Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies

Hosseini-Kivanani, Nina; Vásquez-Correa, Juan Camilo; Stede, Manfred; Nöth, Elmar

doi:10.18653/v1/p19-2010

Cited by 11 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech signals are usually considered as one of the main methods to diagnose Parkinson's disease. In [5] authors performed experimentation on speech signal recordings of three languages identifying speech pronunciation problems in it. It is observed that speech pronunciation like vowels, sentences, words are affected by this disease.…”

Section: Introductionmentioning

confidence: 99%

A Spectrogram-Based Deep Feature Assisted Computer-Aided Diagnostic System for Parkinson’s Disease

et al. 2020

View full text Add to dashboard Cite

Parkinson's disease is a neural degenerative disease. It slowly progresses from mild to severe stage, resulting in the degeneration of dopamine cells of neurons. Due to the deficiency of dopamine cells in the brain, it leads to a motor (tremor, slowness, impaired posture) and non-motor (speech, olfactory) defects in the body. Early detection of Parkinson's disease is a difficult chore as the symptoms of disease appear overtime. However, different diagnostic systems have contributed towards disease detection by considering gait, tremor and speech characteristics. Recent work has shown that speech impairments can be considered as a possible predictor for Parkinson's disease classification and remains an open research area. The speech signals show major differences and variations for Parkinson patients as compared to normal human beings. Therefore, variation in speech should be modeled using acoustic features to identify these variations. In this research, we propose three methods-the first method employs a transfer learning-based approach using spectrograms of speech recordings, the second method evaluates deep features extracted from speech spectrograms using machine learning classifiers and the third method evaluates simple acoustic feature of recordings using machine learning classifiers. The proposed frameworks are evaluated on a Spanish dataset pc-Gita. The results show that the second framework shows promising results with deep features. The highest 99.7% accuracy on vowel \o\ and read text is observed using a multilayer perceptron. Whereas 99.1% accuracy observed on vowel \i\ deep features using random forest. The deep feature-based method performs better as compared to simple acoustic features and transfer learning approaches. The proposed methodology outperforms the existing techniques on the pc-Gita dataset for Parkinson's disease detection.

show abstract

Section: Introductionmentioning

confidence: 99%

A Spectrogram-Based Deep Feature Assisted Computer-Aided Diagnostic System for Parkinson’s Disease

et al. 2020

View full text Add to dashboard Cite

show abstract

“…While motor tests such as tremor, gait and finger tapping are applicable regardless of the individual’s language, in the case of speech tests, the subject may be unable to understand the test or complete it successfully due to challenges with pronunciation, which may influence the test results and their interpretation ( 133 ). To overcome this, the voice tests used for Parkinson’s disease risk survey digital platform implemented in Thailand comprise newly developed speech tests that use sustained vowels (making a loud “Aah” sound for 10 s to assess phonation) and speaking sentences in Thai language (to assess prosody and articulation), thereby enhancing its relevance for Thai native speakers.…”

Section: Methods and Analysismentioning

confidence: 99%

The rise of Parkinson’s disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and “eat, move, sleep” lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand

Bhidayasiri,

Sringean,

Phumphid

et al. 2024

Front. Neurol.

View full text Add to dashboard Cite

The rising prevalence of Parkinson’s disease (PD) globally presents a significant public health challenge for national healthcare systems, particularly in low-to-middle income countries, such as Thailand, which may have insufficient resources to meet these escalating healthcare needs. There are also many undiagnosed cases of early-stage PD, a period when therapeutic interventions would have the most value and least cost. The traditional “passive” approach, whereby clinicians wait for patients with symptomatic PD to seek treatment, is inadequate. Proactive, early identification of PD will allow timely therapeutic interventions, and digital health technologies can be scaled up in the identification and early diagnosis of cases. The Parkinson’s disease risk survey (TCTR20231025005) aims to evaluate a digital population screening platform to identify undiagnosed PD cases in the Thai population. Recognizing the long prodromal phase of PD, the target demographic for screening is people aged ≥ 40 years, approximately 20 years before the usual emergence of motor symptoms. Thailand has a highly rated healthcare system with an established universal healthcare program for citizens, making it ideal for deploying a national screening program using digital technology. Designed by a multidisciplinary group of PD experts, the digital platform comprises a 20-item questionnaire about PD symptoms along with objective tests of eight digital markers: voice vowel, voice sentences, resting and postural tremor, alternate finger tapping, a “pinch-to-size” test, gait and balance, with performance recorded using a mobile application and smartphone’s sensors. Machine learning tools use the collected data to identify subjects at risk of developing, or with early signs of, PD. This article describes the selection and validation of questionnaire items and digital markers, with results showing the chosen parameters and data analysis methods to be robust, reliable, and reproducible. This digital platform could serve as a model for similar screening strategies for other non-communicable diseases in Thailand.

show abstract

“…With the constant disease progression, it turns to be another condition known as dementia. When an individual is influenced by PD possess risk of two-six times towards dementia when compared to other population [4].…”

Section: Introductionmentioning

confidence: 99%

Design of a Predictor Model for Feature Selection using Machine Learning Approaches

P. Pradeep

2024

jes

View full text Add to dashboard Cite

Parkinson’s disease is a neural degenerative disease where patients’ faces various critical neurological disorders. Thus, the earlier prediction of PD helps to enhance the patients’ life. The prediction of PD in earlier stage is complex and it consumes huge time. Therefore, effectual and appropriate prediction of PD is measured to a challenging factor for the health care experts and practitioners. To deal with this issue and to accurately predict the PD in earlier stage, this work concentrates on machine learning approaches for designing a predictor system. For developing the anticipated model, L1-norm based Genetic algorithm (L1-GA) is applied for predicting PD in the earlier stage. This L1-GA is utilized for selecting the influencing features for accurate prediction. This L1-GA produces newer feature subset from UCI Machine Learning (ML) dataset for PD for measuring feature weights. For validation , this work considers k-fold cross validation (CV) is used. Also, metrics like accuracy, error rate and execution time are evaluated. The inputs are taken from The PD dataset which is available online for preceding the feature selection process. The optimal accuracy attained with these newly selected sub-sets are considered for further computation. The simulation is performed in Python environment and the experimental findings determine that this study recommends that L1-GA provides better contribution towards PD feature selection and to predict PD in earlier stage. In recent times, Clinical Decision Support System (CDSS) plays an essential role for assisting PD recognition. As well, the anticipated model lays a bridge to fill the gap encountered in feature selection using the available data. The anticipated model gives better trade-off in contrast to prevailing approaches.

show abstract

Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies

Cited by 11 publications

References 28 publications

A Spectrogram-Based Deep Feature Assisted Computer-Aided Diagnostic System for Parkinson’s Disease

A Spectrogram-Based Deep Feature Assisted Computer-Aided Diagnostic System for Parkinson’s Disease

The rise of Parkinson’s disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and “eat, move, sleep” lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand

Design of a Predictor Model for Feature Selection using Machine Learning Approaches

Contact Info

Product

Resources

About