An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes

Wenfei Wu; Wenlin Zhang; Soban Sadiq; Gary Tse; Syed Ghufran Khalid; Yimeng Fan; Haipeng Liu

doi:10.1016/B978-0-323-95686-4.00027-7

An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes

Wenfei Wu
, Wenlin Zhang
, Soban Sadiq
, Gary Tse
, Syed Ghufran Khalid
, Yimeng Fan
, Haipeng Liu

Zhejiang University
Kent and Medway Medical School
Hong Kong Metropolitan University
The Second Hospital of Tianjin Medical University
Nottingham Trent University
The First Affiliated Hospital of Xi'an Jiaotong University

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

4 Citations (Scopus)

Abstract

Diabetes mellitus (DM) is defined as a group of metabolic disorders characterized by a long-term high blood sugar level caused by abnormal insulin secretion and/or action. Different medications have been developed but the treatment efficacy is patient-specific. The evidence-based prediction of DM treatment response can provide specific reference for self-management, clinical intervention and medication. Recently, some machine learning models have been proposed for the diagnosis of DM. Whereas, the applications in predicting treatment response are limited. The data-driven approach empowered by machine learning enables patient-tailored therapy based on multimodal big health data analysis. In this chapter, we overviewed the state-of-the-art machine learning techniques regarding the data, algorithm, and performance. We summarized the advantages, limitations, and future directions. This chapter provides an up-to-date reference for clinicians, data scientists, and biomedical engineers to improve the treatment for D

Original language	English
Title of host publication	Internet of Things and Machine Learning for Type I and Type II Diabetes
Subtitle of host publication	Use cases
Editors	Sujata Dash, Subhendu Kumar Pani, Willy Susilo, Bernard Man Yung Cheung, Gary Tse
Publisher	Elsevier
Chapter	27
Pages	397-409
Number of pages	13
Edition	1
ISBN (Print)	978-0-323-95686-4
DOIs	https://doi.org/10.1016/B978-0-323-95686-4.00027-7
Publication status	Published - 19 Jul 2024

Bibliographical note

Publisher Copyright:
© 2024 Elsevier Inc. All rights are reserved including those for text and data mining AI training and similar technologies.

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Diabetes mellitus
Hb1Ac
Hypertension
Insulin
Machine learning
Treatment response

Access to Document

10.1016/B978-0-323-95686-4.00027-7

Cite this

Wu, W., Zhang, W., Sadiq, S., Tse, G., Khalid, S. G., Fan, Y., & Liu, H. (2024). An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes. In S. Dash, S. K. Pani, W. Susilo, B. M. Y. Cheung, & G. Tse (Eds.), Internet of Things and Machine Learning for Type I and Type II Diabetes: Use cases (1 ed., pp. 397-409). Elsevier. https://doi.org/10.1016/B978-0-323-95686-4.00027-7

An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes. / Wu, Wenfei; Zhang, Wenlin; Sadiq, Soban et al.
Internet of Things and Machine Learning for Type I and Type II Diabetes: Use cases. ed. / Sujata Dash; Subhendu Kumar Pani; Willy Susilo; Bernard Man Yung Cheung; Gary Tse. 1. ed. Elsevier, 2024. p. 397-409.

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

Wu, W, Zhang, W, Sadiq, S, Tse, G, Khalid, SG, Fan, Y & Liu, H 2024, An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes. in S Dash, SK Pani, W Susilo, BMY Cheung & G Tse (eds), Internet of Things and Machine Learning for Type I and Type II Diabetes: Use cases. 1 edn, Elsevier, pp. 397-409. https://doi.org/10.1016/B978-0-323-95686-4.00027-7

Wu W, Zhang W, Sadiq S, Tse G, Khalid SG, Fan Y et al. An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes. In Dash S, Pani SK, Susilo W, Cheung BMY, Tse G, editors, Internet of Things and Machine Learning for Type I and Type II Diabetes: Use cases. 1 ed. Elsevier. 2024. p. 397-409 doi: 10.1016/B978-0-323-95686-4.00027-7

Wu, Wenfei ; Zhang, Wenlin ; Sadiq, Soban et al. / An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes. Internet of Things and Machine Learning for Type I and Type II Diabetes: Use cases. editor / Sujata Dash ; Subhendu Kumar Pani ; Willy Susilo ; Bernard Man Yung Cheung ; Gary Tse. 1. ed. Elsevier, 2024. pp. 397-409

@inbook{409bb13bbf234939b5e124e45511b38f,

title = "An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes",

abstract = "Diabetes mellitus (DM) is defined as a group of metabolic disorders characterized by a long-term high blood sugar level caused by abnormal insulin secretion and/or action. Different medications have been developed but the treatment efficacy is patient-specific. The evidence-based prediction of DM treatment response can provide specific reference for self-management, clinical intervention and medication. Recently, some machine learning models have been proposed for the diagnosis of DM. Whereas, the applications in predicting treatment response are limited. The data-driven approach empowered by machine learning enables patient-tailored therapy based on multimodal big health data analysis. In this chapter, we overviewed the state-of-the-art machine learning techniques regarding the data, algorithm, and performance. We summarized the advantages, limitations, and future directions. This chapter provides an up-to-date reference for clinicians, data scientists, and biomedical engineers to improve the treatment for D",

keywords = "Diabetes mellitus, Hb1Ac, Hypertension, Insulin, Machine learning, Treatment response",

author = "Wenfei Wu and Wenlin Zhang and Soban Sadiq and Gary Tse and Khalid, \{Syed Ghufran\} and Yimeng Fan and Haipeng Liu",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier Inc. All rights are reserved including those for text and data mining AI training and similar technologies.",

year = "2024",

month = jul,

day = "19",

doi = "10.1016/B978-0-323-95686-4.00027-7",

language = "English",

isbn = "978-0-323-95686-4",

pages = "397--409",

editor = "Sujata Dash and Pani, \{Subhendu Kumar\} and Willy Susilo and Cheung, \{Bernard Man Yung\} and Gary Tse",

booktitle = "Internet of Things and Machine Learning for Type I and Type II Diabetes",

publisher = "Elsevier",

address = "Netherlands",

edition = "1",

}

TY - CHAP

T1 - An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes

AU - Wu, Wenfei

AU - Zhang, Wenlin

AU - Sadiq, Soban

AU - Tse, Gary

AU - Khalid, Syed Ghufran

AU - Fan, Yimeng

AU - Liu, Haipeng

PY - 2024/7/19

Y1 - 2024/7/19

N2 - Diabetes mellitus (DM) is defined as a group of metabolic disorders characterized by a long-term high blood sugar level caused by abnormal insulin secretion and/or action. Different medications have been developed but the treatment efficacy is patient-specific. The evidence-based prediction of DM treatment response can provide specific reference for self-management, clinical intervention and medication. Recently, some machine learning models have been proposed for the diagnosis of DM. Whereas, the applications in predicting treatment response are limited. The data-driven approach empowered by machine learning enables patient-tailored therapy based on multimodal big health data analysis. In this chapter, we overviewed the state-of-the-art machine learning techniques regarding the data, algorithm, and performance. We summarized the advantages, limitations, and future directions. This chapter provides an up-to-date reference for clinicians, data scientists, and biomedical engineers to improve the treatment for D

AB - Diabetes mellitus (DM) is defined as a group of metabolic disorders characterized by a long-term high blood sugar level caused by abnormal insulin secretion and/or action. Different medications have been developed but the treatment efficacy is patient-specific. The evidence-based prediction of DM treatment response can provide specific reference for self-management, clinical intervention and medication. Recently, some machine learning models have been proposed for the diagnosis of DM. Whereas, the applications in predicting treatment response are limited. The data-driven approach empowered by machine learning enables patient-tailored therapy based on multimodal big health data analysis. In this chapter, we overviewed the state-of-the-art machine learning techniques regarding the data, algorithm, and performance. We summarized the advantages, limitations, and future directions. This chapter provides an up-to-date reference for clinicians, data scientists, and biomedical engineers to improve the treatment for D

KW - Diabetes mellitus

KW - Hb1Ac

KW - Hypertension

KW - Insulin

KW - Machine learning

KW - Treatment response

U2 - 10.1016/B978-0-323-95686-4.00027-7

DO - 10.1016/B978-0-323-95686-4.00027-7

M3 - Chapter

SN - 978-0-323-95686-4

SP - 397

EP - 409

BT - Internet of Things and Machine Learning for Type I and Type II Diabetes

A2 - Dash, Sujata

A2 - Pani, Subhendu Kumar

A2 - Susilo, Willy

A2 - Cheung, Bernard Man Yung

A2 - Tse, Gary

PB - Elsevier

ER -

An up-to-date systematic review on machine learning approaches for predicting treatment response in diabetes

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this