Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200417892> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4200417892 abstract "ABSTRACT Mild cognitive impairment (MCI) is an early stage of age-inappropriate cognitive decline, which could develop into dementia – an untreatable neurodegenerative disorder. An early detection of MCI is a crucial step for timely prevention and intervention. To tackle this problem, recent studies have developed deep learning models to detect MCI and various types of dementia using data obtained from the classic clock-drawing test (CDT), a popular neuropsychological screening tool that can be easily and rapidly implemented for assessing cognitive impairments in an aging population. While these models succeed at distinguishing severe forms of dementia, it is still difficult to predict the early stage of the disease using the CDT data alone. Also, the state-of-the-art deep learning techniques still face the black-box challenges, making it questionable to implement them in the clinical setting. Here, we propose a novel deep learning modeling framework that incorporates data from multiple drawing tasks including the CDT, cube-copying, and trail-making tasks obtained from a digital platform. Using self-attention and soft-label methods, our model achieves much higher classification performance at detecting MCI compared to those of a well-established convolutional neural network model. Moreover, our model can highlight features of the MCI data that considerably deviate from those of the healthy aging population, offering accurate predictions for detecting MCI along with visual explanation that aids the interpretation of the deep learning model." @default.
- W4200417892 created "2021-12-31" @default.
- W4200417892 creator A5004289799 @default.
- W4200417892 creator A5004702624 @default.
- W4200417892 creator A5011451938 @default.
- W4200417892 creator A5059182770 @default.
- W4200417892 creator A5059813206 @default.
- W4200417892 creator A5075818328 @default.
- W4200417892 creator A5078708583 @default.
- W4200417892 date "2021-12-16" @default.
- W4200417892 modified "2023-09-25" @default.
- W4200417892 title "An Explainable Self-Attention Deep Neural Network for Detecting Mild Cognitive Impairment Using Multi-input Digital Drawing Tasks" @default.
- W4200417892 cites W1553544812 @default.
- W4200417892 cites W1963487177 @default.
- W4200417892 cites W1972336244 @default.
- W4200417892 cites W2079465034 @default.
- W4200417892 cites W2108598243 @default.
- W4200417892 cites W2109528095 @default.
- W4200417892 cites W2165758561 @default.
- W4200417892 cites W2177693422 @default.
- W4200417892 cites W2250251955 @default.
- W4200417892 cites W2401062574 @default.
- W4200417892 cites W2501591283 @default.
- W4200417892 cites W2753612061 @default.
- W4200417892 cites W2945976633 @default.
- W4200417892 cites W2962858109 @default.
- W4200417892 cites W3012670297 @default.
- W4200417892 cites W3035422918 @default.
- W4200417892 cites W3109437785 @default.
- W4200417892 cites W3134890023 @default.
- W4200417892 cites W3188802600 @default.
- W4200417892 cites W3205109224 @default.
- W4200417892 doi "https://doi.org/10.1101/2021.12.15.472738" @default.
- W4200417892 hasPublicationYear "2021" @default.
- W4200417892 type Work @default.
- W4200417892 citedByCount "1" @default.
- W4200417892 countsByYear W42004178922022 @default.
- W4200417892 crossrefType "posted-content" @default.
- W4200417892 hasAuthorship W4200417892A5004289799 @default.
- W4200417892 hasAuthorship W4200417892A5004702624 @default.
- W4200417892 hasAuthorship W4200417892A5011451938 @default.
- W4200417892 hasAuthorship W4200417892A5059182770 @default.
- W4200417892 hasAuthorship W4200417892A5059813206 @default.
- W4200417892 hasAuthorship W4200417892A5075818328 @default.
- W4200417892 hasAuthorship W4200417892A5078708583 @default.
- W4200417892 hasBestOaLocation W42004178921 @default.
- W4200417892 hasConcept C108583219 @default.
- W4200417892 hasConcept C118552586 @default.
- W4200417892 hasConcept C119857082 @default.
- W4200417892 hasConcept C14216870 @default.
- W4200417892 hasConcept C142724271 @default.
- W4200417892 hasConcept C154945302 @default.
- W4200417892 hasConcept C15744967 @default.
- W4200417892 hasConcept C169900460 @default.
- W4200417892 hasConcept C2779134260 @default.
- W4200417892 hasConcept C2779483572 @default.
- W4200417892 hasConcept C2908647359 @default.
- W4200417892 hasConcept C41008148 @default.
- W4200417892 hasConcept C71924100 @default.
- W4200417892 hasConcept C81363708 @default.
- W4200417892 hasConcept C99454951 @default.
- W4200417892 hasConceptScore W4200417892C108583219 @default.
- W4200417892 hasConceptScore W4200417892C118552586 @default.
- W4200417892 hasConceptScore W4200417892C119857082 @default.
- W4200417892 hasConceptScore W4200417892C14216870 @default.
- W4200417892 hasConceptScore W4200417892C142724271 @default.
- W4200417892 hasConceptScore W4200417892C154945302 @default.
- W4200417892 hasConceptScore W4200417892C15744967 @default.
- W4200417892 hasConceptScore W4200417892C169900460 @default.
- W4200417892 hasConceptScore W4200417892C2779134260 @default.
- W4200417892 hasConceptScore W4200417892C2779483572 @default.
- W4200417892 hasConceptScore W4200417892C2908647359 @default.
- W4200417892 hasConceptScore W4200417892C41008148 @default.
- W4200417892 hasConceptScore W4200417892C71924100 @default.
- W4200417892 hasConceptScore W4200417892C81363708 @default.
- W4200417892 hasConceptScore W4200417892C99454951 @default.
- W4200417892 hasLocation W42004178921 @default.
- W4200417892 hasLocation W42004178922 @default.
- W4200417892 hasLocation W42004178923 @default.
- W4200417892 hasOpenAccess W4200417892 @default.
- W4200417892 hasPrimaryLocation W42004178921 @default.
- W4200417892 hasRelatedWork W2337926734 @default.
- W4200417892 hasRelatedWork W2731899572 @default.
- W4200417892 hasRelatedWork W3116150086 @default.
- W4200417892 hasRelatedWork W3133861977 @default.
- W4200417892 hasRelatedWork W4200173597 @default.
- W4200417892 hasRelatedWork W4311257506 @default.
- W4200417892 hasRelatedWork W4312417841 @default.
- W4200417892 hasRelatedWork W4320802194 @default.
- W4200417892 hasRelatedWork W4321369474 @default.
- W4200417892 hasRelatedWork W4366224123 @default.
- W4200417892 isParatext "false" @default.
- W4200417892 isRetracted "false" @default.
- W4200417892 workType "article" @default.