Machine Learning Applied to EEG Data May Serve as Huntington’s Biomarker, Study Suggests
A method called quantitative electroencephalography (qEEG) enables the identification of Huntington’s gene carriers and could become a disease biomarker, according to a pilot study.
The research, “EEG may serve as a biomarker in Huntington’s disease using machine learning automatic classification,” appeared in the journal Scientific Reports.
Progressive brain atrophy, or shrinkage, is a hallmark of Huntington’s, and is found even before the first disease manifestations.
The value of clinical decision support
cancer diagnosis is an emotional struggle and the beginning of a challenging journey. Clinicians – their partners in this journey – face enormous time pressure and have to sift through a staggering amount of information. For example, more than a million medical papers are added each year to data sources like PubMed, which roughly equals a new paper published every two minutes. Every day, nearly 100 clinical trial reports and reviews are added.1 And in 2018, more than 1000 new cancer drugs were being studied in clinical trials or awaiting FDA review.2,3
Taken on their own, these vast amounts of data don’t automatically add up to improved patient outcomes. No clinician has enough time to delve deeply into the latest and increasingly complex research to confidently decide which diagnostics and therapies are the right choice for an individual patient.
