Search

Di Zhang,1,2 Yichong She,1,2 Jinbo Sun,1,2 Yapeng Cui,1,2 Xuejuan Yang,1,2 Xiao Zeng,1,2 Wei Qin1,2 1Engineering Research Center of Molecular and Neuro Imaging of the Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, People’s Republic of China; 2Intelligent Non-Invasive Neuromodulation Technology and Transformation Joint Laboratory, Xidian University, Xi’an, People’s Republic of ChinaCorrespondence: Xiao Zeng, Xidian University, 266 Xifeng Road, Xinglong, Xi’an, Shaanxi, People’s Republic of China, 710126, Email xiaozeng1024@gmail.comPurpose: This study aims to improve brain age estimation by developing a novel deep learning model utilizing overnight electroencephalography (EEG) data.Methods: We address limitations in current brain age prediction methods by proposing a model trained and evaluated on multiple cohort data, covering a broad age range. The model employs a one-dimensional Swin Transformer to efficiently extract complex patterns from sleep EEG signals and a convolutional neural network with attentional mechanisms to summarize sleep structural features. A multi-flow learning-based framework attentively merges these two features, employing sleep structural information to direct and augment the EEG features. A post-prediction model is designed to integrate the age-related features throughout the night. Furthermore, we propose a DecadeCE loss function to address the problem of an uneven age distribution.Results: We utilized 18,767 polysomnograms (PSGs) from 13,616 subjects to develop and evaluate the proposed model. The model achieves a mean absolute error (MAE) of 4.19 and a correlation of 0.97 on the mixed-cohort test set, and an MAE of 6.18 years and a correlation of 0.78 on an independent test set. Our brain age estimation work reduced the error by more than 1 year compared to other studies that also used EEG, achieving the level of neuroimaging. The estimated brain age index demonstrated longitudinal sensitivity and exhibited a significant increase of 1.27 years in individuals with psychiatric or neurological disorders relative to healthy individuals.Conclusion: The multi-flow deep learning model proposed in this study, based on overnight EEG, represents a more accurate approach for estimating brain age. The utilization of overnight sleep EEG for the prediction of brain age is both cost-effective and adept at capturing dynamic changes. These findings demonstrate the potential of EEG in predicting brain age, presenting a noninvasive and accessible method for assessing brain aging.Keywords: brain age, sleep polysomnography, electroencephalography, deep learning, swin transformer

Background Polysomnography ( PSG) remains the gold standard for diagnosing obstructive sleep apnea ( OSA) and sleep-disordered breathing in children. Yet, simple screening tools are needed as it is not feasible to perform PSG in all patients with possible OSA. Aim The study adapted questions from the Pediatric Sleep Questionnaire-Sleep-Related Breathing Disorder (SRBD) Questionnaire to develop a predictive scale for OSA identified on PSG. We also tested whether adding anthropometric measurements (body mass index and neck circumference) improved prediction of OSA. Methods After IRB approval, OSA questionnaires and anthropometric measurements were collected on 948 consecutive patients scheduled for PSG, aged 4 months to 24.5 years (median = 8.5 years). The sample was reduced to 636 patients in the age range (6-18 years old) where normative values for neck circumference are defined. OSA was characterized using the obstructive apnea-hypopnea index ( AHI). After identifying questions related to OSA in univariate logistic regression, multivariable models were fitted to select questions for a short scale, and points for exceeding body mass or neck circumference cutoffs were added to assess improvement in predictive value. Results A long scale of 16 questionnaire items was constructed using univariate models, while six items were selected for the short scale by multivariable regression. The short scale was associated with greater odds of moderate/severe OSA ( OR = 1.964; 95% CI = 1.620, 2.381; P < 0.001) and attained good predictive value (area under receiver operating characteristics curve [ AUC] = 0.74), which was not significantly improved by addition of BMI and neck circumference data ( AUC = 0.75). Conclusions We developed a six-question scale with good predictive utility for OSA. These findings may contribute to developing a preoperative clinical tool to help clinicians identify children with OSA for determining risk stratification and postoperative disposition. [ABSTRACT FROM AUTHOR]

The sleep patterns were examined through three simulated 20-m nitrox saturation dives. The standard polysomnography of 12 divers was recorded respectively for a total of 204 nights, as were patterns of change or consistency in sleep variables. For the 11 divers in their 20s and 30s there was nothing unusual about their sleep variables. However, a reduction of total sleep time in accordance with the lengthening of sleep latency was observed. This was recognized from the latter part of the bottom period to the postdive period. This tendency was notable for the diver in his 50s. These findings suggest that the decompression environment and the psychological stress of the long-term closed environment of a hyperbaric chamber have effects on divers’ sleep. [ABSTRACT FROM AUTHOR]

Abstract Sleep patterns during saturation dives equivalent to a 30-m depth (pressurized condition) and habitation in a confined environment at 1 atm absolute pressure (non-pressurized condition) were studied to determine the effects of environmental pressure. Eight inexperienced divers experienced the pressurized condition of the saturation dives, and nine healthy subjects experienced the non-pressurized condition. Standard polysomnographs were recorded for 262 nights. For both conditions, reductions in total sleep time accompanied by lengthening in sleep latency and reduction in sleep efficiency were observed from the latter part of the experiments through to the recovery periods. These findings suggest that changes were related to psychological and physiological stresses caused by long stays in a confined environment and not by the environmental pressure. [ABSTRACT FROM AUTHOR]