Predicting clinical diagnosis in Huntington's disease: An imaging polymarker

Abstract

Objective: Huntington's disease (HD) gene-carriers can be identified prior to clinical diagnosis; however, statistical models for predicting when overt motor symptoms will manifest are too imprecise to be useful at the level of the individual. Perfecting this prediction is integral to the search for disease modifying therapies. This study aimed to identify an imaging marker capable of reliably predicting real-life clinical diagnosis in HD.

Method: A multivariate machine learning approach was applied to resting-state and structural MRI scans from 19 pre-manifest HD gene carriers (preHD, 8 of whom developed clinical disease in the 5 years post-scanning) and 21 healthy controls. A classification model was developed using cross-group comparisons between preHD and controls, and within the preHD group in relation to "estimated" and "actual" proximity to disease onset. Imaging measures were modelled individually, and combined, and permutation modelling robustly tested classification accuracy.

Results: Classification performance for preHDs vs. controls was greatest when all measures were combined. The resulting polymarker predicted converters with high accuracy including those who were not expected to manifest in that timescale based on the currently adopted statistical models.

Interpretation: We propose that a holistic multivariate machine learning treatment of brain abnormalities in the premanifest phase can be used to accurately identify those patients within 5 years of developing motor features of Huntington's disease, with implications for prognostication and preclinical trials. This article is protected by copyright. All rights reserved.

http://ift.tt/2s9jMQX