores of 99.37%, and 99.92% respectively. We also employed various ensemble-based approaches that show competitive performance to the individual model's performance.

AB - Diabetes mellitus, a metabolic disease with elevated blood sugar levels, is a significant global public health concern. Identification of diabetes at its very early stage can reduce the prevalence of cases. This work focuses on developing a machine learning-based system that will have a significant impact on diabetic patient identification. To develop such a system we utilized a dataset made up by acquiring direct questionnaires from Sylhet Diabetic Hospital patients. The dataset contains information about the signs and symptoms of patients who are new or likely to have diabetes. We applied 14 different machine-learning techniques where the Gradient Boosting Machine (GBM) outperformed other algorithms with the highest F1 and ROC scores of 99.37%, and 99.92% respectively. We also employed various ensemble-based approaches that show competitive performance to the individual model's performance.

KW - Data mining

KW - Diabetes mellitus

KW - Early stage prediction

KW - Gradient Boosting Machine

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85169840122

U2 - 10.1016/j.cmpbup.2023.100113

DO - 10.1016/j.cmpbup.2023.100113

M3 - Article

AN - SCOPUS:85169840122

SN - 2666-9900

VL - 4

JO - Computer Methods and Programs in Biomedicine Update

JF - Computer Methods and Programs in Biomedicine Update

M1 - 100113

ER -

A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning

Abstract

Open Access - Access Right Statement

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this