Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques

Tahmina Nasrin Poly; Md Mohaimenul Islam; Yu Chuan Jack Li

doi:10.3233/SHTI220752

Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques

Tahmina Nasrin Poly
, Md Mohaimenul Islam
, Yu Chuan Jack Li

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Most screening tests for Diabetes Mellitus (DM) in use today were developed using electronically collected data from Electronic Health Record (EHR). However, developing and under-developing countries are still struggling to build EHR in their hospitals. Due to the lack of HER data, early screening tools are not available for those countries. This study develops a prediction model for early DM by direct questionnaires for a tertiary hospital in Bangladesh. Information gain technique was used to reduce irreverent features. Using selected variables, we developed logistic regression, support vector machine, K-nearest neighbor, Naïve Bayes, random forest (RF), and neural network models to predict diabetes at an early stage. RF outperformed other machine learning algorithms achieved 100% accuracy. These findings suggest that a combination of simple questionnaires and a machine learning algorithm can be a powerful tool to identify undiagnosed DM patients.

Original language	English
Title of host publication	Advances in Informatics, Management and Technology in Healthcare
Editors	John Mantas, Parisis Gallos, Emmanouil Zoulias, Arie Hasman, Mowafa S. Househ, Marianna Diomidous, Joseph Liaskos, Martha Charalampidou
Publisher	IOS Press BV
Pages	409-413
Number of pages	5
ISBN (Electronic)	9781643682907
DOIs	https://doi.org/10.3233/SHTI220752
Publication status	Published - 2022

Publication series

Name	Studies in Health Technology and Informatics
Volume	295
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Diabetes
early-stage prediction
machine learning
random forest

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/SHTI220752

Cite this

Poly, T. N., Islam, M. M., & Li, Y. C. J. (2022). Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques. In J. Mantas, P. Gallos, E. Zoulias, A. Hasman, M. S. Househ, M. Diomidous, J. Liaskos, & M. Charalampidou (Eds.), Advances in Informatics, Management and Technology in Healthcare (pp. 409-413). (Studies in Health Technology and Informatics; Vol. 295). IOS Press BV. https://doi.org/10.3233/SHTI220752

Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques. / Poly, Tahmina Nasrin; Islam, Md Mohaimenul; Li, Yu Chuan Jack.
Advances in Informatics, Management and Technology in Healthcare. ed. / John Mantas; Parisis Gallos; Emmanouil Zoulias; Arie Hasman; Mowafa S. Househ; Marianna Diomidous; Joseph Liaskos; Martha Charalampidou. IOS Press BV, 2022. p. 409-413 (Studies in Health Technology and Informatics; Vol. 295).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Poly, TN, Islam, MM & Li, YCJ 2022, Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques. in J Mantas, P Gallos, E Zoulias, A Hasman, MS Househ, M Diomidous, J Liaskos & M Charalampidou (eds), Advances in Informatics, Management and Technology in Healthcare. Studies in Health Technology and Informatics, vol. 295, IOS Press BV, pp. 409-413. https://doi.org/10.3233/SHTI220752

Poly TN, Islam MM, Li YCJ. Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques. In Mantas J, Gallos P, Zoulias E, Hasman A, Househ MS, Diomidous M, Liaskos J, Charalampidou M, editors, Advances in Informatics, Management and Technology in Healthcare. IOS Press BV. 2022. p. 409-413. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI220752

Poly, Tahmina Nasrin ; Islam, Md Mohaimenul ; Li, Yu Chuan Jack. / Early Diabetes Prediction : A Comparative Study Using Machine Learning Techniques. Advances in Informatics, Management and Technology in Healthcare. editor / John Mantas ; Parisis Gallos ; Emmanouil Zoulias ; Arie Hasman ; Mowafa S. Househ ; Marianna Diomidous ; Joseph Liaskos ; Martha Charalampidou. IOS Press BV, 2022. pp. 409-413 (Studies in Health Technology and Informatics).

@inproceedings{8d00bcb712e043068a6748f348ea811b,

title = "Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques",

abstract = "Most screening tests for Diabetes Mellitus (DM) in use today were developed using electronically collected data from Electronic Health Record (EHR). However, developing and under-developing countries are still struggling to build EHR in their hospitals. Due to the lack of HER data, early screening tools are not available for those countries. This study develops a prediction model for early DM by direct questionnaires for a tertiary hospital in Bangladesh. Information gain technique was used to reduce irreverent features. Using selected variables, we developed logistic regression, support vector machine, K-nearest neighbor, Na{\"i}ve Bayes, random forest (RF), and neural network models to predict diabetes at an early stage. RF outperformed other machine learning algorithms achieved 100\% accuracy. These findings suggest that a combination of simple questionnaires and a machine learning algorithm can be a powerful tool to identify undiagnosed DM patients.",

keywords = "Diabetes, early-stage prediction, machine learning, random forest",

author = "Poly, \{Tahmina Nasrin\} and Islam, \{Md Mohaimenul\} and Li, \{Yu Chuan Jack\}",

note = "Publisher Copyright: {\textcopyright} 2022 The authors and IOS Press.",

year = "2022",

doi = "10.3233/SHTI220752",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press BV",

pages = "409--413",

editor = "John Mantas and Parisis Gallos and Emmanouil Zoulias and Arie Hasman and Househ, \{Mowafa S.\} and Marianna Diomidous and Joseph Liaskos and Martha Charalampidou",

booktitle = "Advances in Informatics, Management and Technology in Healthcare",

address = "Netherlands",

}

TY - GEN

T1 - Early Diabetes Prediction

T2 - A Comparative Study Using Machine Learning Techniques

AU - Poly, Tahmina Nasrin

AU - Islam, Md Mohaimenul

AU - Li, Yu Chuan Jack

PY - 2022

Y1 - 2022

N2 - Most screening tests for Diabetes Mellitus (DM) in use today were developed using electronically collected data from Electronic Health Record (EHR). However, developing and under-developing countries are still struggling to build EHR in their hospitals. Due to the lack of HER data, early screening tools are not available for those countries. This study develops a prediction model for early DM by direct questionnaires for a tertiary hospital in Bangladesh. Information gain technique was used to reduce irreverent features. Using selected variables, we developed logistic regression, support vector machine, K-nearest neighbor, Naïve Bayes, random forest (RF), and neural network models to predict diabetes at an early stage. RF outperformed other machine learning algorithms achieved 100% accuracy. These findings suggest that a combination of simple questionnaires and a machine learning algorithm can be a powerful tool to identify undiagnosed DM patients.

AB - Most screening tests for Diabetes Mellitus (DM) in use today were developed using electronically collected data from Electronic Health Record (EHR). However, developing and under-developing countries are still struggling to build EHR in their hospitals. Due to the lack of HER data, early screening tools are not available for those countries. This study develops a prediction model for early DM by direct questionnaires for a tertiary hospital in Bangladesh. Information gain technique was used to reduce irreverent features. Using selected variables, we developed logistic regression, support vector machine, K-nearest neighbor, Naïve Bayes, random forest (RF), and neural network models to predict diabetes at an early stage. RF outperformed other machine learning algorithms achieved 100% accuracy. These findings suggest that a combination of simple questionnaires and a machine learning algorithm can be a powerful tool to identify undiagnosed DM patients.

KW - Diabetes

KW - early-stage prediction

KW - machine learning

KW - random forest

UR - https://www.scopus.com/pages/publications/85133244028

UR - https://www.scopus.com/pages/publications/85133244028#tab=citedBy

U2 - 10.3233/SHTI220752

DO - 10.3233/SHTI220752

M3 - Conference contribution

C2 - 35773898

AN - SCOPUS:85133244028

T3 - Studies in Health Technology and Informatics

SP - 409

EP - 413

BT - Advances in Informatics, Management and Technology in Healthcare

A2 - Mantas, John

A2 - Gallos, Parisis

A2 - Zoulias, Emmanouil

A2 - Hasman, Arie

A2 - Househ, Mowafa S.

A2 - Diomidous, Marianna

A2 - Liaskos, Joseph

A2 - Charalampidou, Martha

PB - IOS Press BV

ER -

Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques

Abstract

Publication series

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this