Pitfalls and Limits in Automatic Dementia Assessment

  • Current work on speech-based dementia assessment focuses on either feature extraction to predict assessment scales, or on the automation of existing test procedures. Most research uses public data unquestioningly and rarely performs a detailed error analysis, focusing primarily on numerical performance. We perform an in-depth analysis of an automated standardized dementia assessment, the Syndrom-Kurz-Test. We find that while there is a high overall correlation with human annotators, due to certain artifacts, we observe high correlations for the severely impaired individuals, which is less true for the healthy or mildly impaired ones. Speech production decreases with cognitive decline, leading to overoptimistic correlations when test scoring relies on word naming. Depending on the test design, fallback handling introduces further biases that favor certain groups. These pitfalls remain independent of group distributions in datasets and require differentiated analysis of target groups.

Download full text files

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Franziska Braun, Christopher Witzl, Andreas Erzigkeit, Hartmut Lehfeld, Thomas Hillemacher, Tobias BockletORCiD, Korbinian RiedhammerORCiD
DOI:https://doi.org/10.21437/Interspeech.2025-2280
ISSN:2958-1796
Parent Title (English):Interspeech 2025
Publisher:ISCA
Document Type:conference proceeding (article)
Language:English
Reviewed:Begutachtet/Reviewed
Release Date:2025/11/25
Tag:dementia screening; neuropsychological tests; pathological speech
Pagenumber:5
First Page:5663
Last Page:5667
institutes:Fakultät Informatik
Zentrum für Künstliche Intelligenz (KIZ)
Research Themes:Digitalisierung & Künstliche Intelligenz
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.