Related Experiment Video
Updated: Aug 6, 2026
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
Published on: June 9, 2018
A novel machine learning approach for the classification of Huntington disease manifestation using motor features
Niroshan Jeyakumar1, Daniel Woolnough2, Guoyin Li2
1Sydney Medical School, University of Sydney, Sydney, New South Wales, Australia; Movement Disorders Unit, Westmead Hospital, Westmead, New South Wales, Australia.
Insights
We developed machine learning models to accurately diagnose manifest Huntington disease (HD) using motor scores. These tools can improve diagnostic consistency and support clinical trial data standardization.
Area of Science:
- Neurology
- Computational Biology
- Biostatistics
Background:
- Current Huntington disease (HD) diagnosis relies on subjective motor assessments.
- Lack of explicit rules for Unified Huntington Disease Rating Scale (UHDRS) scores leads to diagnostic variability.
Purpose of the Study:
- Develop algorithms for objective classification of manifest HD.
- Utilize UHDRS motor scores for improved diagnostic accuracy.
Main Methods:
- Applied supervised machine learning: elastic net logistic regression, random forest, and a novel robust support vector machine (rSVM).
- Trained and tested models on data from Enroll-HD and COHORT observational studies.
- Used existing Diagnostic Confidence Level (DCL)-based classifications as the reference standard.
Main Results:
- All models achieved ≥95% classification accuracy for manifest HD.
- Demonstrated ≥90% sensitivity and specificity in diagnosing manifest HD.
- Identified potential inconsistencies in DCL classifications, with rSVM reclassifying some cases.
Conclusions:
- Developed highly accurate machine learning models for diagnosing manifest HD using UHDRS motor scores.
- Models show potential as clinical decision support tools.
- Applications include data checking and standardization in clinical trials.
Background:
Currently, diagnosis of manifest Huntington disease (HD) is made when there is ≥ 99% confidence that observed motor abnormalities, rated on the Unified Huntington Disease Rating Scale (UHDRS), are due to HD (Diagnostic Confidence Level, DCL, = 4). However, there are no explicit rules relating UHDRS motor score items to an appropriate DCL, leaving diagnosis potentially subjective and variable.
Objective:
We sought to develop algorithms to classify manifest HD, based on UHDRS motor scores.
Methods:
We applied supervised machine learning techniques including elastic net logistic regression, random forest and our novel "robust support vector machine" (rSVM) designed to handle data uncertainty, to build three different classification models for predicting HD class (manifest/non-manifest) based on motor scores. Existing DCL-based classifications formed the reference standard. Models were trained and tested using data from two, large observational studies - Enroll-HD and COHORT.
Results:
All three models demonstrated ≥95% classification accuracy and ≥90% sensitivity and specificity for the diagnosis of manifest HD across both study populations. 47.8% of Enroll-HD cases classified as manifest by the rSVM but non-manifest by the DCL-based reference were considered manifest by another clinical classifier, Participant Category. The majority of these people also had high DCLs and many had high total motor scores so may reflect inconsistencies or data entry errors in the DCL classifications.
Conclusions:
We have developed three highly accurate models for diagnosing manifest HD using UHDRS motor scores. This has potential applications as clinical decision support tools and for data checking and standardization in clinical trials.
