Search

Im Zuge der rasanten Entwicklung der Computertechnik ist künstliche Intelligenz heute zu einem wesentlichen Bestandteil des täglichen Lebens geworden. Auch die Bereiche Medizin und Lungengesundheit stellen in diesem Zusammenhang keine Ausnahme dar. Wissenschaftliche Forschung auf der Grundlage von Big Data durchzuführen, bedeutet nicht, einfach eine große Menge an Daten zu sammeln und dann den Maschinen die Arbeit zu überlassen. Wissenschaftler müssen vielmehr Probleme identifizieren, deren Lösung sich positiv auf die Versorgung der Patienten auswirken würde. In dieser Übersichtsarbeit wird die Rolle der künstlichen Intelligenz sowohl aus physiologischer als auch aus anatomischer Sicht erörtert. Ausgehend von der automatischen quantitativen Bewertung anatomischer Strukturen mithilfe der Bildgebung der Lunge betrachten wir die Themenbereiche der Erkennung von Krankheiten und der Einschätzung der Prognose auf der Grundlage von maschinellem Lernen. Die Bewertung der aktuellen Stärken und Einschränkungen wird es uns ermöglichen, einen breiteren Blick auf zukünftige Entwicklungen zu werfen.

BackgroundMechanisms underlying blood pressure changes in obstructive sleep apnoea (OSA) are incompletely understood. Increased respiratory effort is one of the main features of OSA and is associated with sympathetic overactivity, leading to increased vascular wall stiffness and remodelling. This study investigated associations between a new measure of respiratory effort (percentage of total sleep time spent with increased respiratory effort based on measurement of mandibular jaw movements (MJM): REMOV, %TST) and prevalent hypertension in adults referred for evaluation of suspected OSA.MethodsA machine learning model was built to predict hypertension from clinical data, conventional polysomnography (PSG) indices and MJM-derived parameters (including REMOV). The model was evaluated in a training subset and a test subset.ResultsThe analysis included 1127 patients: 901 (80%) in the training subset and 226 (20%) in the test subset. The prevalence of hypertension was 31% and 30%, respectively, in the training and test subsets. A risk stratification model based on 18 input features including REMOV had good accuracy for predicting prevalent hypertension (sensitivity 0.75 and specificity 0.83). Using the Shapley additive explanation method, REMOV was the best predictor of hypertension after clinical risk factors (age, sex, body mass index and neck circumference) and time with oxygen saturation ConclusionThe proportion of sleep time spent with increased respiratory effort automatically derived from MJM was identified as a potential new reliable metric to predict prevalent hypertension in patients with OSA.

Objective: The aim of the present study was to measure the correlation between the level of exhaled Nitric Oxide (NO) and Obstructive Sleep Apnea (OSA) severity and to evaluate its modification after Continuous Positive Airway Pressure (CPAP) treatment in severe OSA patients. Methods: It was a descriptive and cross-sectional study. Subjects were classified by mild-moderate or severe OSA. CPAP was used for severe OSA patients and followed up for 3 months. Exhaled NO was measured in the morning after the previous night of Respiratory Polygraphy (RPG) recording. Results: This study recruited 123 subjects, including 40 mild-moderate and 83 severe OSA patients. The level of maximum bronchial NO production (J’awNO) in patients with severe OSA was significantly higher than mild-moderate OSA [36.2 (6.1–92.2) vs. 19.6 (1.6-73.0) ppb; p=0.001)]. The level of concentration of NO in the gas phase of the alveolar (CANO) in patients with severe OSA was lower than mild-moderate OSA [5.2 (1.2-12.7) vs. 6.9 (0.8-14.0) ppb; p=0.002). The total flux of NO in the conducting airway compartment (J’awNO) and CANO were correlated with an apnea-hypopnea index (AHI) (rho=0.25 and p=0.02; rho= 0.18 and p=0.04, respectively). There was a weak significant correlation between J’awNO and nadir SpO2 in patients with OSA (rho = -0.22 and p= 0.023). After 3-month treatment with CPAP, the level of J’awNO was significantly reduced in patients with severe OSA [23.4 (12.9-44.5) vs. 33.1 (21.2-55.0); p Conclusion: J’awNO is proportionally increased in patients with severe OSA and reduced after treatment with CPAP. Thus, J’awNO may be used as a relevant and surrogate biomarker of severe OSA.

International audience; No abstract available

We aimed to investigate the performance of a chest X-ray (CXR) scoring scale of lung injury in prediction of death and ICU admission among patients with COVID-19 during the 2021 peak pandemic in HCM City, Vietnam. CXR and clinical data were collected from Vinmec Central Park-hospitalized patients from July to September 2021. Three radiologists independently assessed the day-one CXR score consisting of both severity and extent of lung lesions (maximum score = 24). Among 219 included patients, 28 died and 34 were admitted to the ICU. There was a high consensus for CXR scoring among radiologists (κ = 0.90; CI95%: 0.89–0.92). CXR score was the strongest predictor of mortality (tdAUC 0.85 CI95% 0.69–1) within the first 3 weeks after admission. A multivariate model confirmed a significant effect of an increased CXR score on mortality risk (HR = 1.33, CI95%: 1.10 to 1.62). At a threshold of 16 points, the CXR score allowed for predicting in-hospital mortality and ICU admission with good sensitivity (0.82 (CI95%: 0.78 to 0.87) and 0.86 (CI95%: 0.81 to 0.90)) and specificity (0.89 (CI95%: 0.88 to 0.90) and 0.87 (CI95%: 0.86 to 0.89)), respectively, and can be used to identify high-risk patients in needy countries such as Vietnam.

Introduction Obstructive sleep apnea (OSA) and type 2 diabetes (T2Dia) is a frequent clinical association. Beyond OSA-related hypoxic burden, increased respiratory effort (RE) is one of the main features of OSA and contributes to sympathetic overactivity that in turn might participate to glucose homeostasis dysregulation. The independent contribution of RE to the OSA-T2Dia pathogenesis remains to be demonstrated. The study aims to determine the impact of metrics assessing sleep RE derived from the sleep mandibular jaw movements (MJM) signal on the prevalence of T2Dia in a large cohort of patients addressed for in-laboratory conventional polysomnography (PSG) with suspicion of OSA. Methods An interpretable machine learning model was built to predict T2Dia from clinical data, PSG indices, and MJM-derived parameters (including the time spent with increased RE, expressed in % of TST). The analysis included 1128 subjects, randomly assigned to training (n=853) and validation (n=275) subsets with equal T2Dia prevalence of 11%. Results The risk stratification model based on 19 input features including increased RE showed good performance for predicting prevalent T2Dia (sensitivity=0.81, specificity=0.89). Post-hoc interpretation using the Shapley additive explanation (SHAP) method revealed that increased RE was the most important risk factor of T2Dia after other clinical factors for T2Dia (i.e., sex, BMI and average SpO2), ahead of standard PSG metrics (including the apnea-hypopnea index and oxygen desaturation index). Conclusion These findings suggested that the proportion of sleep time spent with increased RE automatically derived from MJM is a potential new reliable metric to predict prevalent T2Dia in patients with OSA. Support (if any)

Introduction Single night in-lab polysomnography (PSG) is still the conventional procedure for making obstructive sleep apnea (OSA) diagnosis, or alternatively a home sleep apnea test (HSAT) in patients free from comorbidity. Recent publications drew attention to considerable internight within-subject variability in OSA clinical status, notably but not only with HSAT. Taking benefit of multiple nights recording in home-based setting using measurements of mandibular jaw movement (MJM) combined with automated machine learning analysis, this study aimed to investigate the effect of change in sleep parameters on the internight variability of the apnea hypopnea index (VAHI). Methods 160 adults suspected of having OSA successfully completed 3 sleep tests at home with the Sunrise device (Sunrise, Namur, Belgium). Data analysis implied generalized estimating equation (GEE) regression. Results Even though the internight variability of AHI was not statistically significant at the population level with a mean VAHI of -1.1 ± 7.8 events/h, such variability could lead to misdiagnosis and wrong therapeutic decisions based on a single night. After adjusting for effects of gender, body mass index (BMI), age, total sleep time (TST) and time interval between sleep tests, regression models indicated that sleeping in supine position was positively and independently associated with VAHI, the AHI increased by 0.95 event/h for each 10% of increase in sleeping time in supine position. VAHI was negatively and significantly (p < 0.01) associated with sleep efficiency and deep sleep; VAHI decreased of 0.16 event/h (0.04 to 0.28) and 0.29 event/h (0.17 to 0.42) for each % of increase in sleep efficiency and proportion of deep sleep, respectively. Conclusion At the individual level, position, sleep efficiency and deep sleep are associated with short-term internight variability in AHI. Clinical decision based on a single-night testing may lead to errors in OSA diagnosis with delayed or wrong therapeutic decisions. Support (if any)

International audience; Bruxism is a heterogeneous condition related to various underlying mechanisms, including the presence of OSA. This case report illustrates that sleep mandibular movement monitoring and analysis could provide a useful opportunity for detection of both sleep bruxism and respiratory effort. The current case suggests that tracking of respiratory effort could enable evaluation of bruxism and its potential interactions. Successful treatment of sleep-related respiratory effort may lead to improved or resolution of bruxism in cases where such a causal relationship does exist.

Jean-Louis Pepin,1,* Nhat-Nam Le-Dong,2,* Valérie Cuthbert,3 Nathalie Coumans,3 Renaud Tamisier,1 Atul Malhotra,4 Jean-Benoit Martinot3,5 1HP2 Laboratory, Inserm U1300, University Grenoble Alpes, Grenoble, France; 2Sunrise, Namur, Belgium; 3Sleep Laboratory, CHU Université Catholique de Louvain (UCL) Namur Site Sainte-Elisabeth, Namur, Belgium; 4University of California San Diego, La Jolla, CA, USA; 5Institute of Experimental and Clinical Research, UCL Bruxelles Woluwe, Brussels, Belgium*These authors contributed equally to this workCorrespondence: Jean-Benoit Martinot, Centre du Sommeil et de la Vigilance, CHU-UCL Namur Site Ste Elisabeth, 15 Place Louise Godin, Namur, 5000, Belgium, Tel +32 495502608, Fax +32 81570754, Email martinot.j@respisom.bePurpose: Differentiation between obstructive and central apneas and hypopneas requires quantitative measurement of respiratory effort (RE) using esophageal pressure (PES), which is rarely implemented. This study investigated whether the sleep mandibular movements (MM) signal recorded with a tri-axial gyroscopic chin sensor (Sunrise, Namur, Belgium) is a reliable surrogate of PES in patients with suspected obstructive sleep apnea (OSA).Patients and Methods: In-laboratory polysomnography (PSG) with PES and concurrent MM monitoring was performed. PSGs were scored manually using AASM 2012 rules. Data blocks (n=8042) were randomly sampled during normal breathing (NB), obstructive or central apnea/hypopnea (OA/OH/CA/CH), respiratory effort-related arousal (RERA), and mixed apnea (MxA). Analyses were evaluation of the similarity and linear correlation between PES and MM using the longest common subsequence (LCSS) algorithm and Pearson’s coefficient; description of signal amplitudes; estimation of the marginal effect for crossing from NB to a respiratory disturbance for a given change in MM signal using a mixed linear-regression.Results: Participants (n=38) had mild to severe OSA (median AH index 28.9/h; median arousal index 23.2/h). MM showed a high level of synchronization with concurrent PES signals. Distribution of MM amplitude differed significantly between event types: median (95% confidence interval) values of 0.60 (0.16– 2.43) for CA, 0.83 (0.23– 4.71) for CH, 1.93 (0.46– 12.43) for MxA, 3.23 (0.72– 18.09) for OH, and 6.42 (0.88– 26.81) for OA. Mixed regression indicated that crossing from NB to central events would decrease MM signal amplitude by – 1.23 (CH) and – 2.04 (CA) units, while obstructive events would increase MM amplitude by +3.27 (OH) and +6.79 (OA) units (all p< 10− 6).Conclusion: In OSA patients, MM signals facilitated the measurement of specific levels of RE associated with obstructive, central or mixed apneas and/or hypopneas. A high degree of similarity was observed with the PES gold-standard signal.Keywords: obstructive sleep apnea, respiratory effort, mandibular movements, esophageal pressure

Introduction Differentiation between obstructive and central apneas and hypopneas requires quantitative measurement of respiratory effort (RE) using esophageal pressure (PES), which is rarely implemented. This study investigated whether the sleep mandibular movements (MM) signal recorded with a tri-axial chin sensor (Sunrise, Namur, Belgium) is a reliable surrogate of PES in patients with suspected obstructive sleep apnea (OSA). Methods In-laboratory polysomnography (PSG) with PES and concurrent MM monitoring was performed. PSGs were scored manually using AASM 2012 rules. Data blocks (n=8042) were randomly sampled during normal breathing (NB), obstructive or central apnea/hypopnea (OA/OH/CA/CH), respiratory effort-related arousal (RERA), and mixed apnea (MxA). Analyses were: evaluation of the similarity and linear correlation between PES and MM using the longest common subsequence (LCSS) algorithm and Pearson’s coefficient; description of signal amplitudes; estimation of the marginal effect for crossing from NB to a respiratory disturbance for a given change in MM signal using a mixed linear-regression. Results Participants (n=38) had mild to severe OSA (median AH index 28.9/h; median arousal index 23.2/h). MM showed a high level of synchronization with concurrent PES signals. Distribution of gyroscope MM signal amplitude differed significantly between event types: median (95% confidence interval) values of 0.60 (0.17–2.43) for CA, 0.83 (0.23–4.71) for CH, 1.93 (0.54–5.57) for MxA, 3.23 (0.72–18.09) for OH, and 6.42 (0.88–26.81) units for OA. Mixed regression indicated that crossing from NB to central events would decrease gyroscope MM signal amplitude by –1.23 (CH) and –2.04 (CA) units, while obstructive events would increase gyroscope MM signal amplitude by +3.27 (OH) and +6.79 (OA) units (all p Conclusion In OSA patients, MM signals facilitated the measurement of specific levels of RE associated with obstructive, central or mixed apneas and/or hypopneas. A high degree of similarity was observed with the PES gold-standard signal. Support (If Any)

Khue Dang-Thi-Mai,1 Nhat-Nam Le-Dong,2 Vu Le-Thuong,1 Ngoc Tran-Van,1 Sy Duong-Quy3,4 1Department of Respiratory Diseases, Cho Ray Hospital, Ho Chi Minh City, Vietnam; 2Department of Technology, Sunrise, Namur, Belgium; 3Bio-Medical Research Centre, Lam Dong Medical College, Dalat, Vietnam; 4Penn State Medical College, Hershey Medical Center, Hershey, PA, USACorrespondence: Sy Duong-QuyBio-Medical Research Centre, Lam Dong Medical College, 16 Ngo Quyen, Dalat, VietnamTel +84 918413813Fax +84 2633815000Email sduongquy.jfvp@gmail.comPurpose: Our study aimed to evaluate the relationship between exhaled nitric oxide (eNO) markers and obstructive sleep apnea (OSA) severity and verify the changes in eNO profiles among mild, moderate, and severe OSA subgroups.Methods: This study was a cross-sectional and in-hospital population-based study. We investigated 123 OSA patients (17 mild, 23 moderate and, 83 severe OSA) in the department of respiratory diseases. Studied data included anthropometry, respiratory polygraphy, biological markers, spirometry, and multi-flow eNO measurements. Data analysis implied linear correlation, non-parametric ANOVA, and pair-wise comparison.Results: No significant difference could be found among 3 OSA severity subgroups for FENO at – four sampling flow rates (50– 350 mL/s). The bronchial production rate of NO (J’awNO) was proportionally increased, with median values of 11.2, 33.9, and 36.2 in mild, moderate, and severe OSA, respectively (p=0.010). The alveolar concentration of NO (CANO) changed with a non-linear pattern; it was increased in moderate (6.49) vs mild (7.79) OSA but decreased in severe OSA (5.20, p = 0.015). The only correction that could be established between OSA severity and exhaled nitric oxide markers is through J’AWNO (rho=0.25, p=0.02) and CANO (rho= 0.18, p=0.04). There was no significant correlation between FENO measured at three different flow rates and the OSA severity. We also found a weak but significant correlation between FENO 100 and averaged SpO2 (rho = 0.07, p= 0.03).Conclusion: The present study showed that J’AWNO, which represents eNO derived from the central airway, is proportionally increased in more severe OSA, while eNO from alveolar space, indicated by CANO, was also associated with OSA severity and relatively lower in the most severe OSA patients. In contrast, stand-alone FENO metrics did not show a clear difference among the three severity subgroups.Keywords: exhaled nitric oxide, FENO, J’AWNO, CANO, obstructive sleep apnea

With the rapid development of computing today, artificial intelligence has become an essential part of everyday life, with medicine and lung health being no exception. Big data-based scientific research does not mean simply gathering a large amount of data and letting the machines do the work by themselves. Instead, scientists need to identify problems whose solution will have a positive impact on patients’ care. In this review, we will discuss the role of artificial intelligence from both physiological and anatomical standpoints, starting with automatic quantitative assessment of anatomical structures using lung imaging and considering disease detection and prognosis estimation based on machine learning. The evaluation of current strengths and limitations will allow us to have a broader view for future developments.

Purpose Sleep bruxism (SBx) activity is classically identified by capturing masseter and/or temporalis masticatory muscles electromyographic activity (EMG-MMA) during in-laboratory polysomnography (PSG). We aimed to identify stereotypical mandibular jaw movements (MJM) in patients with SBx and to develop rhythmic masticatory muscles activities (RMMA) automatic detection using an artificial intelligence (AI) based approach. Patients and Methods This was a prospective, observational study of 67 suspected obstructive sleep apnea (OSA) patients in whom PSG with masseter EMG was performed with simultaneous MJM recordings. The system used to collect MJM consisted of a small hardware device attached on the chin that communicates to a cloud-based infrastructure. An extreme gradient boosting (XGB) multiclass classifier was trained on 79,650 10-second epochs of MJM data from the 39 subjects with a history of SBx targeting 3 labels: RMMA episodes (n=1072), micro-arousals (n=1311), and MJM occurring at the breathing frequency (n=77,267). Results Validated on unseen data from 28 patients, the model showed a very good epoch-by-epoch agreement (Kappa = 0.799) and balanced accuracy of 86.6% was found for the MJM events when using RMMA standards. The RMMA episodes were detected with a sensitivity of 84.3%. Class-wise receiver operating characteristic (ROC) curve analysis confirmed the well-balanced performance of the classifier for RMMA (ROC area under the curve: 0.98, 95% confidence interval [CI] 0.97–0.99). There was good agreement between the MJM analytic model and manual EMG signal scoring of RMMA (median bias −0.80 events/h, 95% CI −9.77 to 2.85). Conclusion SBx can be reliably identified, quantified, and characterized with MJM when subjected to automated analysis supported by AI technology., Video Abstract Point your SmartPhone at the code above. If you have a QR code reader the video abstract will appear. Or use: https://youtu.be/M7LqfF1ZCyk

Context: Automated sleep stages scoring from surrogate signals is challenging. Mandibular movements (MM) are reliable markers of the neural respiratory drive, with activity patterns reflecting sleep stages. We introduce a new automated sleep stage scoring method using MM signal. Method: Study was conducted on 96 adults (18 to 58 yrs, AHI MM signals were split into 30 seconds epochs, from which 217 features were extracted to classify 3 labels: wake, nonREM and REM sleep. The model was trained on PSG data from 68 subjects consisting of 169 hrs of nonREM, 26 hrs of REM and 21 hrs of wake. The model was validated on unseen data from 28 subjects composed of 147 hrs of nonREM, 38 hrs of REM sleep and 33 hrs of wake. Results: Subjects had a mean total sleep time of 7.14 hrs (CI: 5.53 to 8.49), a mean AHI of 3.57 events/h (CI: 1.00 to 6.92) and a mean arousal index of 9.22 events/h (CI: 4.36 to 16.69). The model showed good global performances, with a balanced accuracy of 0.79 (CI: 0.78 to 0.80) and an area under the receiver operating curve of 0.94, 0.91 and 0.93 for wake, nonREM and REM. Conclusion: This study demonstrated for the first time that MM signals are suitable for automated sleep stage scoring, providing a promising solution for home monitoring of sleep architecture.

IMPORTANCE: Given the high prevalence of obstructive sleep apnea (OSA), there is a need for simpler and automated diagnostic approaches. OBJECTIVE: To evaluate whether mandibular movement (MM) monitoring during sleep coupled with an automated analysis by machine learning is appropriate for OSA diagnosis. DESIGN, SETTING, AND PARTICIPANTS: Diagnostic study of adults undergoing overnight in-laboratory polysomnography (PSG) as the reference method compared with simultaneous MM monitoring at a sleep clinic in an academic institution (Sleep Laboratory, Centre Hospitalier Universitaire Université Catholique de Louvain Namur Site Sainte-Elisabeth, Namur, Belgium). Patients with suspected OSA were enrolled from July 5, 2017, to October 31, 2018. MAIN OUTCOMES AND MEASURES: Obstructive sleep apnea diagnosis required either evoking signs or symptoms or related medical or psychiatric comorbidities coupled with a PSG-derived respiratory disturbance index (PSG-RDI) of at least 5 events/h. A PSG-RDI of at least 15 events/h satisfied the diagnosis criteria even in the absence of associated symptoms or comorbidities. Patients who did not meet these criteria were classified as not having OSA. Agreement analysis and diagnostic performance were assessed by Bland-Altman plot comparing PSG-RDI and the Sunrise system RDI (Sr-RDI) with diagnosis threshold optimization via receiver operating characteristic curves, allowing for evaluation of the device sensitivity and specificity in detecting OSA at 5 events/h and 15 events/h. RESULTS: Among 376 consecutive adults with suspected OSA, the mean (SD) age was 49.7 (13.2) years, the mean (SD) body mass index was 31.0 (7.1), and 207 (55.1%) were men. Reliable agreement was found between PSG-RDI and Sr-RDI in patients without OSA (n = 46; mean difference, 1.31; 95% CI, -1.05 to 3.66 events/h) and in patients with OSA with a PSG-RDI of at least 5 events/h with symptoms (n = 107; mean difference, -0.69; 95% CI, -3.77 to 2.38 events/h). An Sr-RDI underestimation of -11.74 (95% CI, -20.83 to -2.67) events/h in patients with OSA with a PSG-RDI of at least 15 events/h was detected and corrected by optimization of the Sunrise system diagnostic threshold. The Sr-RDI showed diagnostic capability, with areas under the receiver operating characteristic curve of 0.95 (95% CI, 0.92-0.96) and 0.93 (95% CI, 0.90-0.93) for corresponding PSG-RDIs of 5 events/h and 15 events/h, respectively. At the 2 optimal cutoffs of 7.63 events/h and 12.65 events/h, Sr-RDI had accuracy of 0.92 (95% CI, 0.90-0.94) and 0.88 (95% CI, 0.86-0.90) as well as posttest probabilities of 0.99 (95% CI, 0.99-0.99) and 0.89 (95% CI, 0.88-0.91) at PSG-RDIs of at least 5 events/h and at least 15 events/h, respectively, corresponding to positive likelihood ratios of 14.86 (95% CI, 9.86-30.12) and 5.63 (95% CI, 4.92-7.27), respectively. CONCLUSIONS AND RELEVANCE: Automatic analysis of MM patterns provided reliable performance in RDI calculation. The use of this index in OSA diagnosis appears to be promising.

Objectif Le syndrome des apnees du sommeil (SAS) en pediatrie est frequent et co_morbide ; un diagnostic simplifie est necessaire en pratique clinique. Nous evaluons ici la performance d’une machine learning basee sur l’analyse de l’effort respiratoire a travers le signal du seul mouvement mandibulaire (MM) pour le diagnostic du SAS pediatrique (Sunrise, Namur, Belgium). Methodes L’etude prospective a ete realisee chez 140 enfants adresses pour une polysommographie au laboratoire de sommeil (PSG) avec enregistrement simultane des MMs. Le diagnostic et la severite sont definis en PSG par un index d’apnee/hypopnee (OAHI) ≥ 1/h (leger), ≥ 5/h (modere) et ≥ 10/h (severe). Resultats La concordance entre la PSG et Sunrise (Sr) est appreciee par un graphe de Bland-Altman comparant l’indice horaire des evenements obstructifs a type d’apnees/hypopnees et de micro-eveils lies a un effort respiratoire (ORDI). La performance de Sr-ORDI est determinee par une courbe ROC evaluant la sensibilite et la specificite aux 3 niveaux de severite de la PSG. Une difference mediane de 1,57 evenements/h (95 %CI : -2,49 ; 8,11) est mesuree entre Sr_ORDI et PSG_ORDI. Les aires (et leurs ecarts interquartiles) sous les courbes de ROC sont respectivement de 0,75 (0,72 ; 0,78), 0,90 (0,86 ; 0,92) et 0,95 (0,90 ; 0,99) aux seuils de severite en PSG de ≥ 1/h, ≥ 5/h et ≥ 10/h. Conclusion L’analyse automatisee de MM procure un diagnostic robuste du SAS pediatrique modere a severe.

Objectives Adenotonsillectomy (AT) markedly improves but does not necessarily normalize polysomnographic findings in children with adenotonsillar hypertrophy and related sleep-disordered breathing (SDB). Adenotonsillectomy efficacy should be evaluated by follow-up polysomnography (PSG), but this method may underestimate persistent respiratory effort (RE). Mandibular movement (MMas) monitoring is an innovative measurement that readily identifies RE during upper airway obstruction. We hypothesized that MMas indices would decrease in parallel of PSG indices and that children with persistent RE more reliably could be identified with MMas. Methods Twenty-five children (3–12 years of age) with SDB were enrolled in this individual prospective-cohort study. Polysomnography was supplemented with a midsagittal movement magnetic sensor that measured MMas during each respiratory cycle before and > 3 months after AT. Results Adenotonsillectomy significantly improved PSG indices, except for RE-related arousals (RERA). Mandibular movement index changes after AT significantly were correlated with corresponding decreases in sleep apnea–hypopnea index (AHI) and O2 desaturation index (ODI) (Spearman's rho = 0.978 and 0.922, respectively), whereas changes in MMas duration significantly were associated with both RERA duration (rho = 0.475, P = 0.017) and index (rho = 0.564, P = 0.003). Conditional multivariate analysis showed that both AHI and RERA significantly contributed to the variance of MMas index after AT (P = 0.0003 and 0.0005, respectively), whereas MMas duration consistently was related to the duration of RERA regardless of AT. Conclusion Adenotonsillectomy significantly reduced AHI. However, persistent RERA were apparent in a significant proportion of children, and this was reflected by the remaining abnormal MMas pattern. Follow-up of children after AT can be recommended and readily achieved by monitoring MMas to identify persistent RE. Level of Evidence 4. Laryngoscope, 2017

Introduction Sleep bruxism (BXM) is the result of rhythmic muscular masticatory activity (RMMA) and can be captured by masseters surface electromyography (sEMG). Despite the multiple adverse negative consequences of BXM, a simple reliable home diagnostic device is currently unavailable, with in laboratory audio-video polysomnography (type I PSG) remaining the gold standard diagnostic tool. Mandibular movements (MM) recordings during sleep can readily identify RMMA, are simple to set up and can be easily repeated from night to night. Here, we aimed to identify stereotypical MM in patients with BXM, and to develop RMMA automatic detection and BXM diagnosis using an artificial intelligence-based approach. Methods MM were recorded by a dedicated sensor (Sunrise, Namur, Belgium) in 12 patients with BXM during type I PSG. The Sunrise system consists of a coin-sized hardware that is comfortably placed on the subject’s chin. Its embedded inertial measurement unit communicates via Bluetooth with a smartphone and automatically transfers MM signals to a cloud-based infrastructure at the end of the night. Data processing and analysis are then performed in Python programming language. A time series cluster analysis was applied to sequences of masseters sEMG and MM signals during BXM episodes (n=300) and during spontaneous micro-arousals (n=300). Then, a convolutional neuronal network (CNN) was developed to identify BXM and distinguish it from spontaneous micro-arousals while exclusively relying on MM signal. Results Based on the cluster analysis, BXM periods were characterized by a specific pattern of MM signals (higher frequency and amplitude), which was closely associated with the sEMG signals but clearly differed from the MM signal patterns during micro-arousals. CNN-based classifier distinguished the BXM events from other RMMAs during micro-arousals and respiratory efforts with an overall accuracy of 91%. Conclusion Sleep bruxism can be automatically identified, quantified, and characterized with mandibular movements analysis supported by artificial intelligence technology. Support This work was supported by the French National Research Agency (ANR-12-TECS-0010), in the framework of the “Investissements d’avenir” program (ANR-15-IDEX-02). https://life.univ-grenoble-alpes.fr.

Objective: We introduce a new interpretation method for PFT data. Methods: Our new method consists of 3 steps: To build a diagnostic rule for a specific target from multi-PFT parameters. To estimate the Shapley-score, a game-theory based metric which measures the importance of each PFT index by comparing the model’s predictions with and without that index. To generate the interpretation, indicating the contribution level of each parameter to the positive/negative diagnosis. We applied this method to detect interstitial lung disease (ILD) in patients with systemic sclerosis. A machine learning diagnostic rule was developed from data of 300 patients undergoing 5 PFT techniques. Results: Validated on unseen data (n=100), the rule showed a good clinical performance (Sensitivity=0.86, Specificity=0.89, Positive and negative Likelihood-ratios of 7.86 and 0.16 respectively). At population level, the interpretation revealed that AV, TLCO-NO and FEV1 were the most important contributors to positive diagnosis. Personalized interpretations (Fig. 1) allow to verify the model’s plausibility in difficult cases with false negative/positive diagnosis and identify individual patterns of lung function impairments. Conclusion: Compared to the conventional approaches, our new method offers more advantages including ability of multivariate interpretation and valuable information for personalized treatment plan.

Objectif Les mouvements de la mandibule associes a l’effort respiratoire sont soumis a des variations conditionnees par les changements de stade de sommeil. Nous presentons les resultats d’une analyse de machine learning basee sur le seul signal mandibulaire pour le scoring des stades de sommeil. Methodes Le signal est acquis via un dispositif connecte Sunrise (Sunrise, Namur, Belgium) au cours d’une polysomnographie au laboratoire (PSG). Le modele decrit 4 etats : la veille (V), le sommeil lent leger (SLL), lent profond (SLP) et le sommeil paradoxal (SP). Il est entraine sur 707 417 segments de 30 sec. collectes chez 800 sujets suspects de SAS correspondant a 1134 heures de V, 2806 h. de SLL, 1052 h. de SLP et 902 h. de SP. Il est valide sur les donnees ulterieures chez 226 autres sujets. Resultats Le modele montre un niveau eleve de concordance segment par segment avec la PSG (Kappa = 0,71 (95 %CI : 0,59 to 0,80). Il fournit un niveau de concordance acceptable avec les variables de qualite de sommeil de la PSG : la mediane [95 %CI] de la mesure des biais est respectivement de −10,25 min. [−52,87 ; +19,00], de 0 min. [−23,37 ; +6,50], de −2,22 % [−11,06 ; +3,80] et de +7,20 % [−2,41 ; +21,26] pour le temps en SP, pour le temps total de sommeil (TST), pour le delai d’endormissement, pour l’efficience du sommeil et pour SP en % de TST. Conclusion L’analyse par intelligence artificielle du signal mandibulaire se prete bien a la stadification automatique du sommeil. Elle offre une solution ambulatoire peu onereuse pour apprecier sa qualite.

Background and Objective. The concentration of exhaled nitric oxide (eNO), reflecting the activity of inducible NO synthase in airway epithelium, has been found to increase in patients with obstructive sleep apnea (OSA). This study aimed to measure eNO concentration in patients with suspected OSA and to correlate different eNO parameters with clinical and sleep apnea characteristics.Methods. In this cross-sectional study, all patients underwent in-lab overnight polysomnography (PSG) and eNO measurement using a method of multiple flow rates before and after PSG (pre- and post-PSG).Results. According to the result of PSG, 82 persons were divided into two groups: control subjects (n=30;54±14years) and patients with OSA defined as apnea-hypopnea index (AHI) ≥ 5/hour (n=52;53±12years). Body mass index (BMI) and neck and abdomen circumferences of OSA patients were significantly higher than those from control subjects. In OSA group, post-PSG alveolar NO concentration (CANO) (5.3±1.9 ppb) was significantly higher than pre-PSG CANO (4.0±1.7 ppb;P<0.001). Significant correlations have been found between CANO and AHI (P<0.001) and between CANO and nadir SpO2(P<0.05). The daytime CANO value of more than 4.1 ppb can be used to screen symptomatic subjects for the presence of OSA with a high specificity of 93.3%.Conclusion. Our findings indicate CANO as a surrogate marker for OSA in persons with suggestive symptoms.

To assess distal/alveolar inflammation in patients with suggestive symptoms of obstructive sleep apnoea (OSA) using exhaled nitric oxide (NO) measured by two-compartment model (2-CM) after correction for axial NO back-diffusion (trumpet model).Ninety five patients suspected for OSA prospectively underwent pulmonary function test, overnight polysomnography (PSG), and exhaled NO measurement. Patients with apnoea-hypopnoea index (AHI) 5/hour were included in non-OSA group. Exhaled NO was repeatedly measured after PSG in 21 OSA patients and 8 non-OSA subjects.Alveolar NO concentration (C(ANO)) was significantly higher in OSA patients (n = 71; 4.07 ± 1.7 ppb) as compared with non-OSA subjects (n = 24; 2.24 ± 1.06 ppb; p0.0001) whilst maximal bronchial NO flux (J'awNO) and fractional exhaled NO (F(ENO)) did not differ between the two groups. C(ANO) was strongly associated to AHI (r = 0.701; p0.0001) and to recording time with SaO290% (ST-90%; r = 0.659; p0.0001) in OSA patients but not in non-OSA persons. The area under ROC curve for screening patients with OSA and significant nocturnal oxygen desaturation (ST-90% 1%) was 0.865 ± 0.036 (95% IC, 0.793-0.937; p0.0001). C(ANO) at 4.5 ppb could detect these patients with specificity of 94% and sensitivity of 46%. Increase of C(ANO) measured after PSG was significantly related to oxygen desaturation index (ST-90%) in OSA patients.Increased alveolar NO concentration was related to the severity of nocturnal oxygen desaturation in patients with OSA, linking the distal airway inflammation to intermittent hypoxia. (250 words).

Objective: Our study aims to apply a Machine learning (ML) approach to detect the presence of Interstitial Lung disease (ILD) in patients with systemic sclerosis (SSc), using combined data from multiple pulmonary function tests (PFT). Methods: PFT data (Spirometry, Plethysmography and DLNO-CO measurements, all converted into Z-score scale) were obtained in 273 patients with confirmed diagnosis of SSc and 50 healthy non-smokers. The main outcome is ILD, as determined by HRCT. An exhaustive feature selection was performed in R statistical programming language. This process consists of building many classification models (based on support vector machine algorithm) from every possible combination between the PFT indices, then voting for the one that shows the best performance (highest accuracy and lowest error) through a repeated cross-validation (10x10 iterations). Results: The best decision rule implies 7 parameters: DLNO, DLCO, VA, Vc, KCO, TLC and FVC (Figure) This model showed steady and good classification performance through 100 resampled iterations: AUC=0.85, balanced-accuracy=0.76, true positive rate=0.62, true negative rate=0.89, mean misclassification error=0.2, false negative rate=0.38 and false positive rate=0.11. Conclusion: Our results suggest that applying ML technique and multiple PFT data could improve the likelihood to detect early SSc patients with higher risk of ILD.

Chest surface EMG at diaphragmatic insertions (IC-EMG) is an alternative way for capturing respiratory effort (RE) during SAHOS.IC-EMG wasn9t investigated with regards to oesophageal crural diaphragmatic EMG (DI-EMG). Our study aimed to assess the similarity between IC and DI-EMG and the ability of IC-EMG to classify RE episodes. Methods 14 adults SAHOS underwent a lab-based PSG study with IC-EMG and DI-EMG. 70 periods of normal breathing (NB),309 RE events (including 135 RERA,70 OH and104 OA) were randomly selected for analysis in R-studio. After noise reduction, AUC and peak-to-peak distance (d) were calculated for both signals. Similarity between 2 signals was evaluated by cross-correlation as a function of the lag of one relative to the other. Correlation and d-value were compared among 4 groups of RE levels. Ability of each signal to detect RE was evaluated by multiclass CART algorithm. Results Patients have a mean age of 42.8±10.7 yrs and BMI of 31.1±8.6 kg/m2.Their averaged TST and AHI were 347±51.9 min and 35.3±25.1 n/h respectively. IC and DI-EMG signals are cross-correlated in either NB or RE events (r=0.6 to 0.86) by a lag of 0.5-0.9 second. AUC was also correlated (r=0.96). IC showed a significant difference in d-value among 4 groups (NB:14.6 vs RERA:21.9, OH:19.8 and OA:44.2). Using cut-offs at 17.8 and 31.5, IC distance allows classifying RERA, OAH and NB with accuracy, inter-class agreement and specificity of 0.8, 0.63 and 0.91, respectively. Conclusions IC-EMG is a useful method to assess RE and the obstructive nature of AH .

Sy Duong-Quy,1–3 Thuc Vu-Minh,4 Thong Hua-Huy,1 Tram Tang-Thi-Thao,3 Khiet Le-Quang,3 Dinh Tran-Thanh,3 Nhu Doan-Thi-Quynh,3 Nhat-Nam Le-Dong,5 Timothy J Craig,2 Anh-Tuan Dinh-Xuan1 1Department of Respiratory Physiology, Cochin Hospital, Paris Descartes University, Sorbonne Paris Cité, Paris, France; 2Department of Medicine, Penn State University, Hershey, PA, USA; 3Bio-Medical Research Center, Lam Dong Medical College, Dalat, 4Department of Immuno-Allergology, ENT National Institute, Hanoi, Vietnam; 5Department of Pulmonology, St Elisabeth Hospital, Namur, Belgium Background: The measure of fractional exhaled nitric oxide (FENO) in the airways is a useful tool to guide the diagnosis and titration of inhaled corticosteroids in patients with asthma. However, its role in diagnosis of allergic rhinitis (AR), especially in subjects with asthma, is not well established. Objective: To study the cutoff of nasal FENO in the diagnosis of subjects with AR and AR-asthma compared to age-matched subjects without AR or asthma and its correlations with the clinical and functional characteristics. Methods: The study was cross sectional and descriptive. Subjects were grouped into control subjects, AR, and AR-asthma, based on the inclusion criteria. Exhaled NO (nasal FENO, bronchial FENO, and alveolar concentration of NO) was measured by multiple flow electroluminescence device. Results: Six hundred twenty-eight subjects were included: 217 control subjects (children: n=98, 10±4 years; adults: n=119, 50±16 years), 168 subjects with AR (children: n=54, 10±3 years; adults: n=114, 49±15 years), and 243 subjects with AR-asthma (children: n=115, 10±3 years; adults: n=128, 51±14 years). Nasal peak inspiratory flow and peak expiratory flow were lower in subjects with AR and AR-asthma than in control subjects (P

Background The patterns of mandibular movements (MM) during sleep can be used to identify increased respiratory effort periodic large-amplitude MM (LPM), and cortical arousals associated with “sharp” large-amplitude MM (SPM). We hypothesized that Cheyne Stokes breathing (CSB) may be identified by periodic abnormal MM patterns. The present study aims to evaluate prospectively the concordance between CSB detected by periodic MM and polysomnography (PSG) as gold-standard. The present study aims to evaluate prospectively the concordance between CSB detected by periodic MM and polysomnography (PSG) as gold-standard. Methods In 573 consecutive patients attending an in-laboratory PSG for suspected sleep disordered breathing (SDB), MM signals were acquired using magnetometry and scored manually while blinded from the PSG signal. Data analysis aimed to verify the concordance between the CSB identified by PSG and the presence of LPM or SPM. The data were randomly divided into training and validation sets (985 5-min segments/set) and concordance was evaluated using 2 classification models. Results In PSG, 22 patients (mean age ± SD: 65.9 ± 15.0 with a sex ratio M/F of 17/5) had CSB (mean central apnea hourly indice ± SD: 17.5 ± 6.2) from a total of 573 patients with suspected SDB. When tested on independent subset, the classification of CSB based on LPM and SPM is highly accurate (Balanced-accuracy = 0.922, sensitivity = 0.922, specificity = 0.921 and error-rate = 0.078). Logistic models based odds-ratios for CSB in presence of SPM or LPM were 172.43 (95% CI: 88.23–365.04; p

Objectif La position de la mandibule et ses mouvements verticaux pendant le sommeil (VMM) sont le resultat d’une interaction specifique de ses muscles abaisseurs ou elevateurs. Nous avons etudie l’effet causal de VMM sur les changements de pression nasale captures par les lunettes (FPres) a l’occasion d’un micro-eveil et d’un changement d’activite EMG de surface des muscles antagonistes de la mandibule (sEMG). Methodes Les signaux bruts (VMM, FPres et sEMG) ont ete extraits a partir de 100 fragments PSG de duree moyenne de 2 minutes puis exposes a un algorithme de segmentation pour localiser les evenements d’interet. L’effet causal de VMM sur FPres est verifie par les 4 criteres de Bradford Hill : temporalite, force de l’association coherence et une relation dose–effet. Resultats Un effet causal significatif de VMM sur FPres a ete observe dans 80/100 fragments. Le deplacement de mandibule s’est toujours developpe avant la modification de flux. L’ouverture buccale est associee a une perte de flux (− 24,1 μv (− 17,6 a − 30,6) ; p Conclusion Le flux respiratoire pendant le sommeil est conditionne par la transposition mandibulaire, qui a son tour est determinee par l’activite EMG des muscles antagonistes. Controler la dimension verticale de ce deplacement apparait critique pour le succes therapeutique de l’orthese d’avancee mandibulaire.

Systemic sclerosis (SSc) is a connective-tissue disease characterized by vascular injury, immune-system disorders, and excessive fibrosis of the skin and multiple internal organs. Recent reports found that RhoA/Rho-kinase (ROCK) pathway is implicated in various fibrogenic diseases. Intradermal injection of hypochlorous acid (HOCl)-generating solution induced inflammation, autoimmune activation, and fibrosis, mimicking the cutaneous diffuse form of SSc in humans. Our study aimed firstly to describe pulmonary inflammation and fibrosis induced by HOCl in mice, and secondly to determine whether fasudil, a selective inhibitor of ROCK, could prevent lung and skin fibroses in HOCl-injected mice.Female C57BL/6 mice received daily intradermal injection of hypochlorous acid (HOCl) for 6 weeks to induce SSc, with and without daily treatment with fasudil (30 mg·kg(-1)·day(-1)) by oral gavage.HOCl intoxication induced significant lung inflammation (macrophages and neutrophils infiltration), and fibrosis. These modifications were prevented by fasudil treatment. Simultaneously, HOCl enhanced ROCK activity in lung and skin tissues. Inhibition of ROCK reduced skin fibrosis, expression of α-smooth-muscle actin and 3-nitrotyrosine, as well as the activity of ROCK in the fibrotic skin of HOCl-treated mice, through inhibition of phosphorylation of Smad2/3 and ERK1/2. Fasudil significantly decreased the serum levels of anti-DNA-topoisomerase-1 antibodies in mice with HOCl-induced SSc.Our findings confirm HOCl-induced pulmonary inflammation and fibrosis in mice, and provide further evidence for a key role of RhoA/ROCK pathway in several pathological processes of experimental SSc. Fasudil could be a promising therapeutic approach for the treatment of SSc.

Pulmonary hypertension (PH) is a complex disorder resulting from many etiologies that cause disturbances of normal pulmonary haemodynamics. Recent breakthroughs have led to a better understanding of the pathophysiology of the disease. In PH, haemodynamic disturbances are closely linked to structural changes and excessive remodeling of pulmonary vessels, leading to progressive narrowing of the pulmonary vascular lumen. Imbalances between pulmonary vasoconstrictors and vasodilators on the one hand, and factors favoring cell proliferation and apoptosis on the other hand, probably account for most cases of PH. This review aims to update readers with the current knowledge on the molecular physiopathology of PH and how this can progress the therapeutic of this disorder.

Nitric oxide metabolites (NOx) in serum, and alveolar concentration of NO (CA(NO)), are markers of inflammation and alveolitis, respectively, in systemic sclerosis (SSc). We prospectively evaluated the usefulness of both NOx and CA(NO) to assess lung involvement and skin fibrosis in SSc. Serum NOx, and CA(NO) measured by two different methods, namely the two-compartment (2CM) and the "trumpet" models (TM), were concomitantly assessed in 65 patients with SSc and 17 healthy controls. Whilst serum NOx remained comparable between groups, CA(NO) were significantly higher in SSc patients (n=65, 6.7ppb; 4.8-9.7 and 5.9ppb; 3.9-8.9) as compared with controls (n=17, 3.0ppb; 2.0-3.8 and 1.8ppb; 1.1-2.9, p

Exhaled nitric oxide (NO) is increased as a result of lung inflammation, which in turn causes subsequent interstitial lung disease in patients with systemic sclerosis (SSc). However, the exact time course of inflammatory and fibrotic changes in the SSc lung has not yet been described. Our objective was to assess the chronological evolution of lung inflammatory and fibrotic processes in mice pre-treated with hypochlorous acid (HOCl) or bleomycin. C57BL/6 mice were randomized into three groups receiving subcutaneous injections of HOCl, bleomycin, or PBS for 2, 4 or 6 weeks. Exhaled NO (eNO) was measured at the end of each injection period and after 2 resting weeks without injection (8 week group). Mice were then sacrificed to obtain skin and lung tissues to measure fibrotic changes and NO synthases (NOS) expression. Increased eNO, inducible NOS and nitrotyrosine expression in bronchial epithelium, lung neutrophils and macrophages were observed at early phases in both HOCl- and bleomycin-treated mice. Conversely, lung vascular endothelial NOS expression decreased significantly at 6th and 8th weeks. Skin fibrosis was significantly increased from the 4th week and lung fibrosis from 6th week. We conclude that lung inflammation occurs early after injury as reflected by increased exhaled NO and inducible NOS expression, and precedes fibrotic changes in skin and lungs of mice pre-treated with bleomycin and HOCl. Early detection and treatment of pulmonary inflammation might be useful in preventing subsequent occurrence of lung fibrosis in SSc patients.