No description available.

No description available.

[pt] Para o diagnóstico de distúrbios do sono, um dos exames mais usado é a polissonografia (PSG), na qual é registrada uma variedade de sinais fisiológicos. O exame de PSG é observado por um especialista do sono, processo que pode levar muito tempo e incorrer em erros de interpretação. O presente trabalho desenvolve e compara o desempenho de quatro sistemas baseados em arquiteturas de redes neurais de aprendizado profundo, mais especificamente, redes convolutivas (CNN) e redes recorrentes Long-Short Term Memory (LSTM), para a identificação de despertares relacionados ao esforço respiratório (Respiratory Effort-Related Arousal-RERA) e a eventos de despertar relacionados à apneia/hipopneia. Para o desenvolvimento desta pesquisa, foram usadas as informações de apenas seis canais eletroencefalográficos (EEG) provenientes de 994 registros de PSG noturna da base de dados PhysioNet CinC Challenge2018, além disso, foi considerado o uso de class weight e Focal Loss para lidar com o desbalanceamento de classes. Para a avaliação de cada um dos sistemas foram usadas a Accuracy, AUROC e AUPRC como métricas de desempenho. Os melhores resultados para o conjunto de teste foram obtidos com os modelos CNN1 obtendo-se uma Accuracy, AUROC e AUPRC de 0,8404, 0,8885 e 0,8141 respetivamente, e CNN2 obtendo-se uma Accuracy, AUROC e AUPRC de 0,8214, 0,8915 e 0,8097 respetivamente. Os resultados restantes confirmaram que as redes neurais de aprendizado profundo permitem lidar com dados temporais de EEG melhor que os algoritmos de aprendizado de máquina tradicional, e o uso de técnicas como class weight e Focal Loss melhoram o desempenho dos sistemas. / [en] For the diagnosis of sleep disorders, one of the most commonly used tests is polysomnography (PSG), in which a variety of physiological signs are recorded. The study of PSG is observed by a sleep therapist, This process may take a long time and may incur misinterpretation. This work develops and compares the performance of four classification systems based on deep learning neural networks, more specifically, convolutional neural networks (CNN) and recurrent networks Long-Short Term Memory (LSTM), for the identification of Respiratory Effort-Related Arousal (RERA) and to events related to apnea/hypopnea. For the development of this research, it was used the Electroencephalogram (EEG) data of six channels from 994 night polysomnography records from the database PhysioNet CinC Challenge2018, the use of class weight and Focal Loss was considered to deal with class unbalance. Accuracy, AUROC, and AUPRC were used as performance metrics for evaluating each system. The best results for the test set were obtained with the CNN1 models obtaining an accuracy, AUROC and AUPRC of 0.8404, 0.8885 and 0.8141 respectively, and RCNN2 obtaining an accuracy, AUROC and AUPRC of 0.8214, 0.8915 and 0.8097 respectively. The remaining results confirmed that deep learning neural networks allow dealing with EEG time data better than traditional machine learning algorithms, and the use of techniques such as class weight and Focal Loss improve system performance.

Problématique : L’édentement et les troubles du sommeil sont des affections chroniques fréquentes chez les personnes âgées et qui peuvent avoir des conséquences défavorables sur le bien-être de ces personnes, ainsi que sur leur qualité de vie. L’édentement pourrait perturber le sommeil par la modification de la structure crânio-faciale et des tissus mous environnants. Cependant, cette relation n'est pas suffisamment documenté. Objectifs : Le but de cette étude pilote était de préparer la mise en œuvre d’une étude clinique randomisée contrôlée concernant l’effet du port nocturne des prothèses complètes sur la qualité du sommeil. Méthodologie : Treize aînés édentés ont participé à cette étude clinique randomisée contrôlée de type croisé. L’intervention consistait à dormir avec ou sans les prothèses durant la nuit. Les participants à l'étude ont été assignés à porter et ne pas porter leurs prothèses dans des ordres alternatifs pour des périodes de 30 jours. La qualité du sommeil a été évaluée par la polysomnographie portable et le questionnaire Pittburgh Sleep Quality Index (PSQI). Les données supplémentaires incluent la somnolence diurne, évaluée par le questionnaire Epworth Sleepiness Scale (ESS), et la qualité de vie liée à la santé buccodentaire, évaluée par le questionnaire Oral Health Impact Profile 20 (OHIP-20). De plus, à travers les examens cliniques et radiologiques, les données des caractéristiques sociodémographiques, de la morphologie oropharyngée, des caractéristiques buccodentaires et des prothèses ont été recueillies. Les modèles de régression linéaire pour les mesures répétées ont été utilisés pour analyser les résultats. Résultats : L’étude de faisabilité a atteint un taux de recrutement à l’étude de 59,1% et un taux de suivi de 100%. Le port nocturne des prothèses dentaires augmentait l’index d'apnée-hypopnée (IAH) et le score PSQI par rapport au non port nocturne des prothèses : (IAH : Médiane = 20,9 (1,3 - 84,7) versus 11,2 (1,9 - 69,6), p = 0,237; le score PSQI : Médiane = 6,0 (3,0 - 11,0) versus 5,0 (1,0 - 11,0), p = 0,248). Cependant, ces différences n'étaient pas statistiquement significatives, sauf que pour le temps moyen d’apnée (plus long avec des prothèses) (p < 0,005) et le temps de ronflement relatif (moins élevé avec des prothèses) (p < 0,05). La somnolence diurne excessive et la qualité de vie liée à la santé buccodentaire étaient semblables pour les deux interventions (le score ESS : Médiane = 4,0 (3,0-10,0) versus 5,0 (2,0-10,0), p = 0,746; le score OHIP-20: Médiane = 31,0 (20,0-64,0) versus 27,0 (20,0-49,0), p = 0,670). L’impact néfaste du port nocturne des prothèses complètes sur le sommeil a été statistiquement significatif chez les personnes souffrant de l’apnée-hypopnée moyenne à sévère (p < 0,005). Conclusion : L’essai clinique pilote a montré que le port nocturne des prothèses complètes a un impact négatif sur la qualité du sommeil des gens âgés édentés, surtout chez les personnes avec l’apnée obstructive du sommeil modérée à sévère. Les résultats doivent être confirmés par l’étude clinique randomisée contrôlée de phase II. / Problem: Edentulism and sleep disturbance are common chronic conditions in older people and may have adverse consequences on well-being of these persons, as well as their quality of life. Indeed, edentulism can modify the craniofacial structure and surrounding soft tissue, and lead to sleep disturbance in edentate individuals. However, this relationship is not sufficiently documented. Objectives: The aim of this study was to prepare a pilot randomized controlled trial on the effect of nocturnal complete denture wear on sleep quality. Methods: Thirteen edentate elders participated in this randomized cross-over clinical trial. The intervention consisted of sleeping with or without dentures at night. The study participants were assigned to wear and not wear their denture in alternate orders for periods of 30 days. Sleep quality was assessed by portable polysomnography and the Pittsburgh Sleep Quality Index (PSQI). Additional data included: daytime sleepiness assessed by the Epworth Sleepiness Scale (ESS) and oral-health-related quality of life assessed by the Oral Health Impact Profile 20 (OHIP-20). Furthermore, through the clinical and radiographic examinations, data on sociodemographic, oropharyngeal morphology, and oral and prosthesis characteristics were gathered. Linear regression models for repeated measures were used to analyze the data. Results: The recruitment rate for this study was 59.1% and the follow-up rate was 100%. Sleeping with dentures resulted in higher apnea-hypopnea index (AHI) and higher PSQI score when compared with sleeping without dentures (AHI: Median = 20.9 (1.3-84.7) vs. 11.2 (1.9-69.6), p = 0.237; PSQI score: Median = 6.0 (3.0-11.0) vs. 5.0 (1.0-11.0), p = 0.248). However, these differences were not statistically significant, except for the mean apnea time (more with dentures) (p < 0.005) and the relative snoring time (less with dentures) (p < 0.05). Excessive daytime sleepiness and the oral-health-related quality of life were similar for two interventions (ESS score: Median = 4.0 (3.0-10.0) vs. 5.0 (2.0-10.0), p = 0.746; OHIP-20 score: Median = 31.0 (20.0-64.0) vs. 27.0 (20.0-49.0), p = 0.670). The negative impact of sleeping with complete dentures wear was statistically significant in individuals suffering from moderate and severe apnea-hypopnea index (p < 0.005). Conclusion: The pilot clinical trial showed that wearing complete dentures at night has negative effects on the sleep quality of edentate elders, especially in individuals with moderate and severe obstructive apnea sleep. The results need to be confirmed with phase-II randomized clinical trial.

No description available.

This work examines sleep apnea syndrome, sleep physiology and self control of respiration during sleep. There is a review of respiration disorders during sleep and methods of monitoring sleep apnea syndrome. In another part the data of monitoration are processed and method of flow, saturation and snoring signal events detection is described, program algorithm is described and results are presented.