Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech

Estimating the severity of obstructive sleep apnea during wakefulness using speech: A review

Obstructive sleep apnea (OSA) is a chronic breathing disorder during sleep that affects 10-30% of adults in North America. The gold standard for diagnosing OSA is polysomnography (PSG). However, PSG has several drawbacks, for example, it is a cumbersome and expensive procedure, which can be quite inconvenient for patients. Additionally, patients often have to endure long waitlists before they can undergo PSG. As a result, other alternatives for screening OSA have gained attention. Speech, as an accessible modality, is generated by variations in the pharyngeal airway, vocal tract, and soft tissues in the pharynx, which shares similar anatomical structures that contribute to OSA. Consequently, in this study, we aim to provide a comprehensive review of the existing research on the use of speech for estimating the severity of OSA. In this regard, a total of 851 papers were initially identified from the PubMed database using a specified set of keywords defined by population, intervention, comparison and outcome (PICO) criteria, along with a concatenated graph of the 5 most cited papers in the field extracted from ConnectedPapers platform. Following a rigorous filtering process that considered the preferred reporting items for systematic reviews and meta-analyses (PRISMA) approach, 32 papers were ultimately included in this review. Among these, 28 papers primarily focused on developing methodology, while the remaining 4 papers delved into the clinical perspective of the association between OSA and speech. In the next step, we investigate the physiological similarities between OSA and speech. Subsequently, we highlight the features extracted from speech, the employed feature selection techniques, and the details of the developed models to predict OSA severity. By thoroughly discussing the current findings and limitations of studies in the field, we provide valuable insights into the gaps that need to be addressed in future research directions.

What is the Effect of CPAP Treatment With Humidifier on Vocal Quality?

OBJECTIVE

Evaluate vocal quality in patients with OSA before and after continuous use of CPAP with a humidifier using subjective patient perception and clinical assessment. The hypothesis was that CPAP treatment with a humidifier would benefit voice quality.

STUDY DESIGN

Randomized, sham-controlled, blinded clinical trial.

METHODS

Forty-three natal males with obstructive sleep apnea for whom CPAP treatment was recommended following polysomnography were randomized into two therapy groups: CPAP and Sham-CPAP. Participants completed questionnaires on voice use, a voice self-assessment with the ten-item vocal handicap index (VHI-10), and complementary questionnaires: the Epworth sleepiness scale (ESS), Pittsburgh sleep quality index (PSQI), reflux symptoms index (LPRSI) and oral dryness visual analog scale (DRY). Their voices were recorded at three different times: before CPAP therapy, and after 3 and 6 months of continuous CPAP use. The acoustic voice quality index (AVQI), and an auditory-perceptual judgment (APJ) were also applied before and after the CPAP and Sham treatments.

RESULTS

After 6 months of treatment, the CPAP group presented improvements in their sleep patterns; however, no statistically significant differences were observed between the groups in respect of the results of the voice-related questionnaires, the AVQI values, and the APJ of the voice quality. All of the participants had some degree of vocal deviation at baseline.

CONCLUSIONS

CPAP therapy with a humidifier did not improve vocal quality as evaluated by the clinician or patient self-assessment. However, it did not have any significant negative effects on voice quality, so can be considered safe to use in male OSA patients.

Selection of OSA-specific pronunciations and assessment of disease severity assisted by machine learning

STUDY OBJECTIVES

To screen all of the obstructive sleep apnea (OSA)-characteristic pronunciations, explore the pronunciations which provide a better OSA classification effect than those used previously, and further clarify the correlation between speech signals and OSA.

METHODS

A total of 158 adult male Mandarin native speakers who completed polysomnography at the Sleep Medicine Center of Beijing Tongren Hospital from November 15, 2019, to January 19, 2020, were enrolled in this study. All Chinese syllables were collected from each participant in the sitting position. The syllables, vowels, consonants, and tones were screened to identify the pronunciations that were most effective for OSA classification.

RESULTS

The linear prediction coefficients of Chinese syllables were extracted as features and mathematically modeled using a decision tree model to dichotomize participants with apnea-hypopnea index thresholds of 10 and 30 events/h, and the leave-one-out method was used to verify the classification performance of Chinese syllables for OSA. Chinese syllables such as [leng] and [jue], consonant pronunciations such as [zh] and [f], and vowel pronunciations such as [ing] and [ai] were the most suitable pronunciations for classification of OSA. An OSA classification model consisting of several syllable combinations was constructed, with areas under curve of 0.83 (threshold of apnea-hypopnea index = 10) and 0.87 (threshold of apnea-hypopnea index = 30), respectively.

CONCLUSIONS

This study is the first comprehensive screening of OSA-characteristic pronunciations and can act as a guideline for the construction of OSA speech corpora in other languages.

CITATION

Ding Y, Sun Y, Li Y, et al. Selection of OSA-specific pronunciations and assessment of disease severity assisted by machine learning. J Clin Sleep Med. 2022;18(11):2663-2672.

Declines in Connected Language Are Associated with Very Early Mild Cognitive Impairment: Results from the Wisconsin Registry for Alzheimer's Prevention

Changes to everyday spoken language ("connected language") are evident in persons with AD dementia, yet little is known about when these changes are first detectable on the continuum of cognitive decline. The aim of this study was to determine if participants with very early, subclinical memory declines were also showing declines in connected language. We analyzed connected language samples obtained from a simple picture description task at two time points in 264 participants from the Wisconsin Registry for Alzheimer's Prevention (WRAP). In parallel, participants were classified as either "Cognitively Healthy" or "Early Mild Cognitive Impairment" based on longitudinal neuropsychological test performance. Linear mixed effects models were used to analyze language parameters that were extracted from the connected language samples using automated feature extraction. Participants with eMCI status declined faster in features of speech fluency and semantic content than those who were cognitively stable. Measures of lexical diversity and grammatical complexity were not associated with eMCI status in this group. These findings provide novel insights about the relationship between cognitive decline and everyday language, using a quick, inexpensive, and performance-based method.

Reviewing the connection between speech and obstructive sleep apnea

BACKGROUND

Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications.

METHODS

A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied.

RESULTS

The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results.

CONCLUSION

The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.