Limitations and challenges of AI-ECG

Qing-Peng Zhang; Cheuk To Skylar Chung; Yi-En Li; Tong Liu; Zhi-Heng Lv; Jia-Wei Xie

doi:10.1007/978-981-97-8359-5_4

Limitations and challenges of AI-ECG

Qing-Peng Zhang^*, Cheuk To Skylar Chung, Yi-En Li, Tong Liu, Zhi-Heng Lv, Jia-Wei Xie

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

Abstract

Cardiovascular and metabolic diseases stand as significant contributors to global mortality. The current approach to assessing electrocardiograms (ECGs) involves a combination of human analysis and automated machine readings. However, these methods are restricted in their ability to extract complex information from ECGs, underscoring the potential for AI advancements to enhance ECG analysis. Novel algorithms rooted in machine learning and deep learning offer promise in complementing traditional ECG evaluation methods. While recent studies exhibit the feasibility of AI-ECG algorithms for detection, it is vital to acknowledge the distinct challenges and limitations they entail. This chapter aims to cultivate reader understanding and awareness of AI systems, with a focus on addressing present challenges. © Tianjin Science & Technology Translation & Publishing Co., Ltd. 2024. All rights reserved.

Original language	English
Title of host publication	AI Augmented ECG Technology
Editors	Kang-Yin Chen, Tong Liu, Hua-Yue Tao
Publisher	Springer Singapore
Chapter	4
Pages	123-131
ISBN (Electronic)	9789819783595
ISBN (Print)	9789819783618, 9789819783588
DOIs	https://doi.org/10.1007/978-981-97-8359-5_4
Publication status	Published - 2024
Externally published	Yes

Access Output

10.1007/978-981-97-8359-5_4

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inbook{28e3a1325b46444687f525dcf9caf98d,

title = "Limitations and challenges of AI-ECG",

abstract = "Cardiovascular and metabolic diseases stand as significant contributors to global mortality. The current approach to assessing electrocardiograms (ECGs) involves a combination of human analysis and automated machine readings. However, these methods are restricted in their ability to extract complex information from ECGs, underscoring the potential for AI advancements to enhance ECG analysis. Novel algorithms rooted in machine learning and deep learning offer promise in complementing traditional ECG evaluation methods. While recent studies exhibit the feasibility of AI-ECG algorithms for detection, it is vital to acknowledge the distinct challenges and limitations they entail. This chapter aims to cultivate reader understanding and awareness of AI systems, with a focus on addressing present challenges. {\textcopyright} Tianjin Science & Technology Translation & Publishing Co., Ltd. 2024. All rights reserved.",

author = "Qing-Peng Zhang and Chung, {Cheuk To Skylar} and Yi-En Li and Tong Liu and Zhi-Heng Lv and Jia-Wei Xie",

year = "2024",

doi = "10.1007/978-981-97-8359-5_4",

language = "English",

isbn = "9789819783618",

pages = "123--131",

editor = "Kang-Yin Chen and Tong Liu and Hua-Yue Tao",

booktitle = "AI Augmented ECG Technology",

publisher = "Springer Singapore",

address = "Singapore",

}

TY - CHAP

T1 - Limitations and challenges of AI-ECG

AU - Zhang, Qing-Peng

AU - Chung, Cheuk To Skylar

AU - Li, Yi-En

AU - Liu, Tong

AU - Lv, Zhi-Heng

AU - Xie, Jia-Wei

PY - 2024

Y1 - 2024

N2 - Cardiovascular and metabolic diseases stand as significant contributors to global mortality. The current approach to assessing electrocardiograms (ECGs) involves a combination of human analysis and automated machine readings. However, these methods are restricted in their ability to extract complex information from ECGs, underscoring the potential for AI advancements to enhance ECG analysis. Novel algorithms rooted in machine learning and deep learning offer promise in complementing traditional ECG evaluation methods. While recent studies exhibit the feasibility of AI-ECG algorithms for detection, it is vital to acknowledge the distinct challenges and limitations they entail. This chapter aims to cultivate reader understanding and awareness of AI systems, with a focus on addressing present challenges. © Tianjin Science & Technology Translation & Publishing Co., Ltd. 2024. All rights reserved.

AB - Cardiovascular and metabolic diseases stand as significant contributors to global mortality. The current approach to assessing electrocardiograms (ECGs) involves a combination of human analysis and automated machine readings. However, these methods are restricted in their ability to extract complex information from ECGs, underscoring the potential for AI advancements to enhance ECG analysis. Novel algorithms rooted in machine learning and deep learning offer promise in complementing traditional ECG evaluation methods. While recent studies exhibit the feasibility of AI-ECG algorithms for detection, it is vital to acknowledge the distinct challenges and limitations they entail. This chapter aims to cultivate reader understanding and awareness of AI systems, with a focus on addressing present challenges. © Tianjin Science & Technology Translation & Publishing Co., Ltd. 2024. All rights reserved.

UR - http://www.scopus.com/inward/record.url?scp=105002624887&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105002624887&origin=recordpage

U2 - 10.1007/978-981-97-8359-5_4

DO - 10.1007/978-981-97-8359-5_4

M3 - RGC 12 - Chapter in an edited book (Author)

SN - 9789819783618

SN - 9789819783588

SP - 123

EP - 131

BT - AI Augmented ECG Technology

A2 - Chen, Kang-Yin

A2 - Liu, Tong

A2 - Tao, Hua-Yue

PB - Springer Singapore

ER -

Limitations and challenges of AI-ECG

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this