Speech as a Biomarker for Disease Detection

Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are...

Full description

Saved in:
Bibliographic Details
Main Authors: Catarina Botelho, Alberto Abad, Tanja Schultz, Isabel Trancoso
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767227/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850246468920672256
author Catarina Botelho
Alberto Abad
Tanja Schultz
Isabel Trancoso
author_facet Catarina Botelho
Alberto Abad
Tanja Schultz
Isabel Trancoso
author_sort Catarina Botelho
collection DOAJ
description Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients’ lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines “reference speech” and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer’s and Parkinson’s disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.
format Article
id doaj-art-e65e34229c864ad4a9ffd1fde5d7afc7
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e65e34229c864ad4a9ffd1fde5d7afc72025-08-20T01:59:12ZengIEEEIEEE Access2169-35362024-01-011218448718450810.1109/ACCESS.2024.350643310767227Speech as a Biomarker for Disease DetectionCatarina Botelho0https://orcid.org/0000-0003-4794-1003Alberto Abad1https://orcid.org/0000-0003-2122-5148Tanja Schultz2https://orcid.org/0000-0002-9809-7028Isabel Trancoso3https://orcid.org/0000-0001-5874-6313INESC-ID, Lisbon, PortugalINESC-ID, Lisbon, PortugalCognitive Systems Laboratory (CSL), University of Bremen, Bremen, GermanyINESC-ID, Lisbon, PortugalSpeech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients’ lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines “reference speech” and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer’s and Parkinson’s disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.https://ieeexplore.ieee.org/document/10767227/Alzheimer’s diseaseautomatic disease detectioninterpretabilityneural additive modelsParkinson’s diseasereference intervals
spellingShingle Catarina Botelho
Alberto Abad
Tanja Schultz
Isabel Trancoso
Speech as a Biomarker for Disease Detection
IEEE Access
Alzheimer’s disease
automatic disease detection
interpretability
neural additive models
Parkinson’s disease
reference intervals
title Speech as a Biomarker for Disease Detection
title_full Speech as a Biomarker for Disease Detection
title_fullStr Speech as a Biomarker for Disease Detection
title_full_unstemmed Speech as a Biomarker for Disease Detection
title_short Speech as a Biomarker for Disease Detection
title_sort speech as a biomarker for disease detection
topic Alzheimer’s disease
automatic disease detection
interpretability
neural additive models
Parkinson’s disease
reference intervals
url https://ieeexplore.ieee.org/document/10767227/
work_keys_str_mv AT catarinabotelho speechasabiomarkerfordiseasedetection
AT albertoabad speechasabiomarkerfordiseasedetection
AT tanjaschultz speechasabiomarkerfordiseasedetection
AT isabeltrancoso speechasabiomarkerfordiseasedetection