Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope

The present study explores the potential of artificial intelligence as a substitute for trained clinician identification of a carotid bruit from multiple auditory recordings from an electronic stethoscope in 98 people with type 2 diabetes, 48 of whom had a bruit. We employed various deep networks, i...

Full description

Saved in:
Bibliographic Details
Main Authors: Aref Miri Rekavandi, Mohammed Bennamoun, Farid Boussaid, Wendy A. Davis, Timothy M. E. Davis
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11050375/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427497177841664
author Aref Miri Rekavandi
Mohammed Bennamoun
Farid Boussaid
Wendy A. Davis
Timothy M. E. Davis
author_facet Aref Miri Rekavandi
Mohammed Bennamoun
Farid Boussaid
Wendy A. Davis
Timothy M. E. Davis
author_sort Aref Miri Rekavandi
collection DOAJ
description The present study explores the potential of artificial intelligence as a substitute for trained clinician identification of a carotid bruit from multiple auditory recordings from an electronic stethoscope in 98 people with type 2 diabetes, 48 of whom had a bruit. We employed various deep networks, including ResNet and VGGish, alongside tailor-made deep learning models for this purpose. Our findings indicated that in scenarios such as this, where the data show high variability and yet are limited, the highest model accuracy achieved was 67.8%. This suggests the inadequacy of AI-driven systems in accurately detecting carotid bruits in the present participant sample. Detailed results for each deep learning and machine learning approach are presented separately, and the dataset has been established as a benchmark for future studies. Given the complexity observed with the current data volume, additional studies with larger sample sizes are warranted.
format Article
id doaj-art-54d9a1bbdc2f4e47b8d91de8201a7a27
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-54d9a1bbdc2f4e47b8d91de8201a7a272025-08-20T03:29:02ZengIEEEIEEE Access2169-35362025-01-011311802311803210.1109/ACCESS.2025.358293811050375Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic StethoscopeAref Miri Rekavandi0https://orcid.org/0000-0001-9542-759XMohammed Bennamoun1https://orcid.org/0000-0002-6603-3257Farid Boussaid2https://orcid.org/0000-0001-7250-7407Wendy A. Davis3https://orcid.org/0000-0002-5709-8235Timothy M. E. Davis4https://orcid.org/0000-0003-0749-7411Department of Computer Science and Software Engineering, The University of Western Australia, Perth, AustraliaDepartment of Computer Science and Software Engineering, The University of Western Australia, Perth, AustraliaDepartment of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, AustraliaMedical School, Fremantle Hospital, The University of Western Australia, Fremantle, AustraliaMedical School, Fremantle Hospital, The University of Western Australia, Fremantle, AustraliaThe present study explores the potential of artificial intelligence as a substitute for trained clinician identification of a carotid bruit from multiple auditory recordings from an electronic stethoscope in 98 people with type 2 diabetes, 48 of whom had a bruit. We employed various deep networks, including ResNet and VGGish, alongside tailor-made deep learning models for this purpose. Our findings indicated that in scenarios such as this, where the data show high variability and yet are limited, the highest model accuracy achieved was 67.8%. This suggests the inadequacy of AI-driven systems in accurately detecting carotid bruits in the present participant sample. Detailed results for each deep learning and machine learning approach are presented separately, and the dataset has been established as a benchmark for future studies. Given the complexity observed with the current data volume, additional studies with larger sample sizes are warranted.https://ieeexplore.ieee.org/document/11050375/Clinical decision makingcarotid bruitelectronic stethoscopetype 2 diabetes
spellingShingle Aref Miri Rekavandi
Mohammed Bennamoun
Farid Boussaid
Wendy A. Davis
Timothy M. E. Davis
Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
IEEE Access
Clinical decision making
carotid bruit
electronic stethoscope
type 2 diabetes
title Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
title_full Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
title_fullStr Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
title_full_unstemmed Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
title_short Can Deep Learning Models Acquire Specialist Knowledge? Identifying Carotid Bruits in Type 2 Diabetes Using an Electronic Stethoscope
title_sort can deep learning models acquire specialist knowledge identifying carotid bruits in type 2 diabetes using an electronic stethoscope
topic Clinical decision making
carotid bruit
electronic stethoscope
type 2 diabetes
url https://ieeexplore.ieee.org/document/11050375/
work_keys_str_mv AT arefmirirekavandi candeeplearningmodelsacquirespecialistknowledgeidentifyingcarotidbruitsintype2diabetesusinganelectronicstethoscope
AT mohammedbennamoun candeeplearningmodelsacquirespecialistknowledgeidentifyingcarotidbruitsintype2diabetesusinganelectronicstethoscope
AT faridboussaid candeeplearningmodelsacquirespecialistknowledgeidentifyingcarotidbruitsintype2diabetesusinganelectronicstethoscope
AT wendyadavis candeeplearningmodelsacquirespecialistknowledgeidentifyingcarotidbruitsintype2diabetesusinganelectronicstethoscope
AT timothymedavis candeeplearningmodelsacquirespecialistknowledgeidentifyingcarotidbruitsintype2diabetesusinganelectronicstethoscope