Premium
O4‐12‐04: EVALUATION OF THE IDEA (IDENTIFICATION AND INTERVENTIONS FOR DEMENTIA IN ELDERLY AFRICANS) BRIEF COGNITIVE SCREENING TOOL FOR IDENTIFICATION OF DELIRIUM IN OLDER HOSPITALISED ADULTS IN TANZANIA
Author(s) -
Paddick Stella-Maria,
Lewis Emma Grace,
Duinmaijer Ashanti T.,
Banks Jessica,
Urasa Sarah,
Tucker Laura,
Kisoli Aloyce,
Cletus Jane,
Lissu Carolyn,
Kisima John,
Dotchin Catherine,
Gray William K.,
Mushi Declare,
Walker Richard
Publication year - 2016
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.2016.06.675
Subject(s) - delirium , dementia , medicine , tanzania , cognition , psychological intervention , cognitive decline , referral , psychiatry , pediatrics , family medicine , disease , environmental science , environmental planning
tion and classification, and show that ML methods improve diagnostic accuracy compared to existing CDT scoring systems. Methods: We applied our novel dCDT software to categorize every pen stroke from 3994 neurologically impaired and cognitively healthy (CH) subjects, computing approximately 1000 novel variables on that data. Using ML techniques (e.g., regularized logistic regression) we created models that best classify subjects into four categories: memory impaired, vascular related disorders, Parkinson’s disease, CH. We embodied in code eight manual scoring systems (MSS), then adjusted their parameters to optimize their performance. We measured our ML model performances using 5-fold cross-validation, reporting AUCs averaged over the 5 folds and compared predictive performance to the MSS optimized versions. Results: Classifiers produced by ML methods significantly outperformed MSS: ML methods had an AUC performance ranging from 0.87 to 0.92 (depending on the algorithm and condition being classified), while corresponding AUCs for MSS ranged from 0.63 to 0.74. The MSS AUC ranges were higher than what those manual scoring systems would produce in practice, as optimization ensured their best performance and embodying them in code eliminated all interrater reliability error. Conclusions: ML methods combined with precise spatial and temporal analysis of drawing behavior enables the creation of new ways to detect and classify cognitive functions with far greater accuracy, enabling improved diagnostic capabilities with little to no manual effort. Applying ML to theoretical models improves predictive value by using features not typically considered under existing frameworks. Combining new technology and advanced analytics with theoretical neurosciences enables new opportunities for early diagnosis and treatment.