Parkinson's disease diagnostics using AI and natural language knowledge transfer

TL;DR

This paper presents a deep learning method leveraging natural language knowledge transfer to classify speech recordings for Parkinson's disease diagnosis, achieving high accuracy with non-invasive smartphone data.

Contribution

It introduces a novel audio classification approach using wav2vec 2.0 for PD detection, combining speech analysis with transfer learning from language models.

Findings

Achieved up to 97.92% accuracy in PD classification

Constructed a speech dataset from smartphone recordings

Compared AI performance with neurology professionals' assessments

Abstract

In this work, the issue of Parkinson's disease (PD) diagnostics using non-invasive antemortem techniques was tackled. A deep learning approach for classification of raw speech recordings in patients with diagnosed PD was proposed. The core of proposed method is an audio classifier using knowledge transfer from a pretrained natural language model, namely \textit{wav2vec 2.0}. Method was tested on a group of 38 PD patients and 10 healthy persons above the age of 50. A dataset of speech recordings acquired using a smartphone recorder was constructed and the recordings were label as PD/non-PD with severity of the disease additionally rated using Hoehn-Yahr scale. The audio recordings were cut into 2141 samples that include sentences, syllables, vowels and sustained phonation. The classifier scores up to 97.92\% of cross-validated accuracy. Additionally, paper presents results of a human-level performance assessment questionnaire, which was consulted with the neurology professionals