PMID- 35204032
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220301
IS  - 2076-3425 (Print)
IS  - 2076-3425 (Electronic)
IS  - 2076-3425 (Linking)
VI  - 12
IP  - 2
DP  - 2022 Feb 15
TI  - Semantic Feature Extraction Using SBERT for Dementia Detection.
LID - 10.3390/brainsci12020270 [doi]
LID - 270
AB  - Dementia is a neurodegenerative disease that leads to the development of 
      cognitive deficits, such as aphasia, apraxia, and agnosia. It is currently 
      considered one of the most significant major medical problems worldwide, 
      primarily affecting the elderly. This condition gradually impairs the patient's 
      cognition, eventually leading to the inability to perform everyday tasks without 
      assistance. Since dementia is an incurable disease, early detection plays an 
      important role in delaying its progression. Because of this, tools and methods 
      have been developed to help accurately diagnose patients in their early stages. 
      State-of-the-art methods have shown that the use of syntactic-type linguistic 
      features provides a sensitive and noninvasive tool for detecting dementia in its 
      early stages. However, these methods lack relevant semantic information. In this 
      work, we propose a novel methodology, based on the semantic features approach, by 
      using sentence embeddings computed by Siamese BERT networks (SBERT), along with 
      support vector machine (SVM), K-nearest neighbors (KNN), random forest, and an 
      artificial neural network (ANN) as classifiers. Our methodology extracted 17 
      features that provide demographic, lexical, syntactic, and semantic information 
      from 550 oral production samples of elderly controls and people with Alzheimer's 
      disease, provided by the DementiaBank Pitt Corpus database. To quantify the 
      relevance of the extracted features for the dementia classification task, we 
      calculated the mutual information score, which demonstrates a dependence between 
      our features and the MMSE score. The experimental classification performance 
      metrics, such as the accuracy, precision, recall, and F1 score (77, 80, 80, and 
      80%, respectively), validate that our methodology performs better than 
      syntax-based methods and the BERT approach when only the linguistic features are 
      used.
FAU - Santander-Cruz, Yamanki
AU  - Santander-Cruz Y
AD  - Facultad de Ingenieria, Universidad Autonoma de Queretaro, Queretaro C.P. 76010, 
      Mexico.
FAU - Salazar-Colores, Sebastian
AU  - Salazar-Colores S
AUID- ORCID: 0000-0002-6353-0864
AD  - Centro de Investigaciones en Optica, Leon C.P. 37150, Mexico.
FAU - Paredes-Garcia, Wilfrido Jacobo
AU  - Paredes-Garcia WJ
AUID- ORCID: 0000-0001-9740-0358
AD  - Facultad de Ingenieria, Universidad Autonoma de Queretaro, Queretaro C.P. 76010, 
      Mexico.
FAU - Guendulain-Arenas, Humberto
AU  - Guendulain-Arenas H
AD  - Departamento de Geriatria, Instituto Mexicano del Seguro Social, San Juan del Rio 
      C.P. 76800, Mexico.
FAU - Tovar-Arriaga, Saul
AU  - Tovar-Arriaga S
AUID- ORCID: 0000-0002-2695-1934
AD  - Facultad de Ingenieria, Universidad Autonoma de Queretaro, Queretaro C.P. 76010, 
      Mexico.
LA  - eng
PT  - Journal Article
DEP - 20220215
PL  - Switzerland
TA  - Brain Sci
JT  - Brain sciences
JID - 101598646
PMC - PMC8870383
OTO - NOTNLM
OT  - NLP feature extraction
OT  - SBERT
OT  - dementia
OT  - semantic analysis
OT  - syntax analysis
COIS- The authors declare no conflict of interest.
EDAT- 2022/02/26 06:00
MHDA- 2022/02/26 06:01
PMCR- 2022/02/15
CRDT- 2022/02/25 01:03
PHST- 2021/12/04 00:00 [received]
PHST- 2022/01/28 00:00 [revised]
PHST- 2022/01/29 00:00 [accepted]
PHST- 2022/02/25 01:03 [entrez]
PHST- 2022/02/26 06:00 [pubmed]
PHST- 2022/02/26 06:01 [medline]
PHST- 2022/02/15 00:00 [pmc-release]
AID - brainsci12020270 [pii]
AID - brainsci-12-00270 [pii]
AID - 10.3390/brainsci12020270 [doi]
PST - epublish
SO  - Brain Sci. 2022 Feb 15;12(2):270. doi: 10.3390/brainsci12020270.