Learning stable and predictive network-based patterns of schizophrenia and its clinical symptoms

Abstract

Schizophrenia is often associated with disrupted brain connectivity. However, identifying specific neuroimaging-based patterns pathognomonic for schizophrenia and related symptom severity remains a challenging open problem requiring large-scale datadriven analyses emphasizing not only statistical significance but also stability across multiple datasets, contexts and cohorts. Accurate prediction on previously unseen subjects, or generalization, is also essential for any useful biomarker of schizophrenia. In order to build a predictive model based on functional network feature patterns, we studied whole-brain fMRI functional networks, both at the voxel level and lower-resolution supervoxel level. Targeting Auditory Oddball task data on the FBIRN fMRI dataset (n = 95), we considered node-degree and link-weight network features and evaluated stability and generalization accuracy of statistically significant feature sets in discriminating patients vs. controls. We also applied sparse multivariate regression (elastic net) to whole-brain functional connectivity features, for the first time, to derive stable predictive features for symptom severity. Wholebrain link-weight features achieved 74% accuracy in identifying patients and were more stable than voxel-wise node-degrees. Linkweight features predicted severity of several negative and positive symptom scales, including inattentiveness and bizarre behavior. The most-significant, stable and discriminative functional connectivity changes involved increased correlations between thalamus and primary motor/primary sensory cortex, and between precuneus (BA7) and thalamus, putamen, and Brodmann areas BA9 and BA44. Precuneus, along with BA6 and primary sensory cortex, was also involved in predicting severity of several symptoms. Overall, the proposed multi-step methodology may help identify more reliable multivariate patterns allowing for accurate prediction of schizophrenia and its symptoms severity.

Medicine and the rise of the robots: a qualitative review of recent advances of artificial intelligence in health

“…The emerging literature has also shown that AI is proving to be useful in these clinical areas. For example, researchers built a predictive model based on machine learning using whole-brain functional magnetic resonance imaging (fMRI) to achieve 74% accuracy in identifying patients with more severe negative and positive symptoms in schizophrenia, suggesting the use of brain imaging to predict the disease and its symptom severity 20. In another study, researchers demonstrated that a linguistic machine learning system, using fMRI and proton magnetic resonance spectroscopy ( 1 H-MRS) inputs, showed nearly perfect classification accuracy and was able to predict lithium response in bipolar patients with at least 88% accuracy in training and 80% accuracy in validation, allowing psychiatrists the ability to predict lithium response and avoid unnecessary treatment 21…”

Machine learning in schizophrenia genomics, a case‐control study using 5,090 exomes

“…Given the role of environment, it is unlikely to find a genetic test that predicts with 100% certainty the individuals who will develop SCZ solely based on genomic data. If, however, such a predictive algorithm is trained using genomic data (including both exonic mutations and CNVs), transcriptome data, and ML approaches using other phenotypic information, such as speech (Bedi et al, 2015) or neuroimaging data (Gheiratmand et al, 2017) are available in study phs000473.v1.p1. We thank the authors and dbGaP for access to the WES data.…”

Inferring health conditions from fMRI-graph data

“…These connectivities were calculated as in § § 2.3 and 4.1. More sophisticated choices of Regions Of Interests and functional-connectivity measures (Marrelec and Fransson, 2011;Smith et al, 2011;Wang et al, 2014;Gheiratmand et al, 2017;Demirci et al, 2008) or even integration of functional and structural imaging (Michael et al, 2010) could obviously lead to an increased predictive power. A different choice of sufficient statistics could also improve the performance.…”