@inproceedings{BraunFoerstelOppermannetal.2022, author = {Braun, Franziska and F{\"o}rstel, Markus and Oppermann, Bastian and Erzigkeit, Andreas and Lehfeld, Hartmut and Hillemacher, Thomas and Riedhammer, Korbinian}, title = {Automated Evaluation of Standardized Dementia Screening Tests}, series = {Interspeech 2022}, booktitle = {Interspeech 2022}, publisher = {ISCA}, address = {ISCA}, doi = {10.21437/Interspeech.2022-10436}, pages = {2478 -- 2482}, year = {2022}, abstract = {For dementia screening and monitoring, standardized tests play a key role in clinical routine since they aim at minimizing subjectivity by measuring performance on a variety of cognitive tasks. In this paper, we report a study consisting of a semistandardized history taking followed by two standardized neuropsychological tests, namely the SKT and the CERAD-NB. The tests include basic tasks such as naming objects, learning word lists, but also widely used tools such as the MMSE. Most of the tasks are performed verbally and should thus be suitable for automated scoring based on transcripts. For the first batch of 30 patients, we analyze the correlation between expert manual evaluations and automatic evaluations based on manual and automatic transcriptions. For both SKT and CERAD-NB, we observe high to perfect correlations using manual transcripts; for certain tasks with lower correlation, the automatic scoring is stricter than the human reference since it is limited to the audio. Using automatic transcriptions, correlations drop as expected and are related to recognition accuracy; however, we still observe high correlations of up to 0.98 (SKT) and 0.85 (CERADNB). We show that using word alternatives helps to mitigate recognition errors and subsequently improves correlation with expert scores.}, language = {en} } @inproceedings{BraunWitzlErzigkeitetal.2025, author = {Braun, Franziska and Witzl, Christopher and Erzigkeit, Andreas and Lehfeld, Hartmut and Hillemacher, Thomas and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Pitfalls and Limits in Automatic Dementia Assessment}, series = {Interspeech 2025}, booktitle = {Interspeech 2025}, publisher = {ISCA}, issn = {2958-1796}, doi = {10.21437/Interspeech.2025-2280}, pages = {5663 -- 5667}, year = {2025}, abstract = {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.}, language = {en} }