Probabilistic prediction of neurological disorders with a statistical assessment of neuroimaging data modalities

TL;DR

This paper introduces a probabilistic model using Gaussian process priors to predict neurological disease states from neuroimaging data, assessing the importance of different modalities and brain regions with promising results.

Contribution

It proposes a multinomial logit model with Gaussian process priors for disease prediction and analysis of neuroimaging modality importance, employing advanced MCMC methods.

Findings

High predictive accuracy for Parkinsonian disorders

Little added benefit from multiple neuroimaging sequences

Regional importance aligns with clinical pathology

Abstract

For many neurological disorders, prediction of disease state is an important clinical aim. Neuroimaging provides detailed information about brain structure and function from which such predictions may be statistically derived. A multinomial logit model with Gaussian process priors is proposed to: (i) predict disease state based on whole-brain neuroimaging data and (ii) analyze the relative informativeness of different image modalities and brain regions. Advanced Markov chain Monte Carlo methods are employed to perform posterior inference over the model. This paper reports a statistical assessment of multiple neuroimaging modalities applied to the discrimination of three Parkinsonian neurological disorders from one another and healthy controls, showing promising predictive performance of disease states when compared to nonprobabilistic classifiers based on multiple modalities. The statistical analysis also quantifies the relative importance of different neuroimaging measures and brain regions in discriminating between these diseases and suggests that for prediction there is little benefit in acquiring multiple neuroimaging sequences. Finally, the predictive capability of different brain regions is found to be in accordance with the regional pathology of the diseases as reported in the clinical literature.