Inferring health conditions from fMRI-graph data

TL;DR

This paper presents a method to derive likelihoods from fMRI-graph data for disease diagnosis, enabling better integration of multiple tests and improving clinical decision-making.

Contribution

It introduces a likelihood-based approach from first principles for fMRI data, allowing comparison of data-reduction algorithms and better clinical integration.

Findings

Likelihoods comparable to previous schizophrenia studies

Method enables combining multiple diagnostic tests

Approach based on partial exchangeability and conjugate priors

Abstract

Automated classification methods for disease diagnosis are currently in the limelight, especially for imaging data. Classification does not fully meet a clinician's needs, however: in order to combine the results of multiple tests and decide on a course of treatment, a clinician needs the likelihood of a given health condition rather than binary classification yielded by such methods. We illustrate how likelihoods can be derived step by step from first principles and approximations, and how they can be assessed and selected, illustrating our approach using fMRI data from a publicly available data set containing schizophrenic and healthy control subjects. We start from the basic assumption of partial exchangeability, and then the notion of sufficient statistics and the "method of translation" (Edgeworth, 1898) combined with conjugate priors. This method can be used to construct a likelihood that can be used to compare different data-reduction algorithms. Despite the simplifications and possibly unrealistic assumptions used to illustrate the method, we obtain classification results comparable to previous, more realistic studies about schizophrenia, whilst yielding likelihoods that can naturally be combined with the results of other diagnostic tests.