AI-Driven CHD Detection Using an Ultra-Low Power Embedded System

Emma Carroll; Giuseppe Caracciolo; Sergi Gomez Quintana; Viktoriya Shelevytska; Andriy Temko; Emanuel Popovici

doi:10.1109/ISSC61953.2024.10603118

AI-Driven CHD Detection Using an Ultra-Low Power Embedded System

Emma Carroll
, Giuseppe Caracciolo
, Sergi Gomez Quintana
, Viktoriya Shelevytska
, Andriy Temko
, Emanuel Popovici

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

Abstract

Congenital heart disease (CHD) is a significant global health concern, particularly in disadvantaged communities that lack access to advanced diagnostic equipment and medical ability. Capitalizing on advances in digital stethoscope technology, this paper presents an innovative AI-driven CHD detection system implemented on an ultra-low-power embedded platform. Utilizing phonocardiogram data acquired using a digital stethoscope, our solution offers accurate CHD screening, while consuming less than 5mW, enabling 24-hour operation on a small 55mAh battery. This approach enhances portability, reduces pre-screening costs, and ensures the required accuracy for early diagnosis. The model used for inference implementation is based on an Extreme Gradient Boosting (XGBoost) algorithm. The system's design and optimization for low-power environments are discussed, along with its potential of integration with low power digital stethoscope platforms.

Original language	English
Title of host publication	Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024
Editors	Huiru Zheng, Ian Cleland, Adrian Moore, Haiying Wang, David Glass, Joe Rafferty, Raymond Bond, Jonathan Wallace
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350352986
DOIs	https://doi.org/10.1109/ISSC61953.2024.10603118
Publication status	Published - 2024
Event	35th Irish Systems and Signals Conference, ISSC 2024 - Belfast, United Kingdom Duration: 13 Jun 2024 → 14 Jun 2024

Publication series

Name	Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

Conference

Conference	35th Irish Systems and Signals Conference, ISSC 2024
Country/Territory	United Kingdom
City	Belfast
Period	13/06/24 → 14/06/24

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

AI
Congenital heart disease
embedded systems
low-power inference
neonates
optimization
phonocardiogram
XGBoost

Access to Document

10.1109/ISSC61953.2024.10603118

Cite this

Carroll, E., Caracciolo, G., Quintana, S. G., Shelevytska, V., Temko, A., & Popovici, E. (2024). AI-Driven CHD Detection Using an Ultra-Low Power Embedded System. In H. Zheng, I. Cleland, A. Moore, H. Wang, D. Glass, J. Rafferty, R. Bond, & J. Wallace (Eds.), Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024 (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISSC61953.2024.10603118

Carroll, Emma ; Caracciolo, Giuseppe ; Quintana, Sergi Gomez et al. / AI-Driven CHD Detection Using an Ultra-Low Power Embedded System. Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. editor / Huiru Zheng ; Ian Cleland ; Adrian Moore ; Haiying Wang ; David Glass ; Joe Rafferty ; Raymond Bond ; Jonathan Wallace. Institute of Electrical and Electronics Engineers Inc., 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024).

@inproceedings{bb44a6b7aadd4aa1aaf2906f08e3ac2a,

title = "AI-Driven CHD Detection Using an Ultra-Low Power Embedded System",

abstract = "Congenital heart disease (CHD) is a significant global health concern, particularly in disadvantaged communities that lack access to advanced diagnostic equipment and medical ability. Capitalizing on advances in digital stethoscope technology, this paper presents an innovative AI-driven CHD detection system implemented on an ultra-low-power embedded platform. Utilizing phonocardiogram data acquired using a digital stethoscope, our solution offers accurate CHD screening, while consuming less than 5mW, enabling 24-hour operation on a small 55mAh battery. This approach enhances portability, reduces pre-screening costs, and ensures the required accuracy for early diagnosis. The model used for inference implementation is based on an Extreme Gradient Boosting (XGBoost) algorithm. The system's design and optimization for low-power environments are discussed, along with its potential of integration with low power digital stethoscope platforms.",

keywords = "AI, Congenital heart disease, embedded systems, low-power inference, neonates, optimization, phonocardiogram, XGBoost",

author = "Emma Carroll and Giuseppe Caracciolo and Quintana, \{Sergi Gomez\} and Viktoriya Shelevytska and Andriy Temko and Emanuel Popovici",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 35th Irish Systems and Signals Conference, ISSC 2024 ; Conference date: 13-06-2024 Through 14-06-2024",

year = "2024",

doi = "10.1109/ISSC61953.2024.10603118",

language = "English",

series = "Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Huiru Zheng and Ian Cleland and Adrian Moore and Haiying Wang and David Glass and Joe Rafferty and Raymond Bond and Jonathan Wallace",

booktitle = "Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024",

address = "United States",

}

Carroll, E, Caracciolo, G, Quintana, SG, Shelevytska, V, Temko, A & Popovici, E 2024, AI-Driven CHD Detection Using an Ultra-Low Power Embedded System. in H Zheng, I Cleland, A Moore, H Wang, D Glass, J Rafferty, R Bond & J Wallace (eds), Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024, Institute of Electrical and Electronics Engineers Inc., 35th Irish Systems and Signals Conference, ISSC 2024, Belfast, United Kingdom, 13/06/24. https://doi.org/10.1109/ISSC61953.2024.10603118

AI-Driven CHD Detection Using an Ultra-Low Power Embedded System. / Carroll, Emma; Caracciolo, Giuseppe; Quintana, Sergi Gomez et al.
Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. ed. / Huiru Zheng; Ian Cleland; Adrian Moore; Haiying Wang; David Glass; Joe Rafferty; Raymond Bond; Jonathan Wallace. Institute of Electrical and Electronics Engineers Inc., 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024).

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

TY - GEN

T1 - AI-Driven CHD Detection Using an Ultra-Low Power Embedded System

AU - Carroll, Emma

AU - Caracciolo, Giuseppe

AU - Quintana, Sergi Gomez

AU - Shelevytska, Viktoriya

AU - Temko, Andriy

AU - Popovici, Emanuel

PY - 2024

Y1 - 2024

N2 - Congenital heart disease (CHD) is a significant global health concern, particularly in disadvantaged communities that lack access to advanced diagnostic equipment and medical ability. Capitalizing on advances in digital stethoscope technology, this paper presents an innovative AI-driven CHD detection system implemented on an ultra-low-power embedded platform. Utilizing phonocardiogram data acquired using a digital stethoscope, our solution offers accurate CHD screening, while consuming less than 5mW, enabling 24-hour operation on a small 55mAh battery. This approach enhances portability, reduces pre-screening costs, and ensures the required accuracy for early diagnosis. The model used for inference implementation is based on an Extreme Gradient Boosting (XGBoost) algorithm. The system's design and optimization for low-power environments are discussed, along with its potential of integration with low power digital stethoscope platforms.

AB - Congenital heart disease (CHD) is a significant global health concern, particularly in disadvantaged communities that lack access to advanced diagnostic equipment and medical ability. Capitalizing on advances in digital stethoscope technology, this paper presents an innovative AI-driven CHD detection system implemented on an ultra-low-power embedded platform. Utilizing phonocardiogram data acquired using a digital stethoscope, our solution offers accurate CHD screening, while consuming less than 5mW, enabling 24-hour operation on a small 55mAh battery. This approach enhances portability, reduces pre-screening costs, and ensures the required accuracy for early diagnosis. The model used for inference implementation is based on an Extreme Gradient Boosting (XGBoost) algorithm. The system's design and optimization for low-power environments are discussed, along with its potential of integration with low power digital stethoscope platforms.

KW - AI

KW - Congenital heart disease

KW - embedded systems

KW - low-power inference

KW - neonates

KW - optimization

KW - phonocardiogram

KW - XGBoost

UR - https://www.scopus.com/pages/publications/85201153062

U2 - 10.1109/ISSC61953.2024.10603118

DO - 10.1109/ISSC61953.2024.10603118

M3 - Conference proceeding

AN - SCOPUS:85201153062

T3 - Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

BT - Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

A2 - Zheng, Huiru

A2 - Cleland, Ian

A2 - Moore, Adrian

A2 - Wang, Haiying

A2 - Glass, David

A2 - Rafferty, Joe

A2 - Bond, Raymond

A2 - Wallace, Jonathan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 35th Irish Systems and Signals Conference, ISSC 2024

Y2 - 13 June 2024 through 14 June 2024

ER -

Carroll E, Caracciolo G, Quintana SG, Shelevytska V, Temko A, Popovici E. AI-Driven CHD Detection Using an Ultra-Low Power Embedded System. In Zheng H, Cleland I, Moore A, Wang H, Glass D, Rafferty J, Bond R, Wallace J, editors, Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. Institute of Electrical and Electronics Engineers Inc. 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024). doi: 10.1109/ISSC61953.2024.10603118

AI-Driven CHD Detection Using an Ultra-Low Power Embedded System

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this