Output details

Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity

<28> Developed computational speech analysis and machine learning algorithms for clinically-accurate Parkinson’s disease (PD) symptom quantification. The computational background to the Parkinson’s Voice Initiative (http://www.parkinsonsvoice.org), this work achieved significant and sustained worldwide publicity (BBC

News, most read article for 5 days; National Public Radio All Things Considered, US, 17M listeners; TED talk, 450,000 views, translated into 27 languages; Huffington Post, US; Le Monde, France, full-page spread) and acclaim (Max Little TED Fellowship, UNESCO Netexplo Award). The dataset, hosted at UC Irvine Machine Learning Repository (28,000 downloads), is widely-used as a challenging benchmark test of new machine learning algorithms.