Digital speech biomarkers for assessing cognitive decline
across neurodegenerative conditions

J 2025

Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions

KOVÁČ, Daniel; Ľubomíra NOVÁKOVÁ; Jiří MEKYSKA; Kryštof NOVOTNÝ; Luboš BRABENEC et al.

Základní údaje

Originální název

Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions

Autoři

KOVÁČ, Daniel ; Ľubomíra NOVÁKOVÁ; Jiří MEKYSKA ; Kryštof NOVOTNÝ; Luboš BRABENEC; Patrícia KLOBUŠIAKOVÁ a Irena REKTOROVÁ

Vydání

COMPUTERS IN BIOLOGY AND MEDICINE, ENGLAND, Elsevier Ltd, 2025, 0010-4825

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30210 Clinical neurology

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 6.300 v roce 2024

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14740/25:00142542

Organizační jednotka

Středoevropský technologický institut

DOI

https://doi.org/10.1016/j.compbiomed.2025.111251

EID Scopus

2-s2.0-105020955849

Klíčová slova anglicky

Mild cognitive impairmentParkinson’s diseaseSpontaneous speechLinguistic biomarkersAcoustic biomarkersStatistical analysisMachine learning

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 26. 3. 2026 12:41, Mgr. Eva Dubská

Anotace

V originále

This study investigates speech impairments in individuals with mild cognitive impairment due to Alzheimer’s disease (MCI-AD), mild cognitive impairment with Lewy bodies (MCI-LB), and Parkinson’s disease with mild cognitive impairment (PD-MCI), compared to healthy controls (HC), aiming to identify linguistic and acoustic digital biomarkers that differentiate these groups. Monologue recordings were collected from 68 HC, 42 MCI-AD, 50 MCI-LB, and 47 PD-MCI participants (ON state). Participants were instructed to speak spontaneously for one and a half minutes. Speech was automatically transcribed, manually corrected, and analyzed using natural language processing to extract eight linguistic (lexical/syntactic) and four acoustic (prosodic) biomarkers. Group differences were assessed using the Mann–Whitney U test, with Spearman’s correlation used to examine associations with clinical and MRI measures (FDR-corrected). Machine learning models (XGBoost) were applied to evaluate the classificatory and predictive potential of speech features. Distinct speech patterns were observed across groups: MCI-AD participants exhibited reduced use of function words, resulting in increased content density, PD-MCI participants used shorter sentences and fewer coordinating conjunctions with longer pauses, and MCI-LB participants exhibited greater lexical repetition than MCI-AD. Altered speech features correlated with structural brain changes but not with global cognition (MoCA) or depressive symptoms (GDS). Sentence structure and pausing features showed strong interrelationships. Machine learning models showed that adding speech biomarkers improved classification performance compared to using clinical scores alone. In regression analyses, the models predicted MoCA with a normalized error of 10%, performing similarly on automatic and manually corrected transcripts. These findings suggest that speech biomarkers and traditional clinical assessments may offer complementary information about cognitive status and brain health, supporting their use in scalable, non-invasive cognitive monitoring.

Návaznosti

EH23_025/0008726, projekt VaV

Název: Celý život s jazykem: povaha a ontogeneze jazykové komunikace (LangInLife)

LM2023049, projekt VaV

Název: Český národní uzel Evropské sítě infrastruktur klinického výzkumu

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, CZECRIN - Czech National Node to the European Clinical Research Infrastructure Network

LX22NPO5107, projekt VaV

Název: Národní ústav pro neurologický výzkum

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Národní ústav pro neurologický výzkum, 5.1 EXCELES

NU23J-04-00005, projekt VaV

Název: Jazyk a onemocnění s Lewyho tělísky: Problémy s porozuměním větám a modifikující terapie pomocí neinvazivní stimulace mozku

Investor: Ministerstvo zdravotnictví ČR, Jazyk a onemocnění s Lewyho tělísky: Problémy s porozuměním větám a modifikující terapie pomocí neinvazivní stimulace mozku

Citovat

KOVÁČ, Daniel; Ľubomíra NOVÁKOVÁ; Jiří MEKYSKA; Kryštof NOVOTNÝ; Luboš BRABENEC; Patrícia KLOBUŠIAKOVÁ a Irena REKTOROVÁ. Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions. COMPUTERS IN BIOLOGY AND MEDICINE. ENGLAND: Elsevier Ltd, 2025, roč. 198, č. 111251, s. 1-12. ISSN 0010-4825. Dostupné z: https://doi.org/10.1016/j.compbiomed.2025.111251.

@article{2532317,
   author = {Kováč, Daniel and Nováková, Ľubomíra and Mekyska, Jiří and Novotný, Kryštof and Brabenec, Luboš and Klobušiaková, Patrícia and Rektorová, Irena},
   article_location = {ENGLAND},
   article_number = {111251},
   doi = {https://doi.org/10.1016/j.compbiomed.2025.111251},
   keywords = {Mild cognitive impairmentParkinson’s diseaseSpontaneous speechLinguistic biomarkersAcoustic biomarkersStatistical analysisMachine learning},
   language = {eng},
   issn = {0010-4825},
   journal = {COMPUTERS IN BIOLOGY AND MEDICINE},
   title = {Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions},
   url = {https://doi.org/10.1016/j.compbiomed.2025.111251},
   volume = {198},
   year = {2025}
}

TY  - JOUR
ID  - 2532317
AU  - Kováč, Daniel - Nováková, Ľubomíra - Mekyska, Jiří - Novotný, Kryštof - Brabenec, Luboš - Klobušiaková, Patrícia - Rektorová, Irena
PY  - 2025
TI  - Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions
JF  - COMPUTERS IN BIOLOGY AND MEDICINE
VL  - 198
IS  - 111251
SP  - 1-12
EP  - 1-12
PB  - Elsevier Ltd
SN  - 00104825
KW  - Mild cognitive impairmentParkinson’s diseaseSpontaneous speechLinguistic biomarkersAcoustic biomarkersStatistical analysisMachine learning
UR  - https://doi.org/10.1016/j.compbiomed.2025.111251
N2  - This study investigates speech impairments in individuals with mild cognitive impairment due to Alzheimer’s disease (MCI-AD), mild cognitive impairment with Lewy bodies (MCI-LB), and Parkinson’s disease with mild cognitive impairment (PD-MCI), compared to healthy controls (HC), aiming to identify linguistic and acoustic digital biomarkers that differentiate these groups. Monologue recordings were collected from 68 HC, 42 MCI-AD, 50 MCI-LB, and 47 PD-MCI participants (ON state). Participants were instructed to speak spontaneously for one and a half minutes. Speech was automatically transcribed, manually corrected, and analyzed using natural language processing to extract eight linguistic (lexical/syntactic) and four acoustic (prosodic) biomarkers. Group differences were assessed using the Mann–Whitney U test, with Spearman’s correlation used to examine associations with clinical and MRI measures (FDR-corrected). Machine learning models (XGBoost) were applied to evaluate the classificatory and predictive potential of speech features. Distinct speech patterns were observed across groups: MCI-AD participants exhibited reduced use of function words, resulting in increased content density, PD-MCI participants used shorter sentences and fewer coordinating conjunctions with longer pauses, and MCI-LB participants exhibited greater lexical repetition than MCI-AD. Altered speech features correlated with structural brain changes but not with global cognition (MoCA) or depressive symptoms (GDS). Sentence structure and pausing features showed strong interrelationships. Machine learning models showed that adding speech biomarkers improved classification performance compared to using clinical scores alone. In regression analyses, the models predicted MoCA with a normalized error of 10%, performing similarly on automatic and manually corrected transcripts. These findings suggest that speech biomarkers and traditional clinical assessments may offer complementary information about cognitive status and brain health, supporting their use in scalable, non-invasive cognitive monitoring.
ER  -

KOVÁČ, Daniel; Ľubomíra NOVÁKOVÁ; Jiří MEKYSKA; Kryštof NOVOTNÝ; Luboš BRABENEC; Patrícia KLOBUŠIAKOVÁ a Irena REKTOROVÁ. Digital speech biomarkers for assessing cognitive decline across neurodegenerative conditions. \textit{COMPUTERS IN BIOLOGY AND MEDICINE}. ENGLAND: Elsevier Ltd, 2025, roč.~198, č.~111251, s.~1-12. ISSN~0010-4825. Dostupné z: https://doi.org/10.1016/j.compbiomed.2025.111251.

Přehled o publikaci