Deep learning in automatic detection of dysphonia: Comparing acoustic features and developing a generalizable framework

Reliability and Validity of GRBASzero in Clinical Environments

PURPOSE

This study aimed to evaluate the reliability and validity of GRBASzero in a real clinical setting.

METHODS

The reliability and validity of GRBASzero were assessed using two independent datasets. Dataset 1 included 283 outpatients who underwent both GRBASzero assessment and human expert evaluation. Dataset 2 from the Perceptual Voice Qualities Database comprised 287 voice samples that underwent evaluation by GRBASzero and were subsequently compared with GRBAS (Grade, Roughness, Breathiness, Asthenicity, Strain) ratings provided by human experts. The reliability of GRBASzero was assessed using Fleiss Kappa, while the validity of GRBASzero was examined using the intraclass correlation coefficient.

RESULTS

In dataset 1, the test-retest reliability of GRBASzero was poor, with the consistency of features A and S approaching random allocation. Consistency analysis with human experts showed a poor agreement for all features except for B. In dataset 2, there was also a poor agreement between GRBASzero and human experts.

CONCLUSION

The reliability and validity of GRBASzero in a real clinical environment are poor and do not meet the requirements for clinical testing, indicating the need for further optimization and improvement.

The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic Review

OBJECTIVE

To summarize the use of deep learning in the detection of voice disorders using acoustic and laryngoscopic input, compare specific neural networks in terms of accuracy, and assess their effectiveness compared to expert clinical visual examination.

DATA SOURCES

Embase, MEDLINE, and Cochrane Central.

REVIEW METHODS

Databases were screened through November 11, 2023 for relevant studies. The inclusion criteria required studies to utilize a specified deep learning method, use laryngoscopy or acoustic input, and measure accuracy of binary classification between healthy patients and those with voice disorders.

RESULTS

Thirty-four studies met the inclusion criteria, with 18 focusing on voice analysis, 15 on imaging analysis, and 1 both. Across the 18 acoustic studies, 21 programs were used for identification of organic and functional voice disorders. These technologies included 10 convolutional neural networks (CNNs), 6 multilayer perceptrons (MLPs), and 5 other neural networks. The binary classification systems yielded a mean accuracy of 89.0% overall, including 93.7% for MLP programs and 84.5% for CNNs. Among the 15 imaging analysis studies, a total of 23 programs were utilized, resulting in a mean accuracy of 91.3%. Specifically, the twenty CNNs achieved a mean accuracy of 92.6% compared to 83.0% for the 3 MLPs.

CONCLUSION

Deep learning models were shown to be highly accurate in the detection of voice pathology, with CNNs most effective for assessing laryngoscopy images and MLPs most effective for assessing acoustic input. While deep learning methods outperformed expert clinical exam in limited comparisons, further studies integrating external validation are necessary.

A multi-stage transfer learning strategy for diagnosing a class of rare laryngeal movement disorders

BACKGROUND

It remains hard to directly apply deep learning-based methods to assist diagnosing essential tremor of voice (ETV) and abductor and adductor spasmodic dysphonia (ABSD and ADSD). One of the main challenges is that, as a class of rare laryngeal movement disorders (LMDs), there are limited available databases to be investigated. Another worthy explored research question is which above sub-disorder benefits most from diagnosis based on sustained phonations. The question is from the fact that sustained phonations can help detect pathological voice from healthy voice.

METHOD

A transfer learning strategy is developed for LMD diagnosis with limited data, which consists of three fundamental parts. (1) An extra vocally healthy database from the International Dialects of English Archive (IDEA) is employed to pre-train a convolutional autoencoder. (2) The transferred proportion of the pre-trained encoder is explored. And its impact on LMD diagnosis is also evaluated, yielding a two-stage transfer model. (3) A third stage is designed following the initial two stages to embed information of pathological sustained phonation into the model. This stage verifies the different effects of applying sustained phonation on diagnosing the three sub-disorders, and helps boost the final diagnostic performance.

RESULTS

The analysis in this study is based on clinician-labeled LMD data obtained from the Vanderbilt University Medical Center (VUMC). We find that diagnosing ETV shows sensitivity to sustained phonation within the current database. Meanwhile, the results show that the proposed multi-stage transfer learning strategy can produce (1) accuracy of 65.3% on classifying normal and other three sub-disorders all at once, (2) accuracy of 85.3% in differentiating normal, ABSD, and ETV, and (3) accuracy of 77.7% for normal, ADSD and ETV. These findings demonstrate the effectiveness of the proposed approach.