Predicting glycemic control status and high blood glucose levels through voice characteristic analysis in patients with cystic fibrosis-related diabetes (CFRD).

Cystic fibrosis-related diabetes (CFRD) is associated with reduced life expectancy in adults with cystic fibrosis (CF). Voice analysis may be a convenient method for diagnosing and monitoring CFRD. This study aims to determine the relationship between voice characteristics and markers of glucose and glycemic control and to identify if voice analysis can predict high blood glucose levels and glycemic control in adults with CFRD. We conducted a prospective cross-sectional study in adults with CF from March to December 2021. We recorded 3-second voice samples of a sustained /a/ vowel and analyzed voice characteristic using the Computerized Speech Lab with the Multi-Dimensional Voice Program. In female participants with CFRD, the noise-to-harmonic ratio was significantly lower in those with HbA1c ≥ 7. Furthermore, fundamental frequency variation was significantly lower in both male and female participants with CFRD who had a glucose level of 200 mg/dL or higher at the time of collection. This finding was also associated with a high level of point-of-care glucose. The human voice has potential as a non-invasive tool for measuring glucose levels and glycemic control status in CFRD patients in the future.

Identifying individuals with recent COVID-19 through voice classification using deep learning.

Recently deep learning has attained a breakthrough in model accuracy for the classification of images due mainly to convolutional neural networks. In the present study, we attempted to investigate the presence of subclinical voice feature alteration in COVID-19 patients after the recent resolution of disease using deep learning. The study was a prospective study of 76 post COVID-19 patients and 40 healthy individuals. The diagnoses of post COVID-19 patients were based on more than the eighth week after onset of symptoms. Voice samples of an 'ah' sound, coughing sound and a polysyllabic sentence were collected and preprocessed to log-mel spectrogram. Transfer learning using the VGG19 pre-trained convolutional neural network was performed with all voice samples. The performance of the model using the polysyllabic sentence yielded the highest classification performance of all models. The coughing sound produced the lowest classification performance while the ability of the monosyllabic 'ah' sound to predict the recent COVID-19 fell between the other two vocalizations. The model using the polysyllabic sentence achieved 85% accuracy, 89% sensitivity, and 77% specificity. In conclusion, deep learning is able to detect the subtle change in voice features of COVID-19 patients after recent resolution of the disease.

Instrumental Acoustic Voice Characteristics in Adults with Type 2 Diabetes.

OBJECTIVE: The objective of this study was to investigate if there are differences in acoustic parameters between diabetic patients and normal controls. METHODS: A prospective cross-sectional study was performed in 83 diabetic patients and 70 healthy controls. Voice parameters including fundamental frequency (F0), jitter, shimmer, amplitude perturbation quotient, noise-to-harmonic ratio, smoothed amplitude perturbation quotient, and relative average perturbation were analyzed using Computerized Speech Lab with the Multi-Dimensional Voice Program. RESULTS: F0 in female diabetic patients was significantly lower than controls (222.23 ± 27.89 Hz versus 241.08 ± 28.21 Hz, P< 0.01). In female diabetic subgroups with disease duration more than 10 years, poor glycemic control, or neuropathy, the F0 was still significantly lower. Multivariate analysis showed that F0 was significantly associated with diabetes after controlled for age, body mass index, presence of hypertension, and dyslipidemia. (P= 0.022). However, F0 was not able to predict the presence of diabetes as shown by logistic regression analysis (P= 0.243). CONCLUSIONS: Voice fundamental frequency is lower in females with diabetes. However, voice fundamental frequency cannot adequately predict the presence of diabetes.

Listening and speaking ability of Thai deaf children in preschool aural rehabilitation program.

BACKGROUND: An auditory-oral approach can help deaf children achieve success in oral communication. Many studies confirm that deaf children with access to sound through high-powered and appropriate hearing aids at the youngest age possible have the capability to acquire communication skills similar to their hearingpeers. OBJECTIVE: Evaluate the listening and speaking progress made by 27 Thai hearing-impaired children who attended a preschool aural rehabilitation program, which was established at Audiology and Speech clinic. After hearing aids fitting, deaf children were enrolled to the preschool aural rehabilitation program after receiving their parents consent. MATERIAL AND METHOD: Hearing impaired children were divided into groups of 4-6 children with approximately the same level of performance. The listening and speaking performance at the initial period were recorded. Each group participated in the 3-hour-program once a week, included auditory training, conversation (maternal reflexive method), and speech stimulation. The improvements and problems of each child were recorded at the end of session. Listening and speaking performance evaluation were recorded at six months intervals. RESULTS: There were 12 boys and 15 girls. The average hearing loss in the better ear was 104 dBHL, range from 83-117 dBHL, SD = 8.33. The mean age of enrollment was 2 years and 10 months. The majority gradually developed listening skills and speaking ability. There was no relationship between age of enrollment and the listening and speaking ability (p > 0.05). However, listening skills had positive relationship with length of speech (r = 0.685), number of spoken vocabulary (r = 0.665), and speech character (r = 0.598); p < 0.01. CONCLUSION: Auditory training is an important task to develop listening skills and improve length of speech, speaking vocabulary, and speech character Other benefits from the aural rehabilitation program included monitoring the auditory progression after hearing aid fitting, parents meeting, and promotion a better quality of life by enabling hearing impaired children to participate in hearing society.