Automated Huntington's Disease Prognosis via Biomedical Signals and Shallow Machine Learning

TL;DR

This study demonstrates that shallow machine learning models applied to biomedical signals like EEG, ECG, and NIRS can effectively predict Huntington's disease with high accuracy, offering a less resource-intensive prognosis method.

Contribution

The paper introduces a novel approach using shallow machine learning on biomedical signals for HD prognosis, achieving high accuracy with a small dataset.

Findings

Highest accuracy with Extremely Randomized Trees (AUC 0.963, 91.35%)

Raw signal features are most significant in disease prediction

Biomedical signals can effectively indicate HD abnormalities and progression

Abstract

Background: Huntington's disease (HD) is a rare, genetically determined brain disorder that limits the life of the patient, although early prognosis of HD can substantially improve the patient's quality of life. Current HD prognosis methods include using a variety of complex biomarkers such as clinical and imaging factors, however these methods have many shortfalls, such as their resource demand and failure to distinguish symptomatic and asymptomatic patients. Quantitative biomedical signaling has been used for diagnosis of other neurological disorders such as schizophrenia and has potential for exposing abnormalities in HD patients. Methodology: In this project, we used a premade, certified dataset collected at a clinic with 27 HD positive patients, 36 controls, and 6 unknowns with electroencephalography, electrocardiography, and functional near-infrared spectroscopy data. We first preprocessed the data and extracted a variety of features from both the transformed and raw signals, after which we applied a plethora of shallow machine learning techniques. Results: We found the highest accuracy was achieved by a scaled-out Extremely Randomized Trees algorithm, with area under the curve of the receiver operator characteristic of 0.963 and accuracy of 91.353%. The subsequent feature analysis showed that 60.865% of the features had p<0.05, with the features from the raw signal being most significant. Conclusion: The results indicate the promise of neural and cardiac signals for marking abnormalities in HD, as well as evaluating the progression of the disease in patients.