Deep learning for predicting respiratory rate from biosignals

Kumar, Amit; Ritam, M.; Han, Lina; Guo, Sen; Chandra, Rohitash

doi:10.1016/j.compbiomed.2022.105338

Cited by 58 publications

(29 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RR estimation is closely related to converting to bpm by multiplying the respiratory rate by 4 for more than 15 s [ 20 ]. For this reason, we can use the breathing frequency to obtain an automated feature vector from the power spectral based on the autocorrelation function.…”

Section: Exact Gaussian Process Regression (Egpr) Based Hybrid Featur...mentioning

confidence: 99%

“…Additionally, RR estimation, including vital signals using a generative boosting long short-term memory network (LSTM), was proposed by Liu et al [ 19 ]. Kumar et al [ 20 ] introduced an algorithm for RR estimation using PPG and ECG signals based on the LSTM technique. This method is widely used in ML with time-series data and has particularly attracted attention in healthcare, such as for blood pressure and HR estimations based on PPG signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual-Sensor Signals Based Exact Gaussian Process-Assisted Hybrid Feature Extraction and Weighted Feature Fusion for Respiratory Rate and Uncertainty Estimations

Lee

Moon

Al-antari

et al. 2022

Sensors

View full text Add to dashboard Cite

Accurately estimating respiratory rate (RR) has become essential for patients and the elderly. Hence, we propose a novel method that uses exact Gaussian process regression (EGPR)-assisted hybrid feature extraction and feature fusion based on photoplethysmography and electrocardiogram signals to improve the reliability of accurate RR and uncertainty estimations. First, we obtain the power spectral features and use the multi-phase feature model to compensate for insufficient input data. Then, we combine four different feature sets and choose features with high weights using a robust neighbor component analysis. The proposed EGPR algorithm provides a confidence interval representing the uncertainty. Therefore, the proposed EGPR algorithm, including hybrid feature extraction and weighted feature fusion, is an excellent model with improved reliability for accurate RR estimation. Furthermore, the proposed EGPR methodology is likely the only one currently available that provides highly stable variation and confidence intervals. The proposed EGPR-MF, 0.993 breath per minute (bpm), and EGPR-feature fusion, 1.064 (bpm), show the lowest mean absolute error compared to the other models.

show abstract

Section: Exact Gaussian Process Regression (Egpr) Based Hybrid Featur...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dual-Sensor Signals Based Exact Gaussian Process-Assisted Hybrid Feature Extraction and Weighted Feature Fusion for Respiratory Rate and Uncertainty Estimations

Lee

Moon

Al-antari

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…At present, long short‐term memory (LSTM) has been well used in time series prediction in the medical domain for early risk identification 23 . It is an extension of recurrent neural network (RNN) and has been prominent in modelling temporal sequences 24 . Li et al 25 .…”

Section: Introductionmentioning

confidence: 99%

“…Aliberti et al 27 developed a prediction model to predict future blood glucose values based on LSTM. Kumar et al 24 used LSTM to predict respiratory rate from biosignals. Lobo et al 28 developed an LSTM network approach to predict the haemoglobin level trajectory of patients with anaemia.…”

Section: Introductionmentioning

confidence: 99%

Real‐time trajectory prediction of laparoscopic instrument tip based on long short‐term memory neural network in laparoscopic surgery training

Wang

Yan

Yuan

et al. 2022

Robotics Computer Surgery

View full text Add to dashboard Cite

Background To provide appropriate surgical training guidance, some skill evaluation and safety detection methods have been developed. However, these methods are difficult to provide predictive information for trainees. This paper proposes a new approach for real‐time trajectory prediction of the laparoscopic instrument tip to improve surgical training and the patient safety. Methods This paper proposes a real‐time trajectory prediction model of laparoscopic instrument tip based on long short‐term memory (LSTM) neural network. Meanwhile, motion state is introduced to capture more motion information of the instrument tip and improve the model performance. Results The feasibility, effectiveness and generalisation ability of this proposed model are preliminarily verified. The model shows satisfactory prediction accuracy for the trajectory of the laparoscopic instrument tip. Conclusion LSTM neural network can accurately predict the movement trajectory of the laparoscopic instrument tip. The prediction model can play a critical role in operational risk perception in advance, which can be used in laparoscopic surgery training.

show abstract

“…Common PPG applications require basic signal processing and analysis, such as contour analysis and time–frequency techniques [ 3 , 4 , 16 , 17 , 18 ]. Recent studies also employ neural networks and deep learning to improve the assessment or prediction of physiological states and parameters [ 19 , 20 , 21 ]. However, as the cardiac and respiratory dynamics in general [ 22 , 23 , 24 ] and the PPG dynamics in particular are recognized as deterministic chaos [ 9 , 25 , 26 ], alternative complex approaches may be required for extracting accurate information on the physiological and mental health state, as follows from previous studies [ 9 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

Photoplethysmogram Recording Length: Defining Minimal Length Requirement from Dynamical Characteristics

Sviridova

Zhao

Nakano

et al. 2022

Sensors

View full text Add to dashboard Cite

Photoplethysmography is a widely used technique to noninvasively assess heart rate, blood pressure, and oxygen saturation. This technique has considerable potential for further applications—for example, in the field of physiological and mental health monitoring. However, advanced applications of photoplethysmography have been hampered by the lack of accurate and reliable methods to analyze the characteristics of the complex nonlinear dynamics of photoplethysmograms. Methods of nonlinear time series analysis may be used to estimate the dynamical characteristics of the photoplethysmogram, but they are highly influenced by the length of the time series, which is often limited in practical photoplethysmography applications. The aim of this study was to evaluate the error in the estimation of the dynamical characteristics of the photoplethysmogram associated with the limited length of the time series. The dynamical properties were evaluated using recurrence quantification analysis, and the estimation error was computed as a function of the length of the time series. Results demonstrated that properties such as determinism and entropy can be estimated with an error lower than 1% even for short photoplethysmogram recordings. Additionally, the lower limit for the time series length to estimate the average prediction time was computed.

show abstract

Deep learning for predicting respiratory rate from biosignals

Cited by 58 publications

References 71 publications

Dual-Sensor Signals Based Exact Gaussian Process-Assisted Hybrid Feature Extraction and Weighted Feature Fusion for Respiratory Rate and Uncertainty Estimations

Dual-Sensor Signals Based Exact Gaussian Process-Assisted Hybrid Feature Extraction and Weighted Feature Fusion for Respiratory Rate and Uncertainty Estimations

Real‐time trajectory prediction of laparoscopic instrument tip based on long short‐term memory neural network in laparoscopic surgery training

Photoplethysmogram Recording Length: Defining Minimal Length Requirement from Dynamical Characteristics

Contact Info

Product

Resources

About