A Deep Learning Approach to Diabetes Diagnosis

Zeyu Zhang; Khandaker Asif Ahmed; Md Rakibul Hasan; Tom Gedeon; Md Zakir Hossain

doi:10.1007/978-981-97-5937-8_8

A Deep Learning Approach to Diabetes Diagnosis

Zeyu Zhang^*, Khandaker Asif Ahmed^*, Md Rakibul Hasan^*, Tom Gedeon^*, Md Zakir Hossain^*

^*Corresponding author for this work

School of Computing

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

4 Citations (Scopus)

Abstract

Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in underperformance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis

Original language	English
Title of host publication	Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings
Editors	Ngoc Thanh Nguyen, Krystian Wojtkiewicz, Richard Chbeir, Yannis Manolopoulos, Hamido Fujita, Tzung-Pei Hong, Le Minh Nguyen
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	87-99
Number of pages	13
ISBN (Print)	9789819759361
DOIs	https://doi.org/10.1007/978-981-97-5937-8_8
Publication status	Published - 13 Aug 2024
Event	16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024 - Ras Al Khaimah, United Arab Emirates Duration: 15 Apr 2024 → 18 Apr 2024 https://link.springer.com/book/10.1007/978-981-97-5934-7 https://aciids.pwr.edu.pl/2024/index.php

Publication series

Name	Communications in Computer and Information Science
Volume	2144 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024
Abbreviated title	ACIIDS 2024
Country/Territory	United Arab Emirates
City	Ras Al Khaimah
Period	15/04/24 → 18/04/24
Other	ACIIDS 2024 is an international scientific conference for research in the field of intelligent information and database systems, held 15-18 April 2024 in Ras Al Khaimah, the United Arab Emirates. The conference aims to provide an internationally respected forum for scientific research in the technologies and applications of intelligent information and database systems. The conference is hosted by French SIGAPP Chapter, American University of Ras Al Khaimah and jointly organized by Wrocław University of Science and Technology, Poland, in cooperation with IEEE SMC Technical Committee on Computational Collective Intelligence, European Research Center for Information Systems (ERCIS), University of Newcastle (Australia), Yeungnam University (Korea), Quang Binh University (Vietnam), Leiden University (The Netherlands), Universiti Teknologi Malaysia (Malaysia), Ton Duc Thang University (Vietnam), BINUS University (Indonesia), and Vietnam National University, Hanoi (Vietnam). The proceedings of ACIIDS 2024 will be published by Springer.
Internet address	https://link.springer.com/book/10.1007/978-981-97-5934-7 https://aciids.pwr.edu.pl/2024/index.php

Access to Document

10.1007/978-981-97-5937-8_8

Cite this

Zhang, Z., Ahmed, K. A., Hasan, M. R., Gedeon, T., & Hossain, M. Z. (2024). A Deep Learning Approach to Diabetes Diagnosis. In N. T. Nguyen, K. Wojtkiewicz, R. Chbeir, Y. Manolopoulos, H. Fujita, T.-P. Hong, & L. M. Nguyen (Eds.), Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings (pp. 87-99). (Communications in Computer and Information Science; Vol. 2144 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-5937-8_8

Zhang, Zeyu ; Ahmed, Khandaker Asif ; Hasan, Md Rakibul et al. / A Deep Learning Approach to Diabetes Diagnosis. Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings. editor / Ngoc Thanh Nguyen ; Krystian Wojtkiewicz ; Richard Chbeir ; Yannis Manolopoulos ; Hamido Fujita ; Tzung-Pei Hong ; Le Minh Nguyen. Springer Science and Business Media Deutschland GmbH, 2024. pp. 87-99 (Communications in Computer and Information Science).

@inproceedings{d2d529508c924a158cadf04a5409bba4,

title = "A Deep Learning Approach to Diabetes Diagnosis",

abstract = "Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in underperformance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis",

keywords = "AI for Health, Diabetes Diagnosis, Neural Network, Unbalanced Data",

author = "Zeyu Zhang and Ahmed, {Khandaker Asif} and Hasan, {Md Rakibul} and Tom Gedeon and Hossain, {Md Zakir}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, ACIIDS 2024 ; Conference date: 15-04-2024 Through 18-04-2024",

year = "2024",

month = aug,

day = "13",

doi = "10.1007/978-981-97-5937-8_8",

language = "English",

isbn = "9789819759361",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "87--99",

editor = "Nguyen, {Ngoc Thanh} and Krystian Wojtkiewicz and Richard Chbeir and Yannis Manolopoulos and Hamido Fujita and Tzung-Pei Hong and Nguyen, {Le Minh}",

booktitle = "Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings",

address = "Germany",

url = "https://link.springer.com/book/10.1007/978-981-97-5934-7, https://aciids.pwr.edu.pl/2024/index.php",

}

Zhang, Z, Ahmed, KA, Hasan, MR, Gedeon, T & Hossain, MZ 2024, A Deep Learning Approach to Diabetes Diagnosis. in NT Nguyen, K Wojtkiewicz, R Chbeir, Y Manolopoulos, H Fujita, T-P Hong & LM Nguyen (eds), Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings. Communications in Computer and Information Science, vol. 2144 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 87-99, 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Ras Al Khaimah, United Arab Emirates, 15/04/24. https://doi.org/10.1007/978-981-97-5937-8_8

A Deep Learning Approach to Diabetes Diagnosis. / Zhang, Zeyu; Ahmed, Khandaker Asif; Hasan, Md Rakibul et al.
Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings. ed. / Ngoc Thanh Nguyen; Krystian Wojtkiewicz; Richard Chbeir; Yannis Manolopoulos; Hamido Fujita; Tzung-Pei Hong; Le Minh Nguyen. Springer Science and Business Media Deutschland GmbH, 2024. p. 87-99 (Communications in Computer and Information Science; Vol. 2144 CCIS).

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

TY - GEN

T1 - A Deep Learning Approach to Diabetes Diagnosis

AU - Zhang, Zeyu

AU - Ahmed, Khandaker Asif

AU - Hasan, Md Rakibul

AU - Gedeon, Tom

AU - Hossain, Md Zakir

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024/8/13

Y1 - 2024/8/13

N2 - Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in underperformance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis

AB - Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in underperformance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis

KW - AI for Health

KW - Diabetes Diagnosis

KW - Neural Network

KW - Unbalanced Data

UR - http://www.scopus.com/inward/record.url?scp=85201965162&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-5937-8_8

DO - 10.1007/978-981-97-5937-8_8

M3 - Conference contribution

AN - SCOPUS:85201965162

SN - 9789819759361

T3 - Communications in Computer and Information Science

SP - 87

EP - 99

BT - Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings

A2 - Nguyen, Ngoc Thanh

A2 - Wojtkiewicz, Krystian

A2 - Chbeir, Richard

A2 - Manolopoulos, Yannis

A2 - Fujita, Hamido

A2 - Hong, Tzung-Pei

A2 - Nguyen, Le Minh

PB - Springer Science and Business Media Deutschland GmbH

T2 - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024

Y2 - 15 April 2024 through 18 April 2024

ER -

Zhang Z, Ahmed KA, Hasan MR, Gedeon T, Hossain MZ. A Deep Learning Approach to Diabetes Diagnosis. In Nguyen NT, Wojtkiewicz K, Chbeir R, Manolopoulos Y, Fujita H, Hong TP, Nguyen LM, editors, Recent Challenges in Intelligent Information and Database Systems - 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2024. p. 87-99. (Communications in Computer and Information Science). doi: 10.1007/978-981-97-5937-8_8