Investigating the Correspondence of Clinical Diagnostic Grouping With Underlying Neurobiological and Phenotypic Clusters Using Unsupervised Machine Learning.
Xinyu ZhaoD. RangaprakashBowen YuanThomas S. Denney Jr.Jeffrey S. KatzMichael N. DretschGopikrishna DeshpandePublished in: Frontiers Appl. Math. Stat. (2018)
Keyphrases
- machine learning
- agglomerative clustering
- diagnostic imaging
- disease diagnosis
- medical diagnostic
- normalized cut
- clinically relevant
- clinical diagnosis
- unsupervised clustering
- supervised classification
- unsupervised learning
- supervised learning
- acute myocardial infarction
- clinical setting
- computer aided diagnosis systems
- clustering algorithm
- cluster analysis
- decision trees
- hierarchical clustering
- feature selection
- traditional chinese medicine
- medical diagnosis
- natural language processing
- semi supervised
- machine learning methods
- cluster validation
- meaningful clusters
- biologically inspired
- differential diagnosis
- expert systems
- hierarchical clustering algorithm
- data analysis
- diagnostic process
- medical domain
- coronary artery disease
- clinical decision support systems
- reinforcement learning
- information extraction
- active learning
- machine learning algorithms
- data points
- text classification
- knowledge discovery
- clinical trials
- k means
- document clustering
- point correspondences
- medical images
- text mining
- learning algorithm
- data mining