Contactless Optical Detection of Nocturnal Respiratory Events

Alić, Belmin; Zauber, Tim; Zhang, Chen; Wang, Liao; Wildenauer, Alina; Leosz, Noah; Eggert, Torsten; Dietz-Terjung, Sarah; Sutharsan, Sivagurunathan; Weinreich, Gerhard; Schöbel, Christoph; Notni, Gunther; Wiede, Christian; Seidl, Karsten

doi:10.5220/0011694400003417

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2,3 Accurate assessment of sleep stages and monitoring for underlying respiratory abnormalities are important to diagnosing and treating sleep disorders. 4 The current gold standard is the acute or long-term monitoring of various vital signs by polysomnography (PSG). 5 One of the important vital signs, peripheral oxygen saturation (SpO 2 ), shows the ratio of oxygenated hemoglobin to total hemoglobin in the blood, which in healthy individuals should be in the range of 95%-100%.…”

Section: Introductionmentioning

confidence: 99%

Oxygen saturation estimation from near-infrared multispectral video data using 3D convolutional residual networks

Wang¹,

Zhang²,

Sun³

et al. 2023

Multimodal Sensing and Artificial Intelligence: Technologies and Applications III

View full text Add to dashboard Cite

Non-contact methods can expand the application scenarios of blood oxygen measurement with better hygiene and comfort, but the traditional non-contact methods are usually less accurate. In this study a novel noncontact approach for measuring peripheral oxygen saturation (SpO 2 ) using deep learning and near-infrared multispectral videos is proposed. After a series of data processing including shading correction, global detrending and spectral channel normalization to reduce the influences from illumination non-uniformity, ambient light, and skin tone, the preprocessed video data are split into half-second clips (30 frames) as input of the 3D convolutional residual network. In the experiment, multispectral videos in 25 channels of hand palms from 7 participants were captured. The experimental results show that the proposed approach can accurately estimate SpO 2 from nearinfrared multispectral videos, which demonstrates the agreement with commercial pulse oximeter. The study also evaluated the performance of the approach with different combinations of near-infrared channels.

show abstract

Section: Introductionmentioning

confidence: 99%

Oxygen saturation estimation from near-infrared multispectral video data using 3D convolutional residual networks

Wang¹,

Zhang²,

Sun³

et al. 2023

Multimodal Sensing and Artificial Intelligence: Technologies and Applications III

View full text Add to dashboard Cite

show abstract

Validation of the Sleepiz One + as a radar-based sensor for contactless diagnosis of sleep apnea

Gross-Isselmann,

Eggert,

Wildenauer

et al. 2024

Sleep Breath

View full text Add to dashboard Cite

Purpose The cardiorespiratory polysomnography (PSG) is an expensive and limited resource. The Sleepiz One + is a novel radar-based contactless monitoring device that can be used e.g. for longitudinal detection of nocturnal respiratory events. The present study aimed to compare the performance of the Sleepiz One + device to the PSG regarding the accuracy of apnea–hypopnea index (AHI). Methods From January to December 2021, a total of 141 adult volunteers who were either suspected of having sleep apnea or who were healthy sleepers took part in a sleep study. This examination served to validate the Sleepiz One + device in the presence and absence of additional SpO2 information. The AHI determined by the Sleepiz One + monitor was estimated automatically and compared with the AHI derived from manual PSG scoring. Results The correlation between the Sleepiz-AHI and the PSG-AHI with and without additional SpO2 measurement was rp = 0.94 and rp = 0,87, respectively. In general, the Bland–Altman plots showed good agreement between the two methods of AHI measurement, though their deviations became larger with increasing sleep-disordered breathing. Sensitivity and specificity for recordings without additional SpO2 was 85% and 88%, respectively. Adding a SpO2 sensor increased the sensitivity to 88% and the specificity to 98%. Conclusion The Sleepiz One + device is a valid diagnostic tool for patients with moderate to severe OSA. It can also be easily used in the home environment and is therefore beneficial for e.g. immobile and infectious patients. Trial registration number and date of registration for prospectively registered trials This study was registered on clinicaltrials.gov (NCT04670848) on 2020–12-09.

show abstract

Advancing Sleep Diagnostics: Contactless Multi-Vital Signs Continuous Monitoring with a Multimodal Camera System in Clinical Environment

Liao,

Zhang,

Alić

et al. 2024

2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA)

View full text Add to dashboard Cite

Contactless Optical Detection of Nocturnal Respiratory Events

Cited by 3 publications

References 0 publications

Oxygen saturation estimation from near-infrared multispectral video data using 3D convolutional residual networks

Oxygen saturation estimation from near-infrared multispectral video data using 3D convolutional residual networks

Validation of the Sleepiz One + as a radar-based sensor for contactless diagnosis of sleep apnea

Advancing Sleep Diagnostics: Contactless Multi-Vital Signs Continuous Monitoring with a Multimodal Camera System in Clinical Environment

Contact Info

Product

Resources

About