Non-Contact Monitoring of Respiration in the Neonatal Intensive Care Unit

Jorge, João; Villarroel, Mauricio; Chaichulee, Sitthichok; Guazzi, Alessandro; Davis, Sara; Green, Gabrielle; McCormick, Kenny; Tarassenko, Lionel

doi:10.1109/fg.2017.44

Cited by 56 publications

(40 citation statements)

References 231 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are other research studies with interests on the use of contactfree systems to estimate respiratory rate. These include the use of thermal and depth imaging camera video [16], a multimodal system containing pyro-electric infrared and vibration sensors [17] and video images to monitor respiration in the neonatal intensive care unit [18].…”

Section: Introductionmentioning

confidence: 99%

Accelerometry-Based Estimation of Respiratory Rate for Post-Intensive Care Patient Monitoring

et al. 2018

Self Cite

View full text Add to dashboard Cite

This paper evaluates the use of accelerometers for continuous monitoring of respiratory rate (RR), which is an important vital sign in post-intensive care patients or those inside the intensive care unit (ICU). The respiratory rate can be estimated from accelerometer and photoplethysmography (PPG) signals for patients following ICU discharge. Due to sensor faults, sensor detachment, and various artifacts arising from motion, RR estimates derived from accelerometry and PPG may not be sufficiently reliable for use with existing algorithms. This paper described a case study of 10 selected patients, for which fewer RR estimates have been obtained from PPG signals in comparison to those from accelerometry. We describe an algorithm for which we show a maximum mean absolute error between estimates derived from PPG and accelerometer of 2.56 breaths/min. Our results obtained using the 10 selected patients are highly promising for estimation of RR from accelerometers, where significant agreements have been observed with the PPG-based RR estimates in many segments and across various patients. We present this research as a step towards producing reliable RR monitoring systems using low-cost mobile accelerometers for monitoring patients inside the ICU or on the ward (post-ICU). Index Terms-Respiratory rate (RR), accelerometer, photoplethysmography (PPG), adaptive line enhancer (ALE), autoregressive (AR).

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerometry-Based Estimation of Respiratory Rate for Post-Intensive Care Patient Monitoring

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our algorithm enables fast detection of apneas, with online detection latencies estimated to be between 3 and 16 seconds, while latencies of >20 s are common in other studies [18,19]. The difference in detection delay can be explained by the respiration-free signal window needed by most other algorithms to measure the absence of periodicity and detect an apnea.…”

Section: Discussionmentioning

confidence: 90%

“…There are several modes of remote respiratory monitoring using different sensors, but there are few to detect apneas. Algorithms aiming at remote apnea detection use radar [8], sonar [9], capacitance sensors [10], infrared sensors [11,12], depth sensors [13][14][15], and video [16][17][18][19]. Video cameras are suitable for safety monitoring, as they are relatively cheap and sensitive to movement, even at longer distance, provided they have suitable resolution.…”

Section: Introductionmentioning

confidence: 99%

Automated non-contact detection of central apneas using video

Geertsema

Visser

Sander

et al. 2020

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Central apneas occurring in the aftermath of epileptic seizures may lead to sudden death. The contact-sensors currently used to detect apneas are not always suitable or tolerated. We developed a robust automated non-contact algorithm for real-time detection of central apneas using video cameras. One video recording with simulated apneas and nine with real-life apneas associated with epileptic seizures, each recorded from 3-4 angles, were used to develop the algorithm. Videos were preprocessed using optical flow, from which translation, dilatation and shear rates were extracted. Presence of breathing motions was quantified in the dominant time-frequency spectrum by calculating the relative power in the respiratory range (0.1-1 Hz). Sigmoid modulation was calculated over different scales to quantify sigmoid-like drops in the respiratory range power. Each sigmoid modulation maximum constitutes a possible apnea event. Two event features were calculated to enable distinction between apnea events and movements: modulation maximum amplitude and total spectral power modulation at the time of the event. An ensemble support vector machine was trained to classify events using a bagging procedure and validated in a leave-one-subject-out cross validation procedure. All apnea episodes were detected in the signals from at least one camera angle. Integrating camera inputs capturing different angles increased overall detection sensitivity (>90%). Overall detection specificity of >99% was achieved with both individual cameras and integrated camera inputs. These results suggest that it is feasible to detect central apneas automatically in video, using this algorithm. When validated, the algorithm might be used as an online remote apnea detector for safety monitoring.

show abstract

“…In [20], Jorge et al developed a novel method for the extraction of respiration from camera-based measurements taken from the top-view of an incubator for critically-ill or premature infants, similar system was presented by Aarts et al in [10]. Moreover in [4], Tarassenko et al have been able to obtain estimates of heart rate and respiratory rate and preliminary results on changes in oxygen saturation from double-monitored patients undergoing haemodialysis in the Oxford Kidney Unit.…”

Section: Related Workmentioning

confidence: 99%

“…Historically, it was believed that the small variations in the received signal (in both RF-and imaging-based wireless methods) were because of noise and undesirable (and unpredictable) reflections and scattering from the environment. However, as the technology in sensing and signal processing improved, researchers have discovered that some of these variations are actually from humans physiological movements (heartbeats and respiration) and that they were able to extract this information (RF-based in [2], [3], [7], [9], [16]- [19], Imaging-based in [4], [12]- [14], [20]- [23]). Given these studies, we investigated if it is possible to extract the physiological data from visible light signal variations and to monitor the vital signs remotely.…”

Section: Introductionmentioning

confidence: 99%

Non-Contact Vital Signs Monitoring Through Visible Light Sensing

Abuella

Ekin

2020

IEEE Sensors J.

View full text Add to dashboard Cite

In this paper, we present a wireless system for monitoring human vital signs like breathing and heartbeat via visible light sensing (VLS). Typical techniques for tracking heathcondition require body contact and most of these techniques are intrusive in nature. Body contact might irritate the patient's skin and he/she might feel uncomfortable while sensors are touching their body. However, in this method, we can estimate the breathing and heartbeat rates without any body contact using a photo-detector. Vitals monitoring using VLS make use of the idea that reflected light signal off the human body received at the photo-detector will be affected by the chest motion during heartbeats and breathing. We implemented the system using off-the-shelf photo-detector and a signal acquisition system and obtained the results for different people and in different scenarios. We found out that the accuracy of our system compared to FDA approved equipment to measure heartbeats and breathing rate is 94%. This system can be used in various domains and applications in medical facilities and in residential homes.A provisional patent (US#62/639,524) has been obtained for this work.

show abstract

Non-Contact Monitoring of Respiration in the Neonatal Intensive Care Unit

Cited by 56 publications

References 231 publications

Accelerometry-Based Estimation of Respiratory Rate for Post-Intensive Care Patient Monitoring

Accelerometry-Based Estimation of Respiratory Rate for Post-Intensive Care Patient Monitoring

Automated non-contact detection of central apneas using video

Non-Contact Vital Signs Monitoring Through Visible Light Sensing

Contact Info

Product

Resources

About