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.
Introduction Many transgender people take hormone therapy to affirm their gender identity. One potential long-term consequence of gender affirming hormone therapy is increased body mass index (BMI), which may be associated with metabolic syndrome, cardiovascular disease and higher mortality. Only a few published studies explored changes in BMI in transgender people taking gender affirming hormone therapy (GAHT). Objective To examine the changes in BMI longitudinally in response to GAHT in transgender women and men. Methods We conducted a retrospective cohort study of transgender individuals who received GAHT from the endocrinology clinic between January 1, 2000 and September 6, 2018. Subjects who sought GAHT were included if they had two separate measurements of BMI and were excluded if they had a BMI greater than 35 kg/m 2 or were missing demographic data at entry. We used a linear mixed model to analyze the longitudinal change in BMI. Results There were a total of 227 subjects included in this cohort. Among subjects already on GAHT, transgender women were receiving GAHT longer than transgender men (6.59 ± 9.35 vs 3.67 ± 3.43 years, p-value = 0.04). Over the period of 7 years, there was a significant increase in BMI in transwomen who newly initiated GAHT (p-value 0.004). There were no changes in BMI in transgender men and women already on GAHT or in transgender men who newly initiated GAHT in the study. Conclusion We conclude that BMI significantly increases in transwomen but not in transmen after initiation of GAHT in a single center based in the United States. In transwomen and transmen, BMI appears to be stable following 3 to 6 years of GAHT. Future investigations should examine the causes for increased BMI in transgender women including type of GAHT, diet and lifestyle, and association with risk of metabolic syndrome and cardiovascular disease.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.