Classification of schizophrenia patients based on resting-state functional network connectivity

Abstract

There is a growing interest in automatic classification of mental disorders based on neuroimaging data. Small training data sets (subjects) and very large amount of high dimensional data make it a challenging task to design robust and accurate classifiers for heterogeneous disorders such as schizophrenia. Most previous studies considered structural MRI, diffusion tensor imaging and task-based fMRI for this purpose. However, resting-state data has been rarely used in discrimination of schizophrenia patients from healthy controls. Resting data are of great interest, since they are relatively easy to collect, and not confounded by behavioral performance on a task. Several linear and non-linear classification methods were trained using a training dataset and evaluate with a separate testing dataset. Results show that classification with high accuracy is achievable using simple non-linear discriminative methods such as k-nearest neighbors (KNNs) which is very promising. We compare and report detailed results of each classifier as well as statistical analysis and evaluation of each single feature. To our knowledge our effects represent the first use of resting-state functional network connectivity (FNC) features to classify schizophrenia.

Computational neuroimaging strategies for single patient predictions

“…This means that conventional machine learning methods, which operate directly on observed features of A C C E P T E D M A N U S C R I P T (Ingalhalikar et al, 2014) but remain descriptive and do not offer a mechanistic link between the structural and functional components of any identified predictor. Finally, while functional connectivity (i.e., statistical dependencies between regional time series) has enabled successful machine learning applications (Arbabshirani et al, 2013;Craddock et al, 2009;Du et al, 2015;Richiardi et al, 2011;Rosa et al, 2015), its characterisation of neuronal processes is restricted to statistical correlations that are agnostic about the physiological causes of network dynamics. In general, machine learning applied to "raw" neuroimaging data does not easily identify mechanisms from which novel therapeutic approaches could be derived.…”

Accurate classification of schizophrenia patients based on novel resting-state fMRI features

“…In our previous work [26], we showed that resting-state FNC features can be used to classify schizophrenia patients from healthy controls. In this study we use both FNC and autoconnectivity features and test in on much larger dataset compared to our previous works.…”

Nodal centrality of functional network in the differentiation of schizophrenia

“…Using a similar feature extraction approach, multiclass pattern analysis on functional connectivity also discriminated schizophrenic patients and their healthy siblings with a modest accuracy rate (Yu et al, 2013). In another study classifying schizophrenia patients based on functional network connectivity, the correlations between various ICA components were computed to be used as features and worked well for several linear and non-linear classification methods that are commonly used (Arbabshirani et al, 2013). Despite good classification performance in these previous works, the feature selection for classification was usually based on the strength of functional connectivity rather than network characteristics.…”