Performance of machine learning classification models of autism using resting-state fMRI is contingent on sample heterogeneity.
Maya A. ReiterAfrooz JahediAgastinose Ronickom Jac FredoInna FishmanBarbara A. BaileyRalph-Axel MüllerPublished in: Neural Comput. Appl. (2021)
Keyphrases
- classification models
- machine learning
- decision trees
- feature selection
- resting state fmri
- training data
- computer vision
- feature ranking
- learning algorithm
- models built
- support vector machine
- data mining
- attribute selection
- sample size
- feature set
- feature vectors
- training set
- data analysis
- pattern recognition
- bayesian networks
- functional connectivity
- feature extraction