RespNet: A deep learning model for extraction of respiration from photoplethysmogram

Ravichandran, Vignesh; Murugesan, Balamurali; Balakarthikeyan, Vaishali; Ram, Keerthi; S.P, Preejith; Joseph, Jayaraj; Sivaprakasam, Mohanasankar

doi:10.1109/embc.2019.8856301

Cited by 40 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In an era where both the computation speed and deep neural networks are expanding in a tremendously fast pace, high dimensional unveiled patterns are expected to be leveraged in the extraction of human respiration [ 242 ], detecting diseases [ 243 , 244 ], classify apnea events [ 245 ], and score illness gravity [ 160 , 246 ]. This direction has recently started gaining attention by researchers [ 242 , 243 , 244 , 245 , 246 ]. However, this innovation continues to be challenged by inherent factors in the healthcare market, making the road to full artificial intelligence integration difficult.…”

Section: Discussionmentioning

confidence: 99%

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration

Rehouma

Noumeir

Essouri

et al. 2020

Sensors

View full text Add to dashboard Cite

Assessment of respiratory function allows early detection of potential disorders in the respiratory system and provides useful information for medical management. There is a wide range of applications for breathing assessment, from measurement systems in a clinical environment to applications involving athletes. Many studies on pulmonary function testing systems and breath monitoring have been conducted over the past few decades, and their results have the potential to broadly impact clinical practice. However, most of these works require physical contact with the patient to produce accurate and reliable measures of the respiratory function. There is still a significant shortcoming of non-contact measuring systems in their ability to fit into the clinical environment. The purpose of this paper is to provide a review of the current advances and systems in respiratory function assessment, particularly camera-based systems. A classification of the applicable research works is presented according to their techniques and recorded/quantified respiration parameters. In addition, the current solutions are discussed with regards to their direct applicability in different settings, such as clinical or home settings, highlighting their specific strengths and limitations in the different environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration

Rehouma

Noumeir

Essouri

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…This could be realised by having the individual wear a chest band in addition to a pulse capture smart watch for an initial “training” period and breathing at a range of respiratory rates, with the chest strap no longer being required after the model was successfully trained. We previously demonstrated that a single model was sufficient to predict respiratory rate for a single participant over the period of a month’s time [ 6 ].…”

Section: Discussionmentioning

confidence: 99%

“…We compared two machine learning architectures to extract the relative volume trace from the pulse signal: (1) the U-Net architecture, adapted from the original methods described by Rivichandran et al [ 6 ] and (2) an LSTM network, previously described by Prinable et al [ 8 ]. The LSTM network is an architecture that has gated connections designed to learn patterns in historical data by regulating information flow, while a U-Net learns patterns by passing information through a series of filters.…”

Section: Methodsmentioning

confidence: 99%

“…One challenge facing reliable application of pulse oximeter sensors is the accurate extraction of the breathing signal from the photoplethysmogram (PPG) signal. State-of-the-art machine learning algorithms have shown early promise in achieving this, in particular the U-shaped network (U-Net) [ 6 ] and Long Short-Term Memory (LSTM) architectures [ 7 , 8 ]. In our previous work [ 8 ], we demonstrated for the first time that detailed respiratory metrics could also be extracted from a volume trace acquired during normal, tidal breathing using a LSTM network in healthy participants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Derivation of Respiratory Metrics in Health and Asthma

Prinable

Jones

Boland

et al. 2020

Sensors

View full text Add to dashboard Cite

The ability to continuously monitor breathing metrics may have indications for general health as well as respiratory conditions such as asthma. However, few studies have focused on breathing due to a lack of available wearable technologies. To examine the performance of two machine learning algorithms in extracting breathing metrics from a finger-based pulse oximeter, which is amenable to long-term monitoring. Methods: Pulse oximetry data were collected from 11 healthy and 11 with asthma subjects who breathed at a range of controlled respiratory rates. U-shaped network (U-Net) and Long Short-Term Memory (LSTM) algorithms were applied to the data, and results compared against breathing metrics derived from respiratory inductance plethysmography measured simultaneously as a reference. Results: The LSTM vs. U-Net model provided breathing metrics which were strongly correlated with those from the reference signal (all p < 0.001, except for inspiratory: expiratory ratio). The following absolute mean bias (95% confidence interval) values were observed (in seconds): inspiration time 0.01(−2.31, 2.34) vs. −0.02(−2.19, 2.16), expiration time −0.19(−2.35, 1.98) vs. −0.24(−2.36, 1.89), and inter-breath intervals −0.19(−2.73, 2.35) vs. −0.25(2.76, 2.26). The inspiratory:expiratory ratios were −0.14(−1.43, 1.16) vs. −0.14(−1.42, 1.13). Respiratory rate (breaths per minute) values were 0.22(−2.51, 2.96) vs. 0.29(−2.54, 3.11). While percentage bias was low, the 95% limits of agreement was high (~35% for respiratory rate). Conclusion: Both machine learning models show strong correlation and good comparability with reference, with low bias though wide variability for deriving breathing metrics in asthma and health cohorts. Future efforts should focus on improvement of performance of these models, e.g., by increasing the size of the training dataset at the lower breathing rates.

show abstract

“…Long term sleep apnea can cause system dysfunction and multiple diseases, such as increasing the risk of obesity and heart disease, and even sudden death [2]. According to the World Health Group, the high-risk groups of sleep respiratory diseases mainly involve obese patients and the elderly [3]. In the middle-aged men and women in the United States, OSA incidence the number of sleep disordered breathing patients in the world is a large group, and nearly 80-90% of them have apnea syndrome.…”

Section: Introductionmentioning

confidence: 99%

OSA Patient Monitoring System Based on the Internet of Things Framework

Cai¹,

Le²,

Ruan³

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper presents an OSA patient interactive monitoring system based on the Internet of Things (IoT) framework. This system allows OSA patients to get timely rescue when they are sleepy outside. Because the Beidou position marker has an interactive function, it can reduce the anxiety of the patient while waiting for the rescue. At the same time, if a friend helps the OSA patients to call the doctor, the friend can also report the patient's condition in time. This system uses the popular IoT framework. At the bottom is the data acquisition layer, which uses wearable sensors to collect vital signs from patients, with a focus on ECG and SpO2 signals. The middle layer is the network layer that transmits the collected physiological signals to the Beidou indicator using the Bluetooth Low Energy (BLE) protocol. The top layer is the application layer, and the application layer uses the mature rescue interactive platform of Beidou. Since the GPS indicator has not included the communication satellite, So it has no SMS function. OSA patients can only passively wait for a rescue. Moreover, due to the lack of satellites in Asia and the insufficient density of the ground-enhanced system, the positioning error of OSA patients is large. The Beidou system developed by China itself, the main coverage of the satellite is in Asia, and is equipped with a high-density ground-based augmentation system. Therefore, the Beidou model improves the positioning accuracy and is equipped with a special communication satellite, which increases the short message interaction function. Therefore, patients can report disease progression in time while waiting for a rescue. After our simulation test, the effectiveness of the OSA patient rescue monitoring system based on the Internet of Things framework and the positioning accuracy of OSA patients have been greatly improved. Especially when OSA patients work outdoors, the cell phone base station signal coverage is relatively weak. The satellite signal is well covered, plus the SMS function of the Beidou indicator. Therefore, the system can be used to provide timely patient progress and provide data support for the medical rescue team to provide a more accurate rescue plan. After a comparative trial, the rescue rate of OSA patients using the detection device of this system was increased by 15 percentage points compared with the rescue rate using only GPS satellite phones.

show abstract

RespNet: A deep learning model for extraction of respiration from photoplethysmogram

Cited by 40 publications

References 14 publications

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration

Derivation of Respiratory Metrics in Health and Asthma

OSA Patient Monitoring System Based on the Internet of Things Framework

Contact Info

Product

Resources

About