Detecting Parkinson’s Disease from an Online Speech-task: Observational Study (Preprint)

2021 ◽  
Author(s):  
Wasifur Rahman ◽  
Sangwu Lee ◽  
Md. Saiful Islam ◽  
Victor Nikhil Antony ◽  
Harshil Ratnu ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Age Groups ◽  
Medical Intervention ◽  
Machine Learning Algorithms ◽  
Acoustic Features ◽  
Mel Frequency Cepstral Coefficients ◽  
Tree Model ◽  
Speech Task ◽  
The Us

BACKGROUND Access to neurological care—especially for Parkinson's disease (PD)—is a rare privilege for millions of people worldwide, especially in developing countries. In 2013, there were just 1200 neurologists in India for a population of 1.3 billion; the average population per neurologist exceeds 3.3 million in Africa. On the other hand, 60,000 people are diagnosed with Parkinson's disease (PD) every year in the US 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 PD patients worldwide by 2040 is only part of the picture since more than 20% of PD patients remain undiagnosed. Timely diagnosis and frequent assessment are keys to ensure timely and appropriate medical intervention, improving the quality of life for a PD patient. OBJECTIVE In this paper, we envision 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 Parkinson’s disease (PD). METHODS We collected data from 726 unique participants (262 PD, 38% female; 464 non-PD, 65% female; average age: 61) – from all over the US and beyond. A small portion of the data (roughly 7%) was collected in a lab setting to compare quality. 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 (MFCC), jitter and shimmer variants) and deep learning-based features from the speech data. Using these features, we trained several machine learning algorithms. We also applied model interpretation techniques like SHAP (SHapley Additive exPlanations) to find out the importance of each feature in determining the model’s output. RESULTS We achieved 0.75 AUC (Area Under the Curve) performance on determining presence of self-reported Parkinson’s disease by modeling the standard acoustic features through the XGBoost – a gradient-boosted decision tree model. Further analysis reveals that the widely used MFCC features and a subset of previously validated dysphonia features designed for detecting Parkinson’s from verbal phonation task (pronouncing ‘ahh’) influence the model’s decision most. CONCLUSIONS Our model performed equally well on data collected in controlled lab environment as well as ‘in the wild’ across different gender and age groups. Using this tool, we can collect data from almost anyone anywhere with a video/audio enabled device, contributing to equity and access in neurological care.

Gradient Boosting for Parkinson’s Disease Diagnosis from Voice Recordings

2020 ◽  
Author(s):  
Ibrahim Karabayir ◽  
Samuel Goldman ◽  
Suguna Pappu ◽  
Oguz Akbilgic
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Acoustic Features ◽  
Non Invasive ◽  
Light Gradient

Abstract Background: Parkinson’s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings.Method: We used “Parkinson Dataset with Replicated Acoustic Features Data Set” from the UCI-Machine Learning repository. The dataset included 44 speech-test based acoustic features from patients with PD and controls. We analyzed the data using various machine learning algorithms including Light and Extreme Gradient Boosting, Random Forest, Support Vector Machines, K-nearest neighborhood, Least Absolute Shrinkage and Selection Operator Regression, as well as logistic regression. We also implemented a variable importance analysis to identify important variables classifying patients with PD. Results: The cohort included a total of 80 subjects: 40 patients with PD (55% men) and 40 controls (67.5% men). Disease duration was 5 years or less for all subjects, with a mean Unified Parkinson’s Disease Rating Scale (UPDRS) score of 19.6 (SD 8.1), and none were taking PD medication. The mean age for PD subjects and controls was 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our best-performing model used Light Gradient Boosting to provide an AUC of 0.951 with 95% confidence interval 0.946-0.955 in 4-fold cross validation using only seven acoustic features.Conclusions: Machine learning can accurately detect Parkinson’s disease using an inexpensive and non-invasive voice recording. Light Gradient Boosting outperformed other machine learning algorithms. Such approaches could be used to inexpensively screen large patient populations for Parkinson’s disease.

scholarly journals Gradient boosting for Parkinson’s disease diagnosis from voice recordings

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Ibrahim Karabayir ◽  
Samuel M. Goldman ◽  
Suguna Pappu ◽  
Oguz Akbilgic
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Acoustic Features ◽  
Non Invasive ◽  
Light Gradient

Abstract Background Parkinson’s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings. Method We used “Parkinson Dataset with Replicated Acoustic Features Data Set” from the UCI-Machine Learning repository. The dataset included 44 speech-test based acoustic features from patients with PD and controls. We analyzed the data using various machine learning algorithms including Light and Extreme Gradient Boosting, Random Forest, Support Vector Machines, K-nearest neighborhood, Least Absolute Shrinkage and Selection Operator Regression, as well as logistic regression. We also implemented a variable importance analysis to identify important variables classifying patients with PD. Results The cohort included a total of 80 subjects: 40 patients with PD (55% men) and 40 controls (67.5% men). Disease duration was 5 years or less for all subjects, with a mean Unified Parkinson’s Disease Rating Scale (UPDRS) score of 19.6 (SD 8.1), and none were taking PD medication. The mean age for PD subjects and controls was 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our best-performing model used Light Gradient Boosting to provide an AUC of 0.951 with 95% confidence interval 0.946–0.955 in 4-fold cross validation using only seven acoustic features. Conclusions Machine learning can accurately detect Parkinson’s disease using an inexpensive and non-invasive voice recording. Light Gradient Boosting outperformed other machine learning algorithms. Such approaches could be used to inexpensively screen large patient populations for Parkinson’s disease.

Extreme Gradient Boosting for Parkinson’s Disease Diagnosis from Voice Recordings

2020 ◽  
Author(s):  
Ibrahim Karabayir ◽  
Suguna Pappu ◽  
Samuel Goldman ◽  
Oguz Akbilgic
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Diagnosis ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Acoustic Features ◽  
Data Set ◽  
Non Invasive ◽  
Extreme Gradient Boosting

Abstract Background : Parkinson’s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings. Method : We used “Parkinson Dataset with Replicated Acoustic Features Data Set” from the UCI-Machine Learning repository. The dataset included 45 features including sex and 44 speech test based acoustic features from 40 patients with Parkinson’s disease and 40 controls. We analyzed the data using various machine learning algorithms including tree-based ensemble approaches such as random forest and extreme gradient boosting. We also implemented a variable importance analysis to identify important variables classifying patients with PD. Results : The cohort included total of 80 subjects; 40 patients with PD (55% men) and 40 controls (67.5% men). PD patients showed at least two of the three symptoms; resting tremor, bradykinesia, or rigidity. All patients were over 50 years old and the mean age for PD subjects and controls were 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our final model provided an AUC of 0.940 with 95% confidence interval 0.935-0.945in 4-folds cross validation using only six acoustic features including Delta3 (Run2), Delta0 (Run 3), MFCC4 (Run 2), Delta10 (Run 2/Run 3), MFCC10 (Run 2) and Jitter_Rap (Run 1/Run 2). Conclusions : Machine learning can accurately detect Parkinson’s disease using an inexpensive and non-invasive voice recording. Such technologies can be deployed into smartphones for screening of large patient populations for Parkinson’s disease.

scholarly journals Gradient Boosting for Parkinson’s Disease Diagnosis from Voice Recordings

2020 ◽  
Author(s):  
Ibrahim Karabayir ◽  
Samuel Goldman ◽  
Suguna Pappu ◽  
Oguz Akbilgic
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Acoustic Features ◽  
Non Invasive ◽  
Light Gradient

Abstract Background: Parkinson’s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings.Method: We used “Parkinson Dataset with Replicated Acoustic Features Data Set” from the UCI-Machine Learning repository. The dataset included 44 speech-test based acoustic features from patients with PD and controls. We analyzed the data using various machine learning algorithms including Light and Extreme Gradient Boosting, Random Forest, Support Vector Machines, K-nearest neighborhood, Least Absolute Shrinkage and Selection Operator Regression, as well as logistic regression. We also implemented a variable importance analysis to identify important variables classifying patients with PD. Results: The cohort included a total of 80 subjects: 40 patients with PD (55% men) and 40 controls (67.5% men). Disease duration was 5 years or less for all subjects, with a mean Unified Parkinson’s Disease Rating Scale (UPDRS) score of 19.6 (SD 8.1), and none were taking PD medication. The mean age for PD subjects and controls was 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our best-performing model used Light Gradient Boosting to provide an AUC of 0.951 with 95% confidence interval 0.946-0.955 in 4-fold cross validation using only seven acoustic features.Conclusions: Machine learning can accurately detect Parkinson’s disease using an inexpensive and non-invasive voice recording. Light Gradient Boosting outperformed other machine learning algorithms. Such approaches could be used to inexpensively screen large patient populations for Parkinson’s disease.

scholarly journals Weeding through the haze: a survey on cannabis use among people living with Parkinson’s disease in the US

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Megan P. Feeney ◽  
Danny Bega ◽  
Benzi M. Kluger ◽  
A. Jon Stoessl ◽  
Christiana M. Evers ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Scientific Evidence ◽  
Symptom Control ◽  
Cannabis Use ◽  
Symptom Improvement ◽  
Motor Symptoms ◽  
The Us ◽  
Alternative Means ◽  
Non Motor Symptoms

AbstractSymptomatic management of Parkinson’s disease (PD) is complex and many symptoms, especially non-motor symptoms, are not effectively addressed with current medications. In the US, cannabis has become more widely available for medical and recreational use, permitting those in the PD community to try alternative means of symptom control. However, little is known about the attitudes towards, and experiences with, cannabis use among those living with PD. To address this shortcoming, we distributed an anonymous survey to 7,607 people with PD in January 2020 and received 1339 responses (17.6%). 1064 complete responses were available for analysis. Respondents represented 49 states with a mean age of 71.2 years (±8.3) and mean PD duration of 7.4 years (±6.2). About a quarter of respondents (24.5%) reported cannabis use within the previous six months. Age and gender were found to be predictors of cannabis use in this sample (Age OR = 0.95, 95% CI 0.93 to 0.97; Male OR = 1.44, 95% CI 1.03 to 2.03). Users reported learning about cannabis use from the internet/news (30.5%) and friends or other people with PD (26.0%). Cannabis users were more likely to report insufficient control of their non-motor symptoms with prescription medications than non-users (p = 0.03). Cannabis was primarily used for PD (63.6%) and was most often used to treat nonmotor symptoms of anxiety (45.5%), pain (44.0%), and sleep disorders (44.0%). However, nearly a quarter of users (23.0%) also reported they had stopped cannabis use in the previous six months, primarily due to a lack of symptom improvement (35.5%). Three quarters of respondents (75.5%) did not use cannabis, primarily because there was a lack of scientific evidence supporting efficacy (59.9%). Our results suggest that the lack of formal guidance or research evidence about cannabis for PD may in part underlie inconsistencies in both use and reported effectiveness.

The Incidence of Parkinson's Disease: A Systematic Review and Meta-Analysis

2016 ◽  
Vol 46 (4) ◽  
pp. 292-300 ◽  
Author(s):  
Lauren Hirsch ◽  
Nathalie Jette ◽  
Alexandra Frolkis ◽  
Thomas Steeves ◽  
Tamara Pringsheim
Keyword(s):  
Systematic Review ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Meta Analysis ◽  
Age Groups ◽  
Significant Heterogeneity ◽  
International Studies ◽  
Significant Difference ◽  
And Gender

Background: Parkinson's disease (PD) is a common neurodegenerative disorder. Epidemiological studies on the incidence of PD are important to better understand the risk factors for PD and determine the condition's natural history. Objective: This systematic review and meta-analysis examine the incidence of PD and its variation by age and gender. Methods: We searched MEDLINE and EMBASE for epidemiologic studies of PD from 2001 to 2014, as a previously published systematic review included studies published until 2001. Data were analyzed separately for age group and gender, and meta-regression was used to determine whether a significant difference was present between groups. Results: Twenty-seven studies were included in the analysis. Meta-analysis of international studies showed rising incidence with age in both men and women. Significant heterogeneity was observed in the 80+ group, which may be explained by methodological differences between studies. While males had a higher incidence of PD in all age groups, this difference was only statistically significant for those in the age range 60-69 and 70-79 (p < 0.05). Conclusion: PD incidence generally increases with age, although it may stabilize in those who are 80+.

Learning acoustic features to detect Parkinson’s disease

2018 ◽  
Vol 318 ◽  
pp. 102-108 ◽  
Author(s):  
Kebin Wu ◽  
David Zhang ◽  
Guangming Lu ◽  
Zhenhua Guo
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Acoustic Features

AdaBoost for Parkinson's Disease Detection using Robust Scaler and SFS from Acoustic Features

2021 ◽  
Author(s):  
Kakunuri Venkata Ashok Reddy ◽  
Srujith Rao Ambati ◽  
Yennam Shiva Rithik Reddy ◽  
Agumamidi Nithish Reddy
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Disease Detection ◽  
Acoustic Features

Tremor Identification Using Machine Learning in Parkinson's Disease

2019 ◽  
pp. 128-151
Author(s):  
Angana Saikia ◽  
Vinayak Majhi ◽  
Masaraf Hussain ◽  
Sudip Paul ◽  
Amitava Datta
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Support Vector Machine ◽  
Parkinson's Disease ◽  
Discriminant Analysis ◽  
Learning Algorithms ◽  
The Body ◽  
Machine Learning Algorithms ◽  
Support Vector

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

Sign in / Sign up

Export Citation Format

Share Document