Article

Automatic speech recognition alters diagnostic error and biomarker validity in AI-based dementia speech assessment

2026-06-10

Abstract excerpt

<title>Abstract</title> <p>Speech-based digital endpoints are increasingly used to scale speech-based dementia assessment, but transcription systems may alter downstream diagnostic errors and the validity of linguistic biomarkers used by artificial intelligence models. We evaluated whether an AI-based dementia speech classifier trained on human transcripts retained clinical validity when applied to transcripts ge...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: cb482866-4997-58d1-9e2f-bda919460dc2
DOI: 10.21203/rs.3.rs-9892520/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Automatic speech recognition alters diagnostic error and biomarker validity in AI-based dementia speech assessmentDOI 10.21203/rs.3.rs-9892520/v1Read

Automated transcription in primary progressive aphasia: Accuracy and effects on classificationSemantic proximity Read

Evaluation of a speech-based AI system for early detection of Alzheimer’s disease remotely via smartphonesSemantic proximity Read

Linguistic and Acoustic Biomarkers from Simulated Speech Reveal Early Cognitive Impairment Patterns in Alzheimer’s DiseaseSemantic proximity Read

AI-based Speech Error Detection to Differentiate Primary Progressive Aphasia VariantsSemantic proximity Read

Lexical and acoustic speech features relating to Alzheimer’s disease pathologySemantic proximity Read

Clinically meaningful metrics of speech in neurodegenerative disease: Quantification of speech intelligibility and naturalness in ataxiaSemantic proximity Read

Digital language markers distinguish frontal from right anterior temporal lobe atrophy in frontotemporal dementiaSemantic proximity Read

Measuring Reliability in Locally-deployed Language Model Dysarthric Speech AssessmentsSemantic proximity Read

Detecting Preclinical Alzheimer’s Disease Risk in Cognitively Normal Adults Using Speech Acoustics: Validation with Plasma p-Tau217 and APOE-ε4 StatusSemantic proximity Read

Acoustic Analysis of Primary Care Patient-provider Conversations to Screen for Cognitive ImpairmentSemantic proximity Read

Assessing the Effectiveness of Automatic Speech Recognition Technology in Emergency Medicine Settings: A Comparative Study of Four AI-powered EnginesSemantic proximity Read

AI-Enhanced Animal Naming as a Digital Biomarker for Early Cognitive ScreeningSemantic proximity Read