Prodromal detection of Alzheimer's Disease(AD) is a substantial challenge in the research community. Among the tools used in AD diagnosis, cognitive exams are standard in most procedures. However, the barrage of cognitive examinations is both time and resource consuming. With the use of Machine Learning, Feature Elimination (FE) can be combined with classification algorithms to determine which cognitive exams are best suited for diagnosis. Using the results of FE, it can be determined if subsections of different composite scores can be combined to create a new enhanced and exhaustive exam. This paper implements a Recursive Feature Elimination with Cross Validation (RFECV) machine learning algorithm to determine which cognitive exams perform best for AD classification tasks. Out of 119 features, an average of 16 features were selected as optimal. These optimal features average 75% Accuracy, 70% Precision, and 75% Recall and an F1 Weighted score of 71% in classification.
- Recursive Feature Elimination with Cross Validation for Alzheimer's Disease Classification using Cognitive Exam Scores
- Christian Yaphet Freytes - Florida International UniversityRobin Perry Mayrand - Florida International University,Electrical & Computer Engineering,Miami,FL,USALuana Okino Sawada - Florida International University,Computing & Information Sciences,Miami,FL,USAThony Yan Liang - Florida International University,Electrical & Computer Engineering,Miami,FL,USARosie E. Curiel Cid - University of MiamiShanna Burke - Florida International UniversityDavid Loewenstein - University of MiamiRanjan Duara - Mount Sinai Medical CenterMalek Adjouadi - Florida International University
- 2023 Intelligent Methods, Systems, and Applications (IMSA), pp.327-332
- IEEE
- Health (10.13039/100018696) National Science Foundation (10.13039/100000001)
- Center on Aging; Miller School of Medicine; UMMG Dept of Psychiatry & Behavioral Sciences
- English
- Conference proceeding
- 991031927904402976