Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models

Abstract Over the past decade, neuropsychiatric fluctuations in Parkinson’s disease (PD) have been increasingly recognized for their impact on patients’ quality of life. Speech, a complex function carrying motor, emotional, and cognitive information, offers potential insights into these fluctuations...

Full description

Saved in:
Bibliographic Details
Main Authors: Matilde Castelli, Mario Sousa, Illner Vojtech, Michael Single, Deborah Amstutz, Marie Elise Maradan-Gachet, Andreia D. Magalhães, Ines Debove, Jan Rusz, Pablo Martinez-Martin, Raphael Sznitman, Paul Krack, Tobias Nef
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:npj Parkinson's Disease
Online Access:https://doi.org/10.1038/s41531-025-00939-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181787763867648
author Matilde Castelli
Mario Sousa
Illner Vojtech
Michael Single
Deborah Amstutz
Marie Elise Maradan-Gachet
Andreia D. Magalhães
Ines Debove
Jan Rusz
Pablo Martinez-Martin
Raphael Sznitman
Paul Krack
Tobias Nef
author_facet Matilde Castelli
Mario Sousa
Illner Vojtech
Michael Single
Deborah Amstutz
Marie Elise Maradan-Gachet
Andreia D. Magalhães
Ines Debove
Jan Rusz
Pablo Martinez-Martin
Raphael Sznitman
Paul Krack
Tobias Nef
author_sort Matilde Castelli
collection DOAJ
description Abstract Over the past decade, neuropsychiatric fluctuations in Parkinson’s disease (PD) have been increasingly recognized for their impact on patients’ quality of life. Speech, a complex function carrying motor, emotional, and cognitive information, offers potential insights into these fluctuations. While previous studies have focused on acoustic analysis to assess motor speech disorders reliably, the potential of linguistic patterns associated with neuropsychiatric fluctuations in PD remains unexplored. This study analyzed the content of spontaneous speech from 33 PD patients in ON and OFF medication states, using machine learning and large language models (LLMs) to predict medication states and a neuropsychiatric state score. The top-performing model, the LLM Gemma-2 (9B), achieved 98% accuracy in differentiating ON and OFF states and its predicted scores were highly correlated with actual scores (Spearman’s ρ = 0.81). These methods could provide a more comprehensive assessment of PD treatment effects, allowing remote neuropsychiatric symptom monitoring via mobile devices.
format Article
id doaj-art-373c7b6f9bd84809b89bc31f5b2aae28
institution OA Journals
issn 2373-8057
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series npj Parkinson's Disease
spelling doaj-art-373c7b6f9bd84809b89bc31f5b2aae282025-08-20T02:17:49ZengNature Portfolionpj Parkinson's Disease2373-80572025-04-0111111110.1038/s41531-025-00939-8Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language modelsMatilde Castelli0Mario Sousa1Illner Vojtech2Michael Single3Deborah Amstutz4Marie Elise Maradan-Gachet5Andreia D. Magalhães6Ines Debove7Jan Rusz8Pablo Martinez-Martin9Raphael Sznitman10Paul Krack11Tobias Nef12ARTORG Center for Biomedical Engineering Research, Gerontechnology and Rehabilitation Group, University of BernDepartment of Neurology, Bern University Hospital and University of BernDepartment of Circuit Theory, Faculty of Electrical Engineering, Czech Technical University in PragueARTORG Center for Biomedical Engineering Research, Gerontechnology and Rehabilitation Group, University of BernDepartment of Neurology, Bern University Hospital and University of BernDepartment of Neurology, Bern University Hospital and University of BernDepartment of Neurology, Bern University Hospital and University of BernDepartment of Neurology, Bern University Hospital and University of BernDepartment of Circuit Theory, Faculty of Electrical Engineering, Czech Technical University in PragueCenter for Networked Biomedical Research in Neurodegenerative Diseases (CIBERNED), Carlos III Institute of HealthARTORG Center for Biomedical Engineering Research, AIMI, University of BernDepartment of Neurology, Bern University Hospital and University of BernARTORG Center for Biomedical Engineering Research, Gerontechnology and Rehabilitation Group, University of BernAbstract Over the past decade, neuropsychiatric fluctuations in Parkinson’s disease (PD) have been increasingly recognized for their impact on patients’ quality of life. Speech, a complex function carrying motor, emotional, and cognitive information, offers potential insights into these fluctuations. While previous studies have focused on acoustic analysis to assess motor speech disorders reliably, the potential of linguistic patterns associated with neuropsychiatric fluctuations in PD remains unexplored. This study analyzed the content of spontaneous speech from 33 PD patients in ON and OFF medication states, using machine learning and large language models (LLMs) to predict medication states and a neuropsychiatric state score. The top-performing model, the LLM Gemma-2 (9B), achieved 98% accuracy in differentiating ON and OFF states and its predicted scores were highly correlated with actual scores (Spearman’s ρ = 0.81). These methods could provide a more comprehensive assessment of PD treatment effects, allowing remote neuropsychiatric symptom monitoring via mobile devices.https://doi.org/10.1038/s41531-025-00939-8
spellingShingle Matilde Castelli
Mario Sousa
Illner Vojtech
Michael Single
Deborah Amstutz
Marie Elise Maradan-Gachet
Andreia D. Magalhães
Ines Debove
Jan Rusz
Pablo Martinez-Martin
Raphael Sznitman
Paul Krack
Tobias Nef
Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
npj Parkinson's Disease
title Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
title_full Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
title_fullStr Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
title_full_unstemmed Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
title_short Detecting neuropsychiatric fluctuations in Parkinson’s Disease using patients’ own words: the potential of large language models
title_sort detecting neuropsychiatric fluctuations in parkinson s disease using patients own words the potential of large language models
url https://doi.org/10.1038/s41531-025-00939-8
work_keys_str_mv AT matildecastelli detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT mariosousa detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT illnervojtech detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT michaelsingle detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT deborahamstutz detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT marieelisemaradangachet detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT andreiadmagalhaes detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT inesdebove detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT janrusz detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT pablomartinezmartin detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT raphaelsznitman detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT paulkrack detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels
AT tobiasnef detectingneuropsychiatricfluctuationsinparkinsonsdiseaseusingpatientsownwordsthepotentialoflargelanguagemodels