Premium
P1‐453: SUBJECTIVE COGNITIVE COMPLAINTS: DIAGNOSTIC CLASSIFICATION USING A MACHINE LEARNING ALGORITHM
Author(s) -
Söderlund Maria Elvira,
Rodriguez Pablo Oscar,
Guajardo Maria Elena,
Cavagna Marina,
Labos Edith,
Camera Luis,
Adra Sofia,
Schapira Marcelo,
Seinhart Daniel Bernardo
Publication year - 2019
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1016/j.jalz.2019.06.1058
Subject(s) - dementia , machine learning , boston naming test , neuropsychological assessment , test (biology) , neuropsychology , psychology , artificial intelligence , random forest , neuropsychological test , cognition , medicine , computer science , psychiatry , disease , paleontology , pathology , biology
correctly classified 36 Ab(63.2%) and 28 Ab+ (71.8%) participants. For the Ab+ group, follow-up response times varied little by slope, whereas Abparticipants with steeper slopes had faster times at follow-up. Conclusions: Ab+ participants exhibited steeper learning slopes than Ab-. This may reflect early retrieval delays and subsequent hyperactivation or compensatory recruitment of additional brain regions. Learning slopes at baseline also predicted improved performance at follow-up, in line with existing research on within-session practice effects. Implications and future directions discussed.