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.

The Commingled Division of Visual Attention.

Many critical activities require visual attention to be distributed simultaneously among distinct tasks where the attended foci are not spatially separated. In our two experiments, participants performed a large number of trials where both a primary task (enumeration of spots) and a secondary task (reporting the presence/absence or identity of a distinctive shape) required the division of visual attention. The spots and the shape were commingled spatially and the shape appeared unpredictably on a relatively small fraction of the trials. The secondary task stimulus (the shape) was reported in inverse proportion to the attentional load imposed by the primary task (enumeration of spots). When the shape did appear, performance on the primary task (enumeration) suffered relative to when the shape was absent; both speed and accuracy were compromised. When the secondary task required identification in addition to detection, reaction times increased by about 200 percent. These results are broadly compatible with biased competition models of perceptual processing. An important area of application, where the commingled division of visual attention is required, is the augmented reality head-up display (AR-HUD). This innovation has the potential to make operating vehicles safer but our data suggest that there are significant concerns regarding driver distraction.