Smartphone Speech Testing for Symptom Assessment in Rapid Eye Movement Sleep Behavior Disorder and Parkinson’s Disease

Abstract

Speech impairment in Parkinson's Disease (PD) has been extensively studied. Our understanding of speech in people who are at an increased risk of developing PD is, however, rather limited. It is known that isolated Rapid Eye Movement (REM) sleep Behavior Disorder (RBD) is associated with a high risk of developing PD. The aim of this study is to investigate smartphone speech testing to: (1) distinguish participants with RBD from controls and PD, and (2) predict a range of self-or researcheradministered clinical scores that quantify participants' motor symptoms, cognition, daytime sleepiness, depression, and the overall state of health. The rationale of our analyses is to test an initial hypothesis that speech can be used to detect and quantify the symptoms associated with RBD and PD. We analyzed 4242 smartphone voice recordings collected in clinic and at home from 92 Controls, 112 RBD and 335 PD participants. We used acoustic signal analysis and machine learning, employing 337 features that quantify different properties of speech impairment. Using a leave-one-subject-out cross-validation scheme, we were able to distinguish RBD from controls (sensitivity 60.7%, specificity 69.6%) and RBD from PD participants (sensitivity 74.9%, specificity 73.2%), and predict clinical assessments with clinically useful accuracy. These promising findings warrant further investigation in using speech as a digital biomarker for PD and RBD to facilitate intervention in the early and prodromal stages of PD.

Assessing Parkinson’s Disease at Scale Using Telephone-Recorded Speech: Insights from the Parkinson’s Voice Initiative

“…As opposed to other types of speech signals that are often used in clinical assessments, such as running speech and reading aloud a linguistically rich pre-specified text e.g., the Grandfather Passage [20], the use of sustained phonations helps circumvent challenges associated with different accents and linguistic confounds [20]. For example, our previous work has shown that sustained phonations can provide high accuracy in differentiating PwP from controls [10], along with other interesting insights in the speech-PD literature, including replicating PD symptom severity and assisting PD rehabilitation [10,12,18,21]. We emphasize also that the methodology adopted in this study for processing sustained vowels had previously also been generalized to analyze different types of speech, e.g., voice fillers [42], and to provide useful insights more widely in different biomedical speech signal processing applications [43].…”

“…We have used three state-of-the-art statistical mapping algorithms: (1) Random Forests (RF) [34], (2) Support Vector Machines (SVM) [35], (3) Adaptive Boosting (AdaBoost) [36] to tackle the binary differentiation problem in the study. We chose these methods as they are commonly used off-the-shelf classifiers that have been shown to be accurate in diverse supervised learning problems and, in particular, in a similar context differentiating PwP from controls using voice [18,19,25]. For the RF we explored optimizing performance using Breiman's recommendation with half and twice the default recommended number of features over which to select features for each node, and explored findings using 500 trees and 1000 trees.…”

“…In the first step, we randomly selected 1500 samples from PwP and 1500 samples from controls to create a balanced binary classification dataset (n = 3000 samples) which we will use to train, explore, optimize, and validate the classifiers. To assess model validation for this balanced dataset we used a standard 10-fold cross-validation with a 100 iterations, following the standard methodology that we had previously used in similar applications in this field [10,12,18]. The aim is to use this first step to decide on the final model, by optimizing and setting any hyper-parameters so that it can be finalized and used externally in new datasets.…”

“…It is due to this reason, that the potential of capitalizing on acoustic analysis of speech signals to develop PD decision support tools has been pursued vigorously with considerable success over the last 10-15 years. Encouragingly, using voice, studies have proposed technologies based on acoustic analyses to: (1) differentiate PwP from controls [7][8][9][10], (2) monitor the symptom severity of PD [11][12][13][14], (3) assess voice rehabilitation in PD [15], (4) identify at-risk participants (i.e., those with isolated Rapid Eye Movement (REM) sleep behavior disorder as confirmed by a polysomnography test) [16], (4) identify participants with a higher genetic predisposition for developing PD (i.e., those with a mutation in the Leucine-Rich Repeat Kinase 2 (LRRK2) gene) [17], and (5) predict a range of clinical scores that quantify participants' motor symptoms, cognition, daytime sleepiness, depression, and overall state of health [18]. A limitation of these studies was, however, that they typically rely on using high-quality voice recordings for the analyses which are collected under carefully acoustically controlled conditions with high-end specialized equipment.…”

Parkinson’s Disease Detection Based on Running Speech Data From Phone Calls

“…Specifically, touchscreen typ-ing pattern analysis has been used for early detection of finemotor impairment [13], whereas accelerometer-based analysis was employed for tremor detection [14], expressing the effect of PD to upper-extremity motor function of PD patients. Use of speech recordings through smartphone devices of participants enrolled in conducted studies have been used on [25], [26], where authors used a feature-space that represents the key aspects of hypokinetic dysarthria in the early stages of PD, indicating that early screening is possible via acoustic segment analysis. The current work acts as an extension to the previous approaches by focusing on voice-related passive data collection captured during phone calls via the iPrognosis app.…”