Comparing Ensemble-Based Machine Learning Classifiers Developed for Distinguishing Hypokinetic Dysarthria from Presbyphonia

Integrated Vocal Deviation Index (IVDI): A Machine Learning Model to Classifier of the General Grade of Vocal Deviation

OBJECTIVE

To develop a multiparametric index based on machine learning (ML) to predict and classify the overall degree of vocal deviation (GG).

METHOD

The sample consisted of 300 dysphonic and non-dysphonic participants of both sexes. Two speech tasks were sustained vowel [a] and connected speech (counting numbers from 1 to 10). Five speech-language pathologists performed the auditory-perceptual judgment (APJ) of the GG and the degrees of roughness (GR), breathiness (GB), instability (GI), and strain (GS). We extracted 47 acoustic measurements from these tasks. The APJ result and the acoustic measurements were used to develop the multiparametric index. We used mean absolute error, root mean square error, and coefficient of determination (R²) to select the best model of ML to predict GG and feature importance to select the best set of variables for the index. After classifying the GG between nondysphonic, mild, moderate, and severe, the final model was validated using accuracy, sensitivity, specificity, predictive values, likelihood ratios, F1-Score, and weighted kappa.

RESULTS

The gradient boost model showed the best performance among the ML models. Eight features were selected in the model, including four acoustic measures (jitterLoc, smoothed cepstral peak prominenc, mean harmonic-to-noise ratio (HNRmean), and correlation) and four APJ measures (GR, GB, GS, and GI). The final model correctly classified 93.75% of participants and obtained a weighted kappa index of 0.9374, demonstrating the model's excellent performance.

CONCLUSION

The Integrated Vocal Deviation Index includes four acoustic measures and four auditory-perceptual measures and showed excellent performance in classifying voices according to GG.

Acoustic Measures of Dysphonia in Amyotrophic Lateral Sclerosis

PURPOSE

Identifying efficacious measures to characterize dysphonia in complex neurodegenerative diseases is key to optimal assessment and intervention. This study evaluates the validity and sensitivity of acoustic features of phonatory disruption in amyotrophic lateral sclerosis (ALS).

METHOD

Forty-nine individuals with ALS (40-79 years old) were audio-recorded while producing a sustained vowel and continuous speech. Perturbation/noise-based (jitter, shimmer, and harmonics-to-noise ratio) and cepstral/spectral (cepstral peak prominence, low-high spectral ratio, and related features) acoustic measures were extracted. The criterion validity of each measure was assessed using correlations with perceptual voice ratings provided by three speech-language pathologists. Diagnostic accuracy of the acoustic features was evaluated using area-under-the-curve analysis.

RESULTS

Perturbation/noise-based and cepstral/spectral features extracted from /a/ were significantly correlated with listener ratings of roughness, breathiness, strain, and overall dysphonia. Fewer and smaller correlations between cepstral/spectral measures and perceptual ratings were observed for the continuous speech task, although post hoc analyses revealed stronger correlations in speakers with less perceptually impaired speech. Area-under-the-curve analyses revealed that multiple acoustic features, particularly from the sustained vowel task, adequately differentiated between individuals with ALS with and without perceptually dysphonic voices.

CONCLUSIONS

Our findings support using both perturbation/noise-based and cepstral/spectral measures of sustained /a/ to assess phonatory quality in ALS. Results from the continuous speech task suggest that multisubsystem involvement impacts cepstral/spectral analyses in complex motor speech disorders such as ALS. Further investigation of the validity and sensitivity of cepstral/spectral measures during continuous speech in ALS is warranted.

Intelligent speech technologies for transcription, disease diagnosis, and medical equipment interactive control in smart hospitals: A review

The growing and aging of the world population have driven the shortage of medical resources in recent years, especially during the COVID-19 pandemic. Fortunately, the rapid development of robotics and artificial intelligence technologies help to adapt to the challenges in the healthcare field. Among them, intelligent speech technology (IST) has served doctors and patients to improve the efficiency of medical behavior and alleviate the medical burden. However, problems like noise interference in complex medical scenarios and pronunciation differences between patients and healthy people hamper the broad application of IST in hospitals. In recent years, technologies such as machine learning have developed rapidly in intelligent speech recognition, which is expected to solve these problems. This paper first introduces IST's procedure and system architecture and analyzes its application in medical scenarios. Secondly, we review existing IST applications in smart hospitals in detail, including electronic medical documentation, disease diagnosis and evaluation, and human-medical equipment interaction. In addition, we elaborate on an application case of IST in the early recognition, diagnosis, rehabilitation training, evaluation, and daily care of stroke patients. Finally, we discuss IST's limitations, challenges, and future directions in the medical field. Furthermore, we propose a novel medical voice analysis system architecture that employs active hardware, active software, and human-computer interaction to realize intelligent and evolvable speech recognition. This comprehensive review and the proposed architecture offer directions for future studies on IST and its applications in smart hospitals.

Prediction of Parkinson’s Disease Depression Using LIME-Based Stacking Ensemble Model

Depression symptoms are comparable to Parkinson’s disease symptoms, including attention deficit, fatigue, and sleep disruption, as well as symptoms of dementia such as apathy. As a result, it is difficult for Parkinson’s disease caregivers to diagnose depression early. We examined a LIME-based stacking ensemble model to predict the depression of patients with Parkinson’s disease. This study used the epidemiologic data of Parkinson’s disease dementia patients (EPD) from the Korea Disease Control and Prevention Agency’s National Biobank, which included 526 patients’ information. We used Logistic Regression (LR) as the meta-model, and five base models, including LightGBM (LGBM), K-nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), and AdaBoost. After cleansing the data, the stacking ensemble model was trained using 261 participants’ data and 10 variables. According to the research, the best combination of the stacking ensemble model is ET + LGBM + RF + LR, a harmonious model. In order to achieve model prediction explainability, we also combined the stacking ensemble model with a LIME-based explainable model. This explainable stacking ensemble model can help identify the patients and start treatment on them early in a way that medical professionals can comprehend.