Vector-space topic models for detecting Alzheimer's disease

Yancheva, Maria; Rudzicz, Frank

doi:10.18653/v1/p16-1221

Cited by 48 publications

(65 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While our goal in this paper was not to push the state-of-the-art on the DementiaBank dataset, we do find that our best English result (AUC=0.84, which corresponds to an accuracy of 75% and F 1 score of 0.77) is comparable to the other published results on this dataset (Prud'hommeaux and Roark, 2015;Yancheva and Rudzicz, 2016;Sirts et al, 2017;Fraser et al, 2016;Hernández-Domínguez et al, 2018). There are no previously published results on the French dataset.…”

Section: Discussionsupporting

confidence: 63%

Multilingual prediction of

Fraser

Linz

Bai

et al. 2019

Proceedings of the 2019 Conference of the North

Self Cite

View full text Add to dashboard Cite

There is growing evidence that changes in speech and language may be early markers of dementia, but much of the previous NLP work in this area has been limited by the size of the available datasets. Here, we compare several methods of domain adaptation to augment a small French dataset of picture descriptions (n = 57) with a much larger English dataset (n = 550), for the task of automatically distinguishing participants with dementia from controls. The first challenge is to identify a set of features that transfer across languages; in addition to previously used features based on information units, we introduce a new set of features to model the order in which information units are produced by dementia patients and controls. These concept-based language model features improve classification performance in both English and French separately, and the best result (AUC = 0.89) is achieved using the multilingual training set with a combination of information and language model features.

show abstract

Section: Discussionsupporting

confidence: 63%

Multilingual prediction of

Fraser

Linz

Bai

et al. 2019

Proceedings of the 2019 Conference of the North

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fraser et al. [24] reported an accuracy of 81.92%, whereas Yancheva and Rudzicz [26] reported an accuracy, precision, recall, and F‐score of 80%. In both works, the authors performed a classification between HCs and AD participants, without including the MCI sample.…”

Section: Discussionmentioning

confidence: 99%

“…Yancheva and Rudzicz [26] automatically extracted the main ICUs retrieved by elderly adults in the Pitt Corpus. The authors contrasted automatically extracted ICUs to a combination of several predefined lists of ICUs.…”

Section: Introductionmentioning

confidence: 99%

Computer‐based evaluation of Alzheimer's disease and mild cognitive impairment patients during a picture description task

Hernández-Domínguez

Ratté

Sierra

et al. 2018

Alz & Dem Diag Ass & Dis Mo

View full text Add to dashboard Cite

Introduction We present a methodology to automatically evaluate the performance of patients during picture description tasks. Methods Transcriptions and audio recordings of the Cookie Theft picture description task were used. With 25 healthy elderly control (HC) samples and an information coverage measure, we automatically generated a population-specific referent. We then assessed 517 transcriptions (257 Alzheimer's disease [AD], 217 HC, and 43 mild cognitively impaired samples) according to their informativeness and pertinence against this referent. We extracted linguistic and phonetic metrics which previous literature correlated to early-stage AD. We trained two learners to distinguish HCs from cognitively impaired individuals. Results Our measures significantly ( P < .001) correlated with the severity of the cognitive impairment and the Mini–Mental State Examination score. The classification sensitivity was 81% (area under the curve of receiver operating characteristics = 0.79) and 85% (area under the curve of receiver operating characteristics = 0.76) between HCs and AD and between HCs and AD and mild cognitively impaired, respectively. Discussion An automated assessment of a picture description task could assist clinicians in the detection of early signs of cognitive impairment and AD.

show abstract

“…We report the average of the F1 micro and F1 macro scores for the 5-folds for all baseline and proposed models. These results are presented in two parts in Tables 2 and 3. The TF-IDF model sets a very strong baseline with an accuracy of 74.95%, which is already better than the automatic models of Yancheva and Rudzicz (2016) on the same data.…”

Section: Db Classificationmentioning

confidence: 91%