Detecting Parkinson Disease Using a Web-Based Speech Task: Observational Study

Abstract

Background Access to neurological care for Parkinson disease (PD) is a rare privilege for millions of people worldwide, especially in resource-limited countries. In 2013, there were just 1200 neurologists in India for a population of 1.3 billion people; in Africa, the average population per neurologist exceeds 3.3 million people. In contrast, 60,000 people receive a diagnosis of PD every year in the United States alone, and similar patterns of rising PD cases—fueled mostly by environmental pollution and an aging population—can be seen worldwide. The current projection of more than 12 million patients with PD worldwide by 2040 is only part of the picture given that more than 20% of patients with PD remain undiagnosed. Timely diagnosis and frequent assessment are key to ensure timely and appropriate medical intervention, thus improving the quality of life of patients with PD. Objective In this paper, we propose a web-based framework that can help anyone anywhere around the world record a short speech task and analyze the recorded data to screen for PD. Methods We collected data from 726 unique participants (PD: 262/726, 36.1% were women; non-PD: 464/726, 63.9% were women; average age 61 years) from all over the United States and beyond. A small portion of the data (approximately 54/726, 7.4%) was collected in a laboratory setting to compare the performance of the models trained with noisy home environment data against high-quality laboratory-environment data. The participants were instructed to utter a popular pangram containing all the letters in the English alphabet, “the quick brown fox jumps over the lazy dog.” We extracted both standard acoustic features (mel-frequency cepstral coefficients and jitter and shimmer variants) and deep learning–based embedding features from the speech data. Using these features, we trained several machine learning algorithms. We also applied model interpretation techniques such as Shapley additive explanations to ascertain the importance of each feature in determining the model’s output. Results We achieved an area under the curve of 0.753 for determining the presence of self-reported PD by modeling the standard acoustic features through the XGBoost—a gradient-boosted decision tree model. Further analysis revealed that the widely used mel-frequency cepstral coefficient features and a subset of previously validated dysphonia features designed for detecting PD from a verbal phonation task (pronouncing “ahh”) influence the model’s decision the most. Conclusions Our model performed equally well on data collected in a controlled laboratory environment and in the wild across different gender and age groups. Using this tool, we can collect data from almost anyone anywhere with an audio-enabled device and help the participants screen for PD remotely, contributing to equity and access in neurological care.

Analyzing wav2vec embedding in Parkinson’s disease speech: A study on cross-database classification and regression tasks

“…Speech and voice characteristics of individuals with PD exhibit variations influenced by age and gender [21]. Early-onset PD, occurring before the age of 50, introduces an additional layer of complexity in the understanding of these nuances [22].…”

“…The remote assessment of (patho)physiological parameters, encompassing variables such as body temperature, blood oxygenation, heart rate, movement, and speech, holds significant relevance in scenarios where direct contact is impractical or must be avoided for various reasons. The collection of speech data, accessible from virtually anyone with an audio-enabled device, presents an opportunity to remotely screen for PD, thereby promoting inclusivity and accessibility in neurological care [21]. In contemporary biomedical artificial intelligence (AI) systems, particularly multimodal ones, an abundance of distinctive features or signals is embedded within the dataset [53].…”

Natural language processing techniques for studying language in pathological ageing: A scoping review

“…Imre et al., 2019), depression (De Souza et al., 2021) and dysarthria (e.g., due to Parkinson's disease; cf. Rahman et al., 2021). Actually, such a cross‐disciplinary approach presents a promising answer to the clinical challenge of cognitive assessment by combining objectivity (and reproducibility) in the evaluation process with unintrusiveness, speed and low cost.…”

Assessment Tasks and Virtual Exergames for Remote Monitoring of Parkinson’s Disease: An Integrated Approach Based on Azure Kinect

“…Neurologists perform the motor examination during scheduled follow-up visits. However, a more frequent and quantitative assessment of motor tasks would be of great interest for better modulating therapies and design rehabilitation protocols tailored to actual needs and conditions, and to the presence of complications, such as daily fluctuations [ 32 , 33 , 34 ]. For example, quantitative and automatic assessment of motor tasks in the home environment could overcome the limitations of daily diaries [ 35 , 36 ], allowing objective, frequent, and reliable monitoring of motor conditions and more timely adjustment of treatments.…”