Voice Impairment Research Articles

Robust language independent voice data driven Parkinson’s disease detection

Background and Objective:Parkinson’s Disease (PD) is a neurodegenerative movement disorder caused by the progressive loss of dopamine. Approximately 90% of PD patients experience voice impairments and this has been used as a precursor to develop diagnostic decision support systems for the early detection of the disease. Since speech data is heavily dependent on the language and the locality of the individual, an important requirement of such a diagnostic decision support system is the ability to classify PD irrespective of the linguistic demography of the speakers and generalize well to heterogeneous populations and external patient data. Methods:This study focuses on the development of a data-driven language independent PD classification model based on Variational Mode Decomposition (VMD). Sustained phonations in Spanish and Italian are decomposed into VMD modes and used along with a deep learning framework to establish cross-lingual validity. The performance of the proposed method is also assessed within the same dataset alongside assessing generalizability to a different dataset of the same language. Additionally, the possibility of gender bias and the robustness of the proposed method on realistic data is also evaluated. Results:The best results show that the proposed method has a cross-lingual accuracy between 65% and 80%. The cross-linguistic validity scores are higher than all values reported by studies using vowels, including models that have used transfer learning on the target language. The proposed method shows 90% to 95% accuracy when tested within the same dataset and has up to 63% generalizability on an independent dataset with realistic recording settings. It is seen that a consistent performance independent of the gender of the speaker is achieved using the proposed method of training the deep learning classifier with VMD modes. Conclusions:The proposed method of using VMD modes and a deep learning classifier has displayed consistent performance across all the tests, including multilingual and same linguistic demography in the data; and across varied recording conditions. The study highlights the importance of testing the generalizability and the effect of bias in the reported results from the oversight of training data choice and limited testing. The results from the study suggest that the proposed method can be used to develop a robust, language independent generalizable model to aid in the detection of PD from voice.

Validity and Reliability of the Arabic Version of the Glottal Function Index in Dysphonic Patients.

The Glottal Function Index (GFI) is a four-item self-administered survey suitable for the evaluation and treatment of patients with glottal dysfunction. To date, it has been translated into Lithuanian, Persian, and Hebrew. This study is intended to translate and cross-culturally adapt the GFI for use in Arabic-speaking patients with dysphonia. This work is a cross-sectional study involving the administration of the GFI to participants with dysphonia (cases) and patients without dysphonia (controls). The validation process included reliability and validity assessments. The GFI was translated using forward and backward translation methods from English into Arabic. The questionnaire's reliability was assessed using Cronbach's alpha and test-retest reliability (intraclass correlation coefficient, ICC). The Mann-Whitney test evaluated validity by comparing cases and controls. Finally, the Kruskal-Wallis test examined differences in the GFI across various pathologies. The GFI demonstrated favorable internal consistency (Cronbach's alpha=0.848) and excellent test-retest reliability (ICC=0.993). Significant differences in the A-GFI score between the cases and controls were also observed (P<0.001), supporting the instrument's validity. However, no statistically significant differences were found in A-GFI across different diagnoses (P=0.712). The A-GFI is a valid and reliable screening tool for clinicians to assess dysphonia and voice impairment in patients in Arabic-speaking countries. The tool is easy to administer in daily clinical practice given its brevity and self-administration.

A Deep Learning Technique to Clinch the Detection of Parkinson’s Disease using Speech and Voice Attributes

Among the neurodegenerative diseases Parkinson’s Disease ranks second only to Alzheimer’s disease. Though extensive research is carried out in this area there have been no biomarker suggested. At present the diagnosis and monitoring of the disease progression is possible only through clinical examination and function symptoms observation. Voice impairment has been identified as an early marker for Parkinson’s Disease and hence the research in this field is gaining popularity. Machine Learning algorithms have proved useful in analyzing the enormous data with high dimensionality. But this has not been successful in extricating features that will have a strong correlation in predicting the disease accurately. This calls for a more effective and powerful technique like Deep Learning that uses deep neural networks that can select the optimal features and can contribute in the identification of the disease. In this paper an initial step was made by designing an Artificial Neural Network model. This yielded a train and test accuracy more than ninety-nine percentage and seventy-five percentage respectively for classifying the disease but showed overfitting problem which resulted in a decrease in the performance. Hence, the Artificial Neural Network model was hyper-tuned to reduce this problem and there was a slight improvement in the performance. Two methods were employed for optimization – a regularization method early stop and another validation method called Stratified K -Fold Cross Validation. Among these the second approach showed better results by slightly reducing the overfitting issue and it yielded a train and test accuracy score of approximately ninety-nine percentage and ninety-seven percentage with K-fold as five and Stochastic Gradient Descent as the optimizer. Even though the results were promising it was unable to unravel the prime attributes that would eventually identify the disease.

Effects of deep brain stimulation of the subthalamic nucleus on patients with Parkinson's disease: a machine-learning voice analysis.

Deep brain stimulation of the subthalamic nucleus (STN-DBS) can exert relevant effects on the voice of patients with Parkinson's disease (PD). In this study, we used artificial intelligence to objectively analyze the voices of PD patients with STN-DBS. In a cross-sectional study, we enrolled 108 controls and 101 patients with PD. The cohort of PD was divided into two groups: the first group included 50 patients with STN-DBS, and the second group included 51 patients receiving the best medical treatment. The voices were clinically evaluated using the Unified Parkinson's Disease Rating Scale part-III subitem for voice (UPDRS-III-v). We recorded and then analyzed voices using specific machine-learning algorithms. The likelihood ratio (LR) was also calculated as an objective measure for clinical-instrumental correlations. Clinically, voice impairment was greater in STN-DBS patients than in those who received oral treatment. Using machine learning, we objectively and accurately distinguished between the voices of STN-DBS patients and those under oral treatments. We also found significant clinical-instrumental correlations since the greater the LRs, the higher the UPDRS-III-v scores. STN-DBS deteriorates speech in patients with PD, as objectively demonstrated by machine-learning voice analysis.

ORG-RGRU: An automated diagnosed model for multiple diseases by heuristically based optimized deep learning using speech/voice signal

Human ailments create an impact in altering the significant metabolism activities of the body irrespective of various parts. Dysarthric speech is commonly known as Parkinson's disease (PD), where most of people suffer from voice impairment. Moreover, the voice analysis could help the clinicians to detect the disease effectively. Since it affects with neurological activities, the existing models are though render better results, but it cannot be able to meet up the desired outcomes. While diagnosing the disease by the clinicians, the abnormality variations in the voice signal become complicated. Due to the occurrence of unwanted interpretations, it affects the quality of the speech/voice signal. In order to meet this prerequisite, a novel diagnosing method is proposed. The proposed model implements the three-stage classification framework termed as Optimized ResNet and GoogleNet and Radial basis function-Gated Recurrent Unit (ORG-RGRU). The signals are garnered and decomposed using Empirical Wavelet Transform (EWT). The decomposed signal is given to classification in three different ways. Firstly, the decomposed signal is fed into Short-Time Fourier transform (STFT) features that are given into ORG-RGRU, which yields one classified output. Secondly, the relevant features are retrieved by adopting Mel-Frequency Cepstral Coefficients (MFCC), Cepstral and Spectral features, principle speech features, and pitch features (zero frequency response filter). Then, the weighted features are obtained with the optimal weight by the Adaptive Controlling Parameters-based African Vultures Optimization Algorithm (ACP-AVOA). Thus, the optimal features are fed into the Optimized Radial basis function-Gated Recurrent Unit (ORGRU) to exhibit the second classified outcome. Thirdly, the extracted STFT features are given into ResNet and GoogleNet, where the deep features are attained that are given to ORGRU. In order to return the optimal value, the hyper parameters in ResNet, GoogleNet, RBF and GRU are tuned optimally by ACP-AVOA. The high ranking is taken for determining the final classified results. The validation takes place among the developed model and existing conventional approaches. The main finding of the developed model shows 95% and 91% regarding accuracy and Matthews Correlation Coefficient (MCC).

Voice Handicap Following Curative Therapy for Locally Advanced Head and Neck Cancer

Voice changes are a common late effect experienced by head and neck cancer (HNC) survivors, but most prior studies have focused primarily on patients with larynx tumors. The purpose of this study was to characterize voice handicap in a broader population of long term HNC survivors. We also sought to determine the sensitivity of a single question screener for voice handicap in this population. This study enrolled patients with locally advanced HNC (T3+ or N+) who received ≥60 Gy at a single academic institution and survived at least 2 years from the completion of radiation therapy (RT). Voice handicap was assessed using the more comprehensive and validated 10-question Voice Handicap Index (VHI-10). Clinically significant voice handicap was defined as a total VHI-10 score of >11. Patient reported hoarseness was assessed by the single question "Have you had problems with hoarseness?" from the EORTC QLQ-HN35 form. Descriptive statistics and univariate binomial logistic regression were used to identify factors associated with significant voice handicap. Missing data were not imputed and denominators were adjusted for each analysis. All analyses were performed using RStudio (PBC, Boston, MA). A total of 199 patients were enrolled in this study and included in the analysis; 182 (91%) completed the VHI-10 and 189 (95%) completed the EORTC QLQ-HN35. The median time from completion of RT to QoL assessment was 5.6 years (range: 1.7 - 28.9 years) and the median age was 65 years (range: 25 - 88 years). The primary tumor was most commonly within the oropharynx (51%) followed by larynx (13%) and oral cavity (11%). Surgery was performed in 64% and 63% systemic therapy. Clinically significant voice handicap was present in 34% of patients and the median VHI-10 score was 8 (range: 0 - 40). Primary tumors of the larynx (OR 7.18; 95% CI 2.52-23.8) and oral cavity (OR 3.29; 95% CI 1.21-9.35; p = 0.02) were associated with a higher odds of significant voice handicap than oropharynx tumors. Other factors associated with voice handicap were African American race (OR = 2.78 versus white race, 95% CI 1.13-7.14), female sex (OR 2.34; 95% CI 1.21-4.55), and T3+ tumor stage (OR = 3.53, 95% CI 1.48-9.19). The sensitivity and specificity of the single item hoarseness question from the EORTC QLQ-HN35 for predicting significant voice handicap ranged from 64.6% and 69.7% when a "A little bit" was considered a positive response to 24.6% and 98.2% when "Very much" was considered a positive response. Significant voice handicap was present in more than one-third of long term HNC survivors in this cohort and primary tumors of the larynx and oral cavity were associated with a higher odds of voice impairment. A single question about hoarseness was not sensitive for detecting significant voice impairment, potentially because voice quality is impacted by a range of factors besides hoarseness. Results of this study highlight the need to improve our understanding of how voice handicap impacts the QoL of HNC survivors.

A review of emergent intelligent systems for the detection of Parkinson's disease.

Parkinson's disease (PD) is a neurodegenerative disorder affecting people worldwide. The PD symptoms are divided into motor and non-motor symptoms. Detection of PD is very crucial and essential. Such challenges can be overcome by applying artificial intelligence to diagnose PD. Many studies have also proposed the implementation of computer-aided diagnosis for the detection of PD. This systematic review comprehensively analyzed all appropriate algorithms for detecting and assessing PD based on the literature from 2012 to 2023 which are conducted as per PRISMA model. This review focused on motor symptoms, namely handwriting dynamics, voice impairments and gait, multimodal features, and brain observation using single photon emission computed tomography, magnetic resonance and electroencephalogram signals. The significant challenges are critically analyzed, and appropriate recommendations are provided. The critical discussion of this review article can be helpful in today's PD community in such a way that it allows clinicians to provide proper treatment and timely medication.

Vocal Fatigue, Dysphonia Risk, and Associated Factors in Male Brazilian Evangelical Pastors

ObjectivesTo identify the presence of vocal fatigue and dysphonia risk in evangelical pastors and to verify associations of vocal fatigue with dysphonia risk and other factors. Study DesignCross-sectional observational study. MethodsNinety-two evangelical pastors, professionally active, answered an on-line questionnaire divided in three steps. The first step consisted of data for the characterization of the sample. In the second stage, participants answered the vocal fatigue index questionnaire (VFI). Finally, they answered to the Brazilian Dysphonia Screening tool. A descriptive analysis of the data was performed along with Spearman’s Correlation test between VFI factors and the three possible decision rules for the Brazilian Dysphonia Screening tool. A linear regression model was designed to verify predictive variables associated with the outcome “vocal fatigue”. ResultsNinety male individuals were included. The average sample was off the threshold scores of tiredness and voice impairment, physical discomfort, improvement of voice symptoms with rest, and the total score of VFI. The dysphonia risk was low and was weakly negatively correlated with the improvement of voice symptoms with rest. The linear regression indicated that the presence of a current vocal complaint increases about four points in the VFI. ConclusionEvangelical pastors present symptomatology of vocal fatigue and low risk for dysphonia. However, the greater the improvement of voice symptoms with rest, the lower the risk for dysphonia. Furthermore, the presence of a current vocal complaint is associated with increased symptoms of vocal fatigue.

CNN AND LSTM FOR THE CLASSIFICATION OF PARKINSON'S DISEASE BASED ON THE GTCC AND MFCC

Parkinson's disease is a recognizable clinical syndrome with a variety of causes and clinical presentations; it represents a rapidly growing neurodegenerative disorder. Since about 90 percent of Parkinson's disease sufferers have some form of early speech impairment, recent studies on tele diagnosis of Parkinson's disease have focused on the recognition of voice impairments from vowel phonations or the subjects' discourse. In this paper, we present a new approach for Parkinson's disease detection from speech sounds that are based on CNN and LSTM and uses two categories of characteristics Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) obtained from noise-removed speech signals with comparative EMD-DWT and DWT-EMD analysis. The proposed model is divided into three stages. In the first step, noise is removed from the signals using the EMD-DWT and DWT-EMD methods. In the second step, the GTCC and MFCC are extracted from the enhanced audio signals. The classification process is carried out in the third step by feeding these features into the LSTM and CNN models, which are designed to define sequential information from the extracted features. The experiments are performed using PC-GITA and Sakar datasets and 10-fold cross validation method, the highest classification accuracy for the Sakar dataset reached 100% for both EMD-DWT-GTCC-CNN and DWT-EMD-GTCC-CNN, and for the PC-GITA dataset, the accuracy is reached 100% for EMD-DWT-GTCC-CNN and 96.55% for DWT-EMD-GTCC-CNN. The results of this study indicate that the characteristics of GTCC are more appropriate and accurate for the assessment of PD than MFCC.

Dysphonia and Throat Clearing in Singers During the COVID-19 Pandemic in Brazil

The COVID-19 pandemic in Brazil affected the lives of singers, with negative impacts of the disease on the voice, such as dysphonia and throat clearing. This study aims to evaluate the presence of dysphonia and throat clearing in singers during the COVID-19 pandemic in Brazil. This is a cross-sectional analytical study with a sample of 154 singers from all over Brazil. Data collection was carried out online, by completing the questionnaire created by the researcher using Google Forms. The following were considered the outcome variables: voice impairment and throat clearing. The bivariate analysis was performed to test the relationship between COVID-19 infection and voice impairment, COVID-19 infection and throat clearing, COVID-19 infection and laryngeal complaints (voice impairment and throat clearing). In this study, the mean age of the singers was 35.8 (Standard deviation=±10.2 years) and 59.2% were female. Most of them worked as professional singers (81.1%) and had more than 10 years of professional experience (57.4%), mainly singing pop music (85.4%). A total of 62% reported vocal alterations during the COVID-19 infection and 53% had vocal alterations after the infection, with 44.0% reporting the onset of throat clearing after the infection. There was a significant association between COVID-19 infection and having voice impairment (P=0.03; prevalence ratio - PR: 2.33; CI: 1.04-5.46). An association was observed between the onset of throat clearing and the occurrence of COVID-19 infection (P=0.001; PR: 9.13; CI: 2.47-64.42). The results indicated that there is an association between COVID-19 infection and complaints of dysphonia and throat clearing in Brazilian singers. This study demonstrates the importance of guidance to singers infected with COVID-19 by health voice processionals.

An Exploration of Vocal Training Methods for Voice Repair in Children with Cleft Palate and Their Application in Education

Cleft palate is a common congenital oral craniofacial malformation, and patients are often accompanied by speech and voice impairment. Vocal training is an effective treatment method that can help patients with cleft palate repair their speech defects, enhance self-confidence, and promote social interaction. In schools, children with cleft palate also have special educational needs. Therefore, combining vocal training with education is important for the rehabilitation and education of children with cleft palate. This paper reviews the basic principles and specific methods of vocal training, as well as its application in cleft palate patients and its importance in education. Also, this paper presents some practical examples of combining vocal training with education. Taken together, the combination of vocal training and education can better meet the educational needs of cleft palate patients and promote their rehabilitation and social adaptation.

Biopsychosocial needs and problems among preschool children with speech impairment

Background Speech impairment means a communication disorder, such as stuttering, impaired articulation, language impairment, or a voice impairment, that adversely affects a child’s educational performance. Aim The current study aimed to assess the biopsychosocial needs and problems of preschool children with speech impairment. Design A descriptive research design was utilized in the current study. Setting The current study was done in outpatient phonetic clinic at El-Menofeya University Hospital. Sample A purposive sample of 200 preschool children with determined inclusion criteria. Tools for data collection Demographic and medical history questionnaire for children with speech impairment, biopsychosocial needs scale for preschool children with speech impairment and biopsychosocial problems scale for preschool children with speech impairment. Results The current study showed that 69% of the selected children with speech impairment were aged from 4 to 5 years with a mean of 4.2±1.0. Regarding Sex, 54% of selected children were males. While 47% and 46% of their fathers and mothers had diploma levels respectively. Regarding physical needs, 58% of them usually ate healthy and preferable foods. Regarding psychological needs, 71% of the selected children were sometimes satisfied with love and compassion and had family support to overcome fear. Related to social needs, 66% of the selected children were encouraged to participate in group activities. Concerning biopsychosocial problems, 63% of them sometimes had a lack of appetite. Similarly, 48% and 70% had aggressive reactions and fears from others, except for family members, and did not interact with peers easily. Conclusion The study concluded that 86%, 82% and 86% of selected children were satisfied with their physical, psychological, and social needs, respectively, while 92.5% of the selected children needed medical and nursing intervention related to biopsychosocial problems and 7.5% of them needed to modify the unacceptable behaviors related to biopsychosocial problems. Recommendation The study recommended the need for further researches on a large scale to assess biopsychosocial needs and early detection of biopsychosocial problems among preschool-aged children with speech impairment in different community settings. Furthermore, applying biopsychosocial assessment for needs among preschool age children with speech impairment in all phonetics outpatients’ clinics and speech centers.

Classification of Parkinson's disease from smartphone recording data using time-frequency analysis and convolutional neural network.

Parkinson's disease (PD) is a long-term neurodegenerative disease of the central nervous system. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affects most patients is voice impairment. Voice samples are non-invasive data that can be collected remotely for diagnosis and disease progression monitoring. In this study, we analyzed voice recording data from a smartphone as a possible medical self-diagnosis tool by using only one-second voice recording. The data from one of the largest mobile PD studies, the mPower study, was used. A total of 29,798 ten-second voice recordings on smartphone from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by participants saying /aa/ for ten seconds into an iPhone microphone. A dataset comprising 385,143 short one-second audio samples was generated from the original ten-second voice recordings. The samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples. Classification accuracies of the proposed method with LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively. We achieve a respectable classification performance using a generalized approach on a dataset with a large number of samples. The result emphasizes that an analysis based on one-second clip recorded on a smartphone could be a promising non-invasive and remotely available PD biomarker.

A Comparative Study of Early Detection of Parkinsons Disease Using Machine Learning Techniques

Abstract: For many years, Parkinson's disease (PD) has been viewed as a tragedy for humanity. A lot of research is being done on how to detect it using an automated method. This necessitates the use of a machine learning model for PD early diagnosis. Studying the currently employed computational intelligence strategies in the field of research used for PD detection is a crucial requirement for developing a full proof model. Numerous models now in use either concentrate on a single modality or only briefly consider several modalities. This prompted us to conduct a comparative literature review of four primary PD early detection techniques, specifically tremor at rest, bradykinesia, stiffness, and voice impairment. Modern Machine learning methods including K-nearest neighbours, Decision Tree, Support Vector Machine, and Logistic Regression (KNN), Stochastic Gradient Descent (SGD), and Gaussian Naive Bayes (GNB) are applied in these modalities with the corresponding datasets. Additionally, ensemble methods like Hard Voting (HV), Adaptive Boosting (AB), and Random Forest Classifier (RF) are used.

Muscle Tension Dysphonia: A Sequeale of Chemoradiotherapy in Patients of Head and Neck Cancer.

It's very important to demarcate that voice is the production of sound by the larynx while speech is articulation of the produced sound by tongue movements, soft palate and the lips. Mucositis, dysphagia, change in speech and voice are the common sequelae of Radiotherapy (RT) alone or in combination with chemotherapy (CRT) which is commonly used in the treatment of head and neck cancer (HNC). The aim of this study was to investigate the patient-reported voice impairment among non laryngeal head and neck cancer survivors who were treated with curative RT/CRT with or without surgery. This tertiary institutional assessor blinded study consists of a study cohort of 128 patients who after of completion of treatment for HNC reported to the laryngology clinic for voice complaints and throat discomfort. The assessment included laryngeal endoscopic and stroboscopic imaging, acoustics assessment and VHI (Vocal handicap index). This study cohort consisted of 89.8% males and 11.2% females. There was hyperadduction and strain of ventricular bands in almost all the cases. There was hyperactivity and compression of both true and false cords in 80.5% of the cases. DSI impairment level showed significant association with gender, VHI, GRBAS score and RT/CRT and it did not show significant association with smoking and surgery, while VHI showed significant association with DSI and RT/CRT and it did not show significant association with gender, smoking and surgery. Muscle tension is a very common effect of RT/RCT and dysphonia can be easily associated with it. Future research needs to focus on specific voice treatment regimens in HNC treated with RT/CRT to improve the quality of life of these patients.

Диагностические критерии поражения гортани при манифестации ревматоидного артрита

Introduction. Rheumatoid arthritis is a systemic autoimmune inflammation of connective tissue involving the cartilage of the larynx. In this case, pathology of the larynx may be the only manifestation of this disease. The discomfort, foreign body sensation, and pain in the larynx noted by patients in the early stages of the disease are rarely associated by doctors with the manifestation of rheumatoid arthritis. In later stages, symptoms may be masked as comorbid pathology of the heart or upper respiratory tract. An analysis of the available literature revealed insufficient knowledge of issues related to the early diagnosis of inflammation of the larynx in autoimmune diseases, in particular, rheumatoid arthritis. Objective. To conduct a literature review to identify early symptoms of laryngeal damage in patients with the manifestation of rheumatoid arthritis. Materials and methods. Over the past 10 years, a literature review has been conducted in public databases using the following queries: laryngeal injury in autoimmune rheumatic diseases, dysphonia, voice impairment in rheumatoid arthritis, rheumatoid arthritis, and laryngeal joint injury. Data from literature sources, the authors of which made a significant contribution to the development of otorhinolaryngology and rheumatology, were included. Results. Summary data from the literature review are presented on the frequency of complaints made by patients, verification of characteristic symptoms, and their severity depending on the level of damage to the larynx. An early symptom of the manifestation of rheumatoid arthritis is dysphonia, which was observed with inflammation of the cricoarytenoid joints, arytenoid cartilage, and vocal fold nodules. A checklist of early symptoms of laryngeal injury has been compiled for routing patients with rheumatoid arthritis. Conclusion. Laryngeal involvement in rheumatoid arthritis is a fairly common symptom. Dysphonia as an early symptom is observed with polymorphism of inflammatory changes and manifests itself from single nodules to total fixation of the joints of the laryngeal cartilage. In diagnosing the manifestations of rheumatoid arthritis, an interdisciplinary approach of specialists is required.

Automatic Assessment of Parkinson's Disease Using Speech Representations of Phonation and Articulation

Speech from people with Parkinson's disease (PD) are likely to be degraded on phonation, articulation, and prosody. Motivated to describe articulation deficits comprehensively, we investigated 1) the universal phonological features that model articulation manner and place, also known as speech attributes, and 2) glottal features capturing phonation characteristics. These were further supplemented by, and compared with, prosodic features using a popular compact feature set and standard MFCC. Temporal characteristics of these features were modeled by convolutional neural networks. Besides the features, we were also interested in the speech tasks for collecting data for automatic PD speech assessment, like sustained vowels, text reading, and spontaneous monologue. For this, we utilized a recently collected Finnish PD corpus (PDSTU) as well as a Spanish database (PC-GITA). The experiments were formulated as regression problems against expert ratings of PD-related symptoms, including ratings of speech intelligibility, voice impairment, overall severity of communication disorder on PDSTU, as well as on the Unified Parkinson's Disease Rating Scale (UPDRS) on PC-GITA. The experimental results show: 1) the speech attribute features can well indicate the severity of pathologies in parkinsonian speech; 2) combining phonation features with articulatory features improves the PD assessment performance, but requires high-quality recordings to be applicable; 3) read speech leads to more accurate automatic ratings than the use of sustained vowels, but not if the amount of speech is limited to correspond to the sustained vowels in duration; and 4) jointly using data from several speech tasks can further improve the automatic PD assessment performance.

A new Parkinson detection system based on evolutionary fast learning networks and voice measurements

Parkinson's disease (PD) is becoming the second most neurological syndrome of the central nervous system after Alzheimer's disease. It causes diverse symptoms which include bradykinesia (slowness of movement), voice impairments, rigidity, tremor, and poor balance. PD recognition system based on voice has founded a non-invasive alternative, but involves rather complex measurements or variables. Therefore an attention is required toward new approaches for better forecasting accuracy. In this paper, an optimal fast learning network (FLN) based on genetic algorithm (GA) was established as PD diagnosis system. FLN is a double-parallel feed-forward neural network structure, and based on GA for feature reduction and hyperparameter optimisation of the FLN, it was used as a predictive model. Finally, the conducted experiments on the Parkinson data of voice recordings over ten fold cross-validation show that proposed system is less complex and also achieved better average classification results with an accuracy of 97.47%. At the same time, it is effective in automatic identification of important vocal features. Moreover, the highest average degree of improved accuracy was (2.1%) compared with other familiar wrappers including support vector machine and K-nearest neighbours in the similar conditions.

Laryngeal contact granuloma after radiotherapy in patients with nasopharyngeal carcinoma: a case series.

Laryngeal contact granuloma (LCG) is a benign hypertrophic lesion and phonatory injury after abnormal vocal behavior is regarded as its major etiology. Patients receiving radiation for non-laryngeal head and neck tumors are troubled by persistent voice impairment. The occurrence of LCG after radiotherapy for nasopharyngeal carcinoma (NPC) in our practice has implored us to re-exam their underlying etiology. We hypothesize that a proportion of LCG results from voice change caused by non-laryngeal head and neck cancer radiotherapy and firstly describe a distinct LCG population originated after radiotherapy for NPC with respect to the clinical profile, presentation, prognosis and response to treatment of patients. We retrospectively reviewed the laryngoscopic examination and tumor study findings to elucidate the common clinical features of patients who presented with LCG after radiotherapy for NPC. All patients were regularly monitored with telescopic examination until lesions disappeared. Data on age, sex, clinical presentation, telescopic findings, management, latency time of lesion formation, remission time and clinical outcome were reviewed. The medical review identified 27 cases of LCG secondary to radiotherapy for NPC. All lesions had been diagnosed during routine endoscopy following radiation. The interval between radiation onset and endoscopic diagnosis was 3.77 months (range, 0.67-11 months). 20 cases were resolved through simple observation, 4 cases were resolved with the administration of proton pump inhibitors (PPIs), and 3 cases with a poor response to PPI therapy required subsequent surgical resection. The mean remission time in the observation and PPI groups was 4.42 months (range, 0.73-18.9 months) and 5.78 months (range, 2.17-14.63 months), respectively. All patients recovered completely and none experienced recurrence during a mean follow-up of 32.44 months (range, 5.6-71.67 months). Iatrogenic granulomas of vocal process are presenting after radiation for non-laryngeal head and neck cancers. In contrast with spontaneous granulomas, these granulomas can be cured at high remission rates and low recurrence trend without specific intervention. Thus, simple observation may be sufficient for radiation-induced LCG.

Investigating the Impact of Voice Impairment on Quality of Life in Stroke Patients: The Voice Handicap Index (VHI) Questionnaire Study.

The Voice Handicap Index (VHI) is a patient-centered evaluation tool specifically designed for assessing voice-related quality of life. Although the VHI has been extensively used in patients with voice disorders, its applicability in stroke patients has not been fully established. This prospective cross-sectional study aimed to investigate the feasibility of using the VHI questionnaire in identifying stroke patients with voice problems. The study included a cohort of acute to subacute first-ever stroke patients (n = 48), with or without voice problems, as well as other non-stroke patients (n = 31) who agreed to complete the VHI questionnaire. Stroke patients with self-reported voice problems demonstrated significantly higher VHI scores and poorer life quality scores compared to the control groups. These patients also had lower Mini-Mental State Examination (MMSE), Modified Barthel Index (MBI), and Euro-QoL-5D-5L (EQ-5D-5L) scores. Spearman correlation analysis revealed an inverse association between VHI scores and EQ-5D-5L (rho = -0.77, p < 0.001), Korean Mann Assessment of Swallowing Ability (rho = -0.51, p < 0.001), and other functional parameters, including the National Institutes of Health Stroke Scale, MMSE, and MBI scores. Multiple regression analysis indicated that the VHI score was the biggest contributing factor to EQ scores. This is the first study to demonstrate that stroke patients with voice problems may experience reduced quality of life, even after controlling for other confounding factors such as dysphagia or neurological deficits. Future studies are needed whether addressing these issues by implementing the VHI may facilitate the improvement of patients' quality of life.