In-Home Diagnosis of Obstructive Sleep Apnea Using Automatic Video Analysis / Diagnóstico domiciliario de apnea obstructiva del sueño utilizando el análisis automático de vídeo

Study objectives: To evaluate the diagnostic accuracy of a non-invasive technology based on image processing for the identification of obstructive sleep apnea (OSA) and its severity at patients' home. METHODS: Observational, prospective, diagnostic accuracy study to evaluate the degree of measure agreement between Sleepwise (SW), in-laboratory attended polysomnography (PSG) and a home sleep apnea test (HSAT). 38 consecutive subjects with suspected OSA referred as outpatients to the sleep unit were recruited from September 2016 to September 2017. All patients underwent in-laboratory attended PSG and image processing with SW simultaneously overnight. Subsequently, a HSAT and image processing with SW were performed simultaneously overnight at patients' home, and the 2 nights after, patients underwent only image processing with SW consecutively. RESULTS: In-laboratory polysomnography and SW had a Lin's concordance correlation coefficient of 0.933 and a Kappa of 0.930. Between HSAT and SW the Lin's concordance correlation coefficient was 0.842 and a Kappa of 0.571. Agreement between two consecutive nights with SW recording showed a Lin's concordance correlation coefficient of 0.923 and a Kappa of 0. 837. CONCLUSIONS: SW was highly accurate for non-invasive and automatic diagnosis of OSA in outpatients compared to standard methods for OSA diagnosis either in-laboratory attended PSG or HSAT. SW proved to be a technique with repeatable and concordant results on different nights for the same patient. We conclude SW is a non-invasive, easy-to-use, portable, effective and highly accurate system for the in-home diagnosis of OSA

OBJETIVOS: Evaluar la precisión diagnóstica de una tecnología no invasiva basada en el procesamiento de imágenes para la identificación de la apnea obstructiva del sueño (AOS) y su gravedad en el domicilio de los pacientes. MÉTODOS: Estudio observacional, prospectivo y de precisión diagnóstica para evaluar el grado de concordancia entre las mediciones de Sleepwise (SW), polisomnografía (PSG) asistida en el laboratorio y poligrafía respiratoria domiciliaria (PRD). Se reclutaron 38 sujetos consecutivos con sospecha de AOS, referidos como pacientes ambulatorios a la unidad de sueño entre septiembre de 2016 y septiembre de 2017. Se les realizó a todos una PSG y procesamiento de imagen con SW durante la noche en el laboratorio. Posteriormente, se realizó una PRD y procesamiento de imágenes con SW de forma simultánea durante la noche en su domicilio, y las 2 noches siguientes los pacientes se sometieron solo a procesamiento de imágenes con SW. RESULTADOS: La polisomnografía en el laboratorio y el SW mostraron un coeficiente de correlación de concordancia de Lin de 0,933 y un Kappa de 0,930. Entre la PRD y el SW el coeficiente de correlación de concordancia de Lin fue de 0,842 y un Kappa de 0,571. La concordancia entre las 2 noches consecutivas de grabación con el SW mostró un coeficiente de correlación de concordancia de Lin de 0,923 y un Kappa de 0,837. CONCLUSIONES: El SW mostró alta precisión para el diagnóstico no invasivo y automatizado de la AOS en pacientes ambulatorios en comparación con los métodos estándar para el diagnóstico de la AOS, ya sean la PSG asistida en el laboratorio o la PRD. El SW demostró ser una técnica con resultados reproducibles y concordantes en diferentes noches para el mismo paciente. Concluimos que la SW es un sistema no invasivo, fácil de usar, portátil, eficaz y altamente preciso para el diagnóstico domiciliario de la AOS

In-Home Diagnosis of Obstructive Sleep Apnea Using Automatic Video Analysis.

STUDY OBJECTIVES: To evaluate the diagnostic accuracy of a non-invasive technology based on image processing for the identification of obstructive sleep apnea (OSA) and its severity at patients' home. METHODS: Observational, prospective, diagnostic accuracy study to evaluate the degree of measure agreement between Sleepwise (SW), in-laboratory attended polysomnography (PSG) and a home sleep apnea test (HSAT). 38 consecutive subjects with suspected OSA referred as outpatients to the sleep unit were recruited from September 2016 to September 2017. All patients underwent in-laboratory attended PSG and image processing with SW simultaneously overnight. Subsequently, a HSAT and image processing with SW were performed simultaneously overnight at patients' home, and the 2 nights after, patients underwent only image processing with SW consecutively. RESULTS: In-laboratory polysomnography and SW had a Lin's concordance correlation coefficient of 0.933 and a κ of 0.930. Between HSAT and SW the Lin's concordance correlation coefficient was 0.842 and a κ of 0.571. Agreement between two consecutive nights with SW recording showed a Lin's concordance correlation coefficient of 0.923 and a κ of 0. 837. CONCLUSIONS: SW was highly accurate for non-invasive and automatic diagnosis of OSA in outpatients compared to standard methods for OSA diagnosis either in-laboratory attended PSG or HSAT. SW proved to be a technique with repeatable and concordant results on different nights for the same patient. We conclude SW is a non-invasive, easy-to-use, portable, effective and highly accurate system for the in-home diagnosis of OSA.

Automatic Video Analysis for Obstructive Sleep Apnea Diagnosis.

STUDY OBJECTIVES: We investigated the diagnostic accuracy for the identification of obstructive sleep apnea (OSA) and its severity of a noninvasive technology based on image processing (SleepWise). METHODS: This is an observational, prospective study to evaluate the degree of agreement between polysomnography (PSG) and SleepWise. We recruited 56 consecutive subjects with suspected OSA who were referred as outpatients to the Sleep Unit of the Hospital Universitari Germans Trias i Pujol (HUGTiP) from January 2013 to January 2014. All patients underwent laboratory PSG and image processing with SleepWise simultaneously the same night. Both PSG and SleepWise analyses were carried independently and blindly. RESULTS: We analyzed 50 of the 56 patients recruited. OSA was diagnosed through PSG in a total of 44 patients (88%) with a median apnea-hypopnea index (AHI) of 25.35 (24.9). According to SleepWise, 45 patients (90%) met the criteria for a diagnosis of OSA, with a median AHI of 22.8 (22.03). An analysis of the ability of PSG and SleepWise to classify patients by severity on the basis of their AHI shows that the two diagnostic systems distribute the different groups similarly. According to PSG, 23 patients (46%) had a diagnosis of severe OSA, 11 patients (22%) moderate OSA, and 10 patients (20%) mild OSA. According to SleepWise, 20, 13, and 12 patients (40%, 26%, and 24%, respectively) had a diagnosis of severe, moderate, and mild OSA respectively. For OSA diagnosis, SleepWise was found to have sensitivity of 100% and specificity of 83% in relation to PSG. The positive predictive value was 97% and the negative predictive value was 100%. The Bland-Altman plot comparing the mean AHI values obtained through PSG and SleepWise shows very good agreement between the two diagnostic techniques, with a bias of -3.85, a standard error of 12.18, and a confidence interval of -0.39 to -7.31. CONCLUSIONS: SleepWise was reasonably accurate for noninvasive and automatic diagnosis of OSA in outpatients. SleepWise determined the severity of OSA with high reliability. The current study including simultaneous laboratory PSG and SleepWise processing image is proposed as a reasonable validation standard.