Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting

This study explores an innovative approach to early Parkinson’s disease (PD) detection by analyzing speech data collected using a mixed reality (MR) system. A total of 57 Polish participants, including PD patients and healthy controls, performed five speech tasks while using an MR head-mounted displ...

Full description

Saved in:
Bibliographic Details
Main Authors: Milosz Dudek, Daria Hemmerling, Marta Kaczmarska, Joanna Stepien, Mateusz Daniol, Marek Wodzinski, Magdalena Wojcik-Pedziwiatr
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2405
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179986119458816
author Milosz Dudek
Daria Hemmerling
Marta Kaczmarska
Joanna Stepien
Mateusz Daniol
Marek Wodzinski
Magdalena Wojcik-Pedziwiatr
author_facet Milosz Dudek
Daria Hemmerling
Marta Kaczmarska
Joanna Stepien
Mateusz Daniol
Marek Wodzinski
Magdalena Wojcik-Pedziwiatr
author_sort Milosz Dudek
collection DOAJ
description This study explores an innovative approach to early Parkinson’s disease (PD) detection by analyzing speech data collected using a mixed reality (MR) system. A total of 57 Polish participants, including PD patients and healthy controls, performed five speech tasks while using an MR head-mounted display (HMD). Speech data were recorded and analyzed to extract acoustic and linguistic features, which were then evaluated using machine learning models, including logistic regression, support vector machines (SVMs), random forests, AdaBoost, and XGBoost. The XGBoost model achieved the best performance, with an F1-score of 0.90 ± 0.05 in the story-retelling task. Key features such as MFCCs (mel-frequency cepstral coefficients), spectral characteristics, RASTA-filtered auditory spectrum, and local shimmer were identified as significant in detecting PD-related speech alterations. Additionally, state-of-the-art deep learning models (wav2vec2, HuBERT, and WavLM) were fine-tuned for PD detection. HuBERT achieved the highest performance, with an F1-score of 0.94 ± 0.04 in the diadochokinetic task, demonstrating the potential of deep learning to capture complex speech patterns linked to neurodegenerative diseases. This study highlights the effectiveness of combining MR technology for speech data collection with advanced machine learning (ML) and deep learning (DL) techniques, offering a non-invasive and high-precision approach to PD diagnosis. The findings hold promise for broader clinical applications, advancing the diagnostic landscape for neurodegenerative disorders.
format Article
id doaj-art-beef3caf53f3486fa5c6dd14d7f116d9
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-beef3caf53f3486fa5c6dd14d7f116d92025-08-20T02:18:20ZengMDPI AGSensors1424-82202025-04-01258240510.3390/s25082405Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality SettingMilosz Dudek0Daria Hemmerling1Marta Kaczmarska2Joanna Stepien3Mateusz Daniol4Marek Wodzinski5Magdalena Wojcik-Pedziwiatr6Department of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Measurement and Electronics, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Neurology, Andrzej Frycz Modrzewski Krakow University, 30-705 Krakow, PolandThis study explores an innovative approach to early Parkinson’s disease (PD) detection by analyzing speech data collected using a mixed reality (MR) system. A total of 57 Polish participants, including PD patients and healthy controls, performed five speech tasks while using an MR head-mounted display (HMD). Speech data were recorded and analyzed to extract acoustic and linguistic features, which were then evaluated using machine learning models, including logistic regression, support vector machines (SVMs), random forests, AdaBoost, and XGBoost. The XGBoost model achieved the best performance, with an F1-score of 0.90 ± 0.05 in the story-retelling task. Key features such as MFCCs (mel-frequency cepstral coefficients), spectral characteristics, RASTA-filtered auditory spectrum, and local shimmer were identified as significant in detecting PD-related speech alterations. Additionally, state-of-the-art deep learning models (wav2vec2, HuBERT, and WavLM) were fine-tuned for PD detection. HuBERT achieved the highest performance, with an F1-score of 0.94 ± 0.04 in the diadochokinetic task, demonstrating the potential of deep learning to capture complex speech patterns linked to neurodegenerative diseases. This study highlights the effectiveness of combining MR technology for speech data collection with advanced machine learning (ML) and deep learning (DL) techniques, offering a non-invasive and high-precision approach to PD diagnosis. The findings hold promise for broader clinical applications, advancing the diagnostic landscape for neurodegenerative disorders.https://www.mdpi.com/1424-8220/25/8/2405explainable artificial intelligencelarge language modelsmixed realityParkinson’s diseasevoice biomarkersremote patient monitoring
spellingShingle Milosz Dudek
Daria Hemmerling
Marta Kaczmarska
Joanna Stepien
Mateusz Daniol
Marek Wodzinski
Magdalena Wojcik-Pedziwiatr
Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
Sensors
explainable artificial intelligence
large language models
mixed reality
Parkinson’s disease
voice biomarkers
remote patient monitoring
title Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
title_full Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
title_fullStr Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
title_full_unstemmed Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
title_short Analysis of Voice, Speech, and Language Biomarkers of Parkinson’s Disease Collected in a Mixed Reality Setting
title_sort analysis of voice speech and language biomarkers of parkinson s disease collected in a mixed reality setting
topic explainable artificial intelligence
large language models
mixed reality
Parkinson’s disease
voice biomarkers
remote patient monitoring
url https://www.mdpi.com/1424-8220/25/8/2405
work_keys_str_mv AT miloszdudek analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT dariahemmerling analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT martakaczmarska analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT joannastepien analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT mateuszdaniol analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT marekwodzinski analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting
AT magdalenawojcikpedziwiatr analysisofvoicespeechandlanguagebiomarkersofparkinsonsdiseasecollectedinamixedrealitysetting