A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance

Tariq Rahim; Fei Zhao

doi:10.1109/CCNC54725.2025.10976051

A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance

Tariq Rahim
, Fei Zhao

Cardiff Metropolitan University

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

2 Downloads (Pure)

Abstract

Wideband acoustic immittance (WAI) technology has been known for over a decade, delivering an enhanced diagnosis of middle ear (ME) diseases across a wider frequency range than standard tympanometry. Nevertheless, its clinical usage confronts the limitations of restricted interpretation and insufficient explanation of the WAI outcomes. This paper proposes a multimodal machine learning (MML) approach for classifying ME diseases into normal ear and ear with abnormalalty i.e., otitis media with effusion. The proposed MML model is grounded on the integration of a 3 layered convolutional neural network and a multi-layer perception network. The outcomes exhibited that the proposed MML model surpasses the available methods by achieving 98.27% accuracy for classifying ME diseases using the WAI measurements.

Original language	English
Title of host publication	2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025
Place of Publication	Piscataway, U.S.
Publisher	IEEE Publishing
ISBN (Electronic)	9798331508050
DOIs	https://doi.org/10.1109/CCNC54725.2025.10976051
Publication status	Published - 10 Jan 2025

Publication series

Name	Proceedings - IEEE Consumer Communications and Networking Conference, CCNC
ISSN (Print)	2331-9860

Bibliographical note

Organising Body: Institute of Electrical and Electronics Engineers

Keywords

Computer science and informatics
Accuracy
Wideband acoustic immittance
convolutional neural network
machine learning
multi-layer perception

Access to Document

10.1109/CCNC54725.2025.10976051Licence: Other

Rahim-T-56889-AAMAccepted author manuscript, 1.95 MBLicence: Unspecified

A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance
Rahim, T. & Zhao, F., 10 Jan 2025.
Research output: Contribution to conference › Paper › peer-review

Open Access
File
10 Downloads (Pure)

Cite this

Rahim, T., & Zhao, F. (2025). A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance. In 2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025 (Proceedings - IEEE Consumer Communications and Networking Conference, CCNC). IEEE Publishing. https://doi.org/10.1109/CCNC54725.2025.10976051

@inproceedings{b94e6f76279e47779006a14857a83c32,

title = "A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance",

abstract = "Wideband acoustic immittance (WAI) technology has been known for over a decade, delivering an enhanced diagnosis of middle ear (ME) diseases across a wider frequency range than standard tympanometry. Nevertheless, its clinical usage confronts the limitations of restricted interpretation and insufficient explanation of the WAI outcomes. This paper proposes a multimodal machine learning (MML) approach for classifying ME diseases into normal ear and ear with abnormalalty i.e., otitis media with effusion. The proposed MML model is grounded on the integration of a 3 layered convolutional neural network and a multi-layer perception network. The outcomes exhibited that the proposed MML model surpasses the available methods by achieving 98.27\% accuracy for classifying ME diseases using the WAI measurements.",

keywords = "Computer science and informatics, Accuracy, Wideband acoustic immittance, convolutional neural network, machine learning, multi-layer perception",

author = "Tariq Rahim and Fei Zhao",

note = "Organising Body: Institute of Electrical and Electronics Engineers",

year = "2025",

month = jan,

day = "10",

doi = "10.1109/CCNC54725.2025.10976051",

language = "English",

series = "Proceedings - IEEE Consumer Communications and Networking Conference, CCNC",

publisher = "IEEE Publishing",

booktitle = "2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025",

}

Rahim, T & Zhao, F 2025, A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance. in 2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025. Proceedings - IEEE Consumer Communications and Networking Conference, CCNC, IEEE Publishing, Piscataway, U.S. https://doi.org/10.1109/CCNC54725.2025.10976051

A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance. / Rahim, Tariq; Zhao, Fei.
2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025. Piscataway, U.S.: IEEE Publishing, 2025. (Proceedings - IEEE Consumer Communications and Networking Conference, CCNC).

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

TY - GEN

T1 - A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance

AU - Rahim, Tariq

AU - Zhao, Fei

N1 - Organising Body: Institute of Electrical and Electronics Engineers

PY - 2025/1/10

Y1 - 2025/1/10

N2 - Wideband acoustic immittance (WAI) technology has been known for over a decade, delivering an enhanced diagnosis of middle ear (ME) diseases across a wider frequency range than standard tympanometry. Nevertheless, its clinical usage confronts the limitations of restricted interpretation and insufficient explanation of the WAI outcomes. This paper proposes a multimodal machine learning (MML) approach for classifying ME diseases into normal ear and ear with abnormalalty i.e., otitis media with effusion. The proposed MML model is grounded on the integration of a 3 layered convolutional neural network and a multi-layer perception network. The outcomes exhibited that the proposed MML model surpasses the available methods by achieving 98.27% accuracy for classifying ME diseases using the WAI measurements.

AB - Wideband acoustic immittance (WAI) technology has been known for over a decade, delivering an enhanced diagnosis of middle ear (ME) diseases across a wider frequency range than standard tympanometry. Nevertheless, its clinical usage confronts the limitations of restricted interpretation and insufficient explanation of the WAI outcomes. This paper proposes a multimodal machine learning (MML) approach for classifying ME diseases into normal ear and ear with abnormalalty i.e., otitis media with effusion. The proposed MML model is grounded on the integration of a 3 layered convolutional neural network and a multi-layer perception network. The outcomes exhibited that the proposed MML model surpasses the available methods by achieving 98.27% accuracy for classifying ME diseases using the WAI measurements.

KW - Computer science and informatics

KW - Accuracy

KW - Wideband acoustic immittance

KW - convolutional neural network

KW - machine learning

KW - multi-layer perception

U2 - 10.1109/CCNC54725.2025.10976051

DO - 10.1109/CCNC54725.2025.10976051

M3 - Conference contribution

T3 - Proceedings - IEEE Consumer Communications and Networking Conference, CCNC

BT - 2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025

PB - IEEE Publishing

CY - Piscataway, U.S.

ER -

Rahim T, Zhao F. A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance. In 2025 IEEE 22nd Consumer Communications and Networking Conference, CCNC 2025. Piscataway, U.S.: IEEE Publishing. 2025. (Proceedings - IEEE Consumer Communications and Networking Conference, CCNC). doi: 10.1109/CCNC54725.2025.10976051

A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance

Abstract

Publication series

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

A multimodal machine learning framework for diagnosis of otitis media with effusion using 3D wideband acoustic immittance

Cite this