Open AccessBlinded Clinical Evaluation for Dementia of Alzheimer’s Type Classification Using FDG-PET: A Comparison Between Feature-Engineered and Non-Feature-Engineered Machine Learning Methods
Author(s) -
Da Ma,
Evangeline Yee,
Jane Stocks,
Lisanne M. Jenkins,
Karteek Popuri,
Guillaume Chaussé,
Lei Wang,
Stephan Probst,
Mirza Faisal Beg
Publication year - 2021
Publication title -
journal of alzheimer's disease
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.677
H-Index - 139
eISSN - 1875-8908
pISSN - 1387-2877
DOI - 10.3233/jad-201591
Subject(s) - artificial intelligence , dementia , machine learning , feature engineering , feature (linguistics) , clinical dementia rating , convolutional neural network , computer science , support vector machine , neuroimaging , classifier (uml) , pattern recognition (psychology) , deep learning , medicine , pathology , psychiatry , disease , linguistics , philosophy
Advanced machine learning methods can aid in the identification of dementia risk using neuroimaging-derived features including FDG-PET. However, to enable the translation of these methods and test their usefulness in clinical practice, it is crucial to conduct independent validation on real clinical samples, which has yet to be properly delineated in the current literature.