A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning

Emmanuel Mbuya; Tsholofelo Diphoko Mokheleli; Tebogo Bokaba; Patrick Ndayizigamiye

A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning

Emmanuel Mbuya
, Tsholofelo Diphoko Mokheleli
, Tebogo Bokaba
, Patrick Ndayizigamiye

Applied Information Systems

University of Johannesburg

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

Abstract

The global prevalence of diabetes mellitus poses a significant public health challenge. This study aims to use dimensionality reduction methods with machine learning (ML) algorithms to predict the diabetes stage and assess the performance of the developed predictive model. Unlike many studies on predicting diabetes, this study makes use of both medical indicators and social determinants of health to predict the risk of diabetes. Utilizing a large dataset obtained from the Centers for Disease Control and Prevention, comprising 253,680 instances and 23 features, this study employs various ML algorithms and dimensionality reduction techniques. In addition, the study applied several metrics namely accuracy, precision, recall, F1 score, Receiver Operating Characteristic, Area Under the Curve, and balanced accuracy. The study finds that Logistic Regression and XGBoost models outperform other classifiers, achieving an accuracy of 85%. The study suggests that future work could benefit from incorporating deep learning techniques.

Original language	English
Title of host publication	International Conference on Information Systems, ICIS 2023
Subtitle of host publication	"Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies"
Publisher	Association for Information Systems
ISBN (Electronic)	9781713893622
Publication status	Published - 2023
Event	44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023 - Hyderibad, India Duration: 10 Dec 2023 → 13 Dec 2023

Publication series

Name	International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies"

Conference

Conference	44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023
Country/Territory	India
City	Hyderibad
Period	10/12/23 → 13/12/23

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Cross-validation
Diabetes Mellitus
Dimensionality Reduction
Machine Learning

ASJC Scopus subject areas

Computer Science Applications
Information Systems

Cite this

Mbuya, E., Mokheleli, T. D., Bokaba, T., & Ndayizigamiye, P. (2023). A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning. In International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies" (International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies"). Association for Information Systems.

Mbuya, Emmanuel ; Mokheleli, Tsholofelo Diphoko ; Bokaba, Tebogo et al. / A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning. International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies". Association for Information Systems, 2023. (International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies").

@inproceedings{56c9cf90b7f8436ba7f4deba31e03341,

title = "A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning",

abstract = "The global prevalence of diabetes mellitus poses a significant public health challenge. This study aims to use dimensionality reduction methods with machine learning (ML) algorithms to predict the diabetes stage and assess the performance of the developed predictive model. Unlike many studies on predicting diabetes, this study makes use of both medical indicators and social determinants of health to predict the risk of diabetes. Utilizing a large dataset obtained from the Centers for Disease Control and Prevention, comprising 253,680 instances and 23 features, this study employs various ML algorithms and dimensionality reduction techniques. In addition, the study applied several metrics namely accuracy, precision, recall, F1 score, Receiver Operating Characteristic, Area Under the Curve, and balanced accuracy. The study finds that Logistic Regression and XGBoost models outperform other classifiers, achieving an accuracy of 85\%. The study suggests that future work could benefit from incorporating deep learning techniques.",

keywords = "Cross-validation, Diabetes Mellitus, Dimensionality Reduction, Machine Learning",

author = "Emmanuel Mbuya and Mokheleli, \{Tsholofelo Diphoko\} and Tebogo Bokaba and Patrick Ndayizigamiye",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 [Emmanuel Mbuya, Tsholofelo Diphoko Mokheleli, Tebogo Bokaba, Patrick Ndayizigamiye].; 44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023 ; Conference date: 10-12-2023 Through 13-12-2023",

year = "2023",

language = "English",

series = "International Conference on Information Systems, ICIS 2023: {"}Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies{"}",

publisher = "Association for Information Systems",

booktitle = "International Conference on Information Systems, ICIS 2023",

address = "United States",

}

Mbuya, E, Mokheleli, TD, Bokaba, T & Ndayizigamiye, P 2023, A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning. in International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies". International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies", Association for Information Systems, 44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023, Hyderibad, India, 10/12/23.

A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning. / Mbuya, Emmanuel; Mokheleli, Tsholofelo Diphoko; Bokaba, Tebogo et al.
International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies". Association for Information Systems, 2023. (International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies").

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

TY - GEN

T1 - A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning

AU - Mbuya, Emmanuel

AU - Mokheleli, Tsholofelo Diphoko

AU - Bokaba, Tebogo

AU - Ndayizigamiye, Patrick

PY - 2023

Y1 - 2023

N2 - The global prevalence of diabetes mellitus poses a significant public health challenge. This study aims to use dimensionality reduction methods with machine learning (ML) algorithms to predict the diabetes stage and assess the performance of the developed predictive model. Unlike many studies on predicting diabetes, this study makes use of both medical indicators and social determinants of health to predict the risk of diabetes. Utilizing a large dataset obtained from the Centers for Disease Control and Prevention, comprising 253,680 instances and 23 features, this study employs various ML algorithms and dimensionality reduction techniques. In addition, the study applied several metrics namely accuracy, precision, recall, F1 score, Receiver Operating Characteristic, Area Under the Curve, and balanced accuracy. The study finds that Logistic Regression and XGBoost models outperform other classifiers, achieving an accuracy of 85%. The study suggests that future work could benefit from incorporating deep learning techniques.

AB - The global prevalence of diabetes mellitus poses a significant public health challenge. This study aims to use dimensionality reduction methods with machine learning (ML) algorithms to predict the diabetes stage and assess the performance of the developed predictive model. Unlike many studies on predicting diabetes, this study makes use of both medical indicators and social determinants of health to predict the risk of diabetes. Utilizing a large dataset obtained from the Centers for Disease Control and Prevention, comprising 253,680 instances and 23 features, this study employs various ML algorithms and dimensionality reduction techniques. In addition, the study applied several metrics namely accuracy, precision, recall, F1 score, Receiver Operating Characteristic, Area Under the Curve, and balanced accuracy. The study finds that Logistic Regression and XGBoost models outperform other classifiers, achieving an accuracy of 85%. The study suggests that future work could benefit from incorporating deep learning techniques.

KW - Cross-validation

KW - Diabetes Mellitus

KW - Dimensionality Reduction

KW - Machine Learning

UR - https://www.scopus.com/pages/publications/85192510008

M3 - Conference contribution

AN - SCOPUS:85192510008

T3 - International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies"

BT - International Conference on Information Systems, ICIS 2023

PB - Association for Information Systems

T2 - 44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023

Y2 - 10 December 2023 through 13 December 2023

ER -

Mbuya E, Mokheleli TD, Bokaba T, Ndayizigamiye P. A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning. In International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies". Association for Information Systems. 2023. (International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies").

A Multiclass Approach to Predicting Diabetes Stage Using Machine Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this