A review of automated sleep disorder detection.

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.

Efecto del incremento de la PEEP en la actividad muscular respiratoria evaluado con electromiografía de superficie en individuos sanos bajo ventilación espontánea / Effect of PEEP increase on respiratory muscle activity assessed through surface electromyography in healthy subjects during spontaneous breathing / Efeito do incremento da PEEP na atividade mus-cular respiratória avaliado com eletromiografia de superfície em indivíduos saudáveis sob ventilação espontânea

Introducción: en un paciente bajo ventilación mecánica con resistencia aumentada de la vía aérea, la duración de la fase espiratoria es insuficiente para exhalar todo el volumen inspirado. Para mantener la oxigenación y reducir el trabajo de los músculos respiratorios, es común aplicar una presión positiva al final de la espiración (PEEP), que reduce la colapsabilidad del tejido, compensando el aumento de la resistencia. Diversos estudios han demostrado la utilidad de la electromiografía de superficie (EMGS) para cuantificar el trabajo respiratorio. Objetivo: evaluar el efecto de la PEEP en la actividad muscular respiratoria mediante EMGS en individuos sanos bajo ventilación mecánica no invasiva. Metodología: estudio de la actividad muscular en 10 hombres voluntarios sanos ventilados de manera no invasiva con variaciones de la PEEP desde 0 hasta 5 cm H2O en pasos de 1 cm H2O, cada 30 segundos. Resultados: los biopotenciales del diafragma y el esternocleidomastoideo permitieron detectar diferentes respuestas ante el estímulo incremental: 1) aumento del trabajo de los dos músculos durante la inspiración y la espiración; 2) aumento de la actividad en solo uno de los músculos; 3) aumento del trabajo muscular exclusivamente durante la espiración. Conclusión: en individuos ventilados de forma no invasiva, la EMGS relaciona cuantitativamente el nivel de PEEP con el cambio en la actividad del diafragma y el esternocleidomastoideo.

Introduction: In a mechanically ventilated patient with increased airway resistance, the expiratory time span is insufficient to exhale all the inspired volume. In order to maintain oxygenation and to reduce the workload of respiratory muscles, it is common to apply an extrinsic positive end-expiratory pressure (PEEP) that reduces tissue collapsibility, counterbalancing the increased resistance. Several studies have shown the usefulness of surface electromyography (sEMG) to quantify the work of breathing (WOB), particularly in patients with obstructive diseases. Objective: To assess the effect of incremental PEEP in the respiratory muscle activity through sEMG in healthy volunteers noninvasively ventilated. Methods: Study of muscle activity in 10 healthy male volunteers, noninvasively ventilated for 20 minutes. The extrinsic PEEP was applied from 0 to 5 cm H2O in steps of 1 cm H2O at 30 seconds intervals. Results: The bio-potentials of diaphragm and sternocleidomastoid muscles revealed different breathing patterns in response to incremental PEEP: 1) increase in the workload of both muscles during inspiration and expiration; 2) increase in the workload of only one muscle; 3) a remarkable increase in muscle activity only in expiration. Conclusion: In noninvasively ventilated volunteers, sEMG quantitatively relates the PEEP level with changes in sternocleidomastoid and diaphragm activity.

Introdução: Num paciente sob ventilação mecânica com resistência aumentada da via aérea, a duração da fase respiratória é insuficiente para exalar todo o volume inspirado. Para manter a oxigenação e reduzir o trabalho dos músculos respiratórios, é comum aplicar uma pressão positiva no final da respiração (PEEP), que reduz a colapsabilidade do tecido, compensando o aumento da resistência. Diversos estudos demostraram a utilidade da eletromiografia de superfície (EMGS) para quantificar o trabalho respiratório. Objetivo: avaliar o efeito da PEEP na atividade muscular respiratória mediante EMGS em indivíduos saudáveis sob ventilação mecânica não invasiva. Metodologia: estudo da atividade muscular em 10 homens voluntários saudáveis ventilados de maneira não invasiva com variações da PEEP desde 0 até 5 cm H2O em passos de 1 cm H2O, cada 30 segundos. Resultados: os biopotenciais do diafragma e o esternocleidomastoideo permitiram detectar diferentes respostas ante o estímulo incremental: 1) aumento do trabalho dos dois músculos durante a inspiração e a espiração; 2) aumento da atividade em só um dos músculos; 3) aumento do trabalho muscular exclusivamente durante a espiração. Conclusão: em indivíduos ventilados de forma não invasiva, a EMGS relaciona quantitativamente o nível de PEEP com o câmbio na atividade do diafragma e oesternocleidomastoideo.