Photoplethysmogram(PPG)is a noninvasive method for detecting human cardiovascular pulse wave using optical technology.The PPG containing a lot of physiological information is from the MIMIC database.This paper propose...Photoplethysmogram(PPG)is a noninvasive method for detecting human cardiovascular pulse wave using optical technology.The PPG containing a lot of physiological information is from the MIMIC database.This paper proposes a combinatorial method of ensemble empirical mode decomposition(EEMD),cepstrum,fast Fourier transform(FFT)and zero-crossing detection to improve the robustness of the estimation of pulse rate(PR),heart rate(HR)and respiratory rate(RR)from the PPG.First,the PPG signal was decomposed into finite intrinsic mode functions(IMF)by EEMD.Because of its adaptive filtering property,the different signals were reconstructed using different IMFs when estimating different physiological parameters.Second,the PR was obtained by zero-crossing detection after rejecting low frequency IMFs containing artifacts.Third,IMFs with frequency between 1.00 Hz to 1.67 Hz(60 beats/min to 100 beats/min)were selected for estimating HR.Then,the frequency band that reflects the heart activity was analyzed by the cepstrum method.Finally,the respiratory signal can be extracted from PPG signal by IMFs with frequency between 0.05 Hz to 0.75 Hz(3 breahts/min to 45 breaths/min).Then the spectrum of signal was obtained by FFT analysis and the RR was estimated by detecting the maximum frequency peak.The algorithm has been tested on MIMIC database obtained from 53 adults.The experiment results show that the physiological parameters extracted by this integrated signal processing method are consistent with the real physiological parameters.And the computation load of this method is small and the precision is high(not larger than 1.17%in error).展开更多
Hypertension is a leading risk factor for cardiovascular disease (CVD) and the overlap of diabetes mellitus (DM)with hypertension can lead to severe complications. There is a need for early diagnosis and risk stratifi...Hypertension is a leading risk factor for cardiovascular disease (CVD) and the overlap of diabetes mellitus (DM)with hypertension can lead to severe complications. There is a need for early diagnosis and risk stratification toimplement an overall risk management strategy. Presently, the conventional method is not suitable for large-scalescreening. The primary aim of this study is to develop an automated diagnostic system that uses Photoplethysmogram (PPG) signals for the non-invasive diagnosis of hypertension and DM-II. The proposed model usesa statistical feature extracted by decomposing the PPG signal up to level 11 into a sub-band using Discrete wavelettransform (DWT), and a variety of classifiers are used for the classification of hypertension and detection of DM-IIpatients. Three feature selection techniques used are Spearman correlation, ReliefF and Minimum RedundancyMaximum Relevance (mRMR) to select 20 top features out of 130 features using correlation with systole bloodpressure (SBP), diastole blood pressure (DBP) values and D-II. The highest accuracy attained by the Adaptiveneural fuzzy system (ANFIS) for classification categories such as normal (NT) vs prehypertension(PHT), NT vs.hypertension type 1 (HT-I), NT vs hypertension type 2 (HT-II) in terms of F1 score are 92.%, 98.5%, 98.3% (SBP)and 83.1%, 95.6%, 86.8% (DBP),respectively. The accuracy achieved by the adaptive-network-based fuzzyinference system (ANFIS) for the classification of normal (non-diabetic) vs. diabetic patients is 99.1%. The hybridlearning algorithm-based classifier achieved higher accuracy for hypertension risk stratification as compared tothe hard computing classifier, which requires parameter tuning and DWT decomposition is robust to the noisysignal, overcoming the limitation of the morphological feature-based model.展开更多
BACKGROUND:Unsustained return of spontaneous circulation(ROSC)is a critical barrier to survival in cardiac arrest patients.This study examined whether end-tidal carbon dioxide(ETCO_(2))and pulse oximetry photoplethysm...BACKGROUND:Unsustained return of spontaneous circulation(ROSC)is a critical barrier to survival in cardiac arrest patients.This study examined whether end-tidal carbon dioxide(ETCO_(2))and pulse oximetry photoplethysmogram(POP)parameters can be used to identify unsustained ROSC.METHODS:We conducted a multicenter observational prospective cohort study of consecutive patients with cardiac arrest from 2013 to 2014.Patients’general information,ETCO_(2),and POP parameters were collected and statistically analyzed.RESULTS:The included 105 ROSC episodes(from 80 cardiac arrest patients)comprised 51 sustained ROSC episodes and 54 unsustained ROSC episodes.The 24-hour survival rate was significantly higher in the sustained ROSC group than in the unsustained ROSC group(29.2%vs.9.4%,P<0.05).The logistic regression analysis showed that the difference between after and before ROSC in ETCO_(2)(ΔETCO_(2))and the difference between after and before ROCS in area under the curve of POP(ΔAUCp)were independently associated with sustained ROSC(odds ratio[OR]=0.931,95%confi dence interval[95%CI]0.881-0.984,P=0.011 and OR=0.998,95%CI 0.997-0.999,P<0.001).The area under the receiver operating characteristic curve ofΔETCO_(2),ΔAUCp,and the combination of both to predict unsustained ROSC were 0.752(95%CI 0.660-0.844),0.883(95%CI 0.818-0.948),and 0.902(95%CI 0.842-0.962),respectively.CONCLUSION:Patients with unsustained ROSC have a poor prognosis.The combination ofΔETCO_(2) andΔAUCp showed signifi cant predictive value for unsustained ROSC.展开更多
Obstructive Sleep Apnea(OSA)is a respiratory syndrome that occurs due to insufficient airflow through the respiratory or respiratory arrest while sleeping and sometimes due to the reduced oxygen saturation.The aim of ...Obstructive Sleep Apnea(OSA)is a respiratory syndrome that occurs due to insufficient airflow through the respiratory or respiratory arrest while sleeping and sometimes due to the reduced oxygen saturation.The aim of this paper is to analyze the respiratory signal of a person to detect the Normal Breathing Activity and the Sleep Apnea(SA)activity.In the proposed method,the time domain and frequency domain features of respiration signal obtained from the PPG device are extracted.These features are applied to the Classification and Regression Tree(CART)-Particle Swarm Optimization(PSO)classifier which classifies the signal into normal breathing signal and sleep apnea signal.The proposed method is validated to measure the performance metrics like sensitivity,specificity,accuracy and F1 score by applying time domain and frequency domain features separately.Additionally,the performance of the CART-PSO(CPSO)classification algorithm is evaluated through comparing its measures with existing classification algorithms.Concurrently,the effect of the PSO algorithm in the classifier is validated by varying the parameters of PSO.展开更多
Wearable cardiac monitoring devices can provide uninterrupted monitoring of cardiac activities over a long period of time.They have developed rapidly in recent years in terms of convenience,comfort,and intelligence.Ai...Wearable cardiac monitoring devices can provide uninterrupted monitoring of cardiac activities over a long period of time.They have developed rapidly in recent years in terms of convenience,comfort,and intelligence.Aided by the development of sensor and materials technology,big data and artificial intelligence,wearable cardiac monitoring can become a crucial basis for novel medical models in the future.Herein,the basic concepts and representative devices of wearable cardiac monitoring are first introduced.Subsequently,its core technologies and the latest representative research progress in physiology signal sensing,signal quality enhancement,and signal reliability are systematically reviewed.Finally,an insight and outlook on the future development trends and challenges of wearable cardiac monitoring are discussed.展开更多
The photoplethysmogram(PPG) of a pulse wave,similar in appearance to the arterial blood pressure(ABP) waveform,contains rich information about the cardiovascular system.The decay time constant RC,equal to the product ...The photoplethysmogram(PPG) of a pulse wave,similar in appearance to the arterial blood pressure(ABP) waveform,contains rich information about the cardiovascular system.The decay time constant RC,equal to the product of peripheral resistance R and total arterial compliance C,is a meaningful cardiovascular model parameter in vascular assessment.Using or ameliorating the existing ABP methods does not achieve a satisfactory estimation of RC from the PPG volume pulse(VRC).Thus,a novel non-iterative shape method(NSM) of evaluating VRC is introduced in this paper.The mathematic expression between a novel,readily available morphological parameter called the area difference ratio(ADR) and VRC was established.As it was difficult to calculate VRC from the complicated expression analytically,we recommend estimating it using a piecewise linear interpolation criterion.Also,since the effect of the PPG magnitude is eliminated in the calculation of ADR,precaliberation or normalization is dispensable in the NSM.Results of human experiments indicated that the NSM was computationally efficient,and the simulation experiments confirmed that the NSM was theoretically available for ABP.展开更多
文摘Photoplethysmogram(PPG)is a noninvasive method for detecting human cardiovascular pulse wave using optical technology.The PPG containing a lot of physiological information is from the MIMIC database.This paper proposes a combinatorial method of ensemble empirical mode decomposition(EEMD),cepstrum,fast Fourier transform(FFT)and zero-crossing detection to improve the robustness of the estimation of pulse rate(PR),heart rate(HR)and respiratory rate(RR)from the PPG.First,the PPG signal was decomposed into finite intrinsic mode functions(IMF)by EEMD.Because of its adaptive filtering property,the different signals were reconstructed using different IMFs when estimating different physiological parameters.Second,the PR was obtained by zero-crossing detection after rejecting low frequency IMFs containing artifacts.Third,IMFs with frequency between 1.00 Hz to 1.67 Hz(60 beats/min to 100 beats/min)were selected for estimating HR.Then,the frequency band that reflects the heart activity was analyzed by the cepstrum method.Finally,the respiratory signal can be extracted from PPG signal by IMFs with frequency between 0.05 Hz to 0.75 Hz(3 breahts/min to 45 breaths/min).Then the spectrum of signal was obtained by FFT analysis and the RR was estimated by detecting the maximum frequency peak.The algorithm has been tested on MIMIC database obtained from 53 adults.The experiment results show that the physiological parameters extracted by this integrated signal processing method are consistent with the real physiological parameters.And the computation load of this method is small and the precision is high(not larger than 1.17%in error).
文摘Hypertension is a leading risk factor for cardiovascular disease (CVD) and the overlap of diabetes mellitus (DM)with hypertension can lead to severe complications. There is a need for early diagnosis and risk stratification toimplement an overall risk management strategy. Presently, the conventional method is not suitable for large-scalescreening. The primary aim of this study is to develop an automated diagnostic system that uses Photoplethysmogram (PPG) signals for the non-invasive diagnosis of hypertension and DM-II. The proposed model usesa statistical feature extracted by decomposing the PPG signal up to level 11 into a sub-band using Discrete wavelettransform (DWT), and a variety of classifiers are used for the classification of hypertension and detection of DM-IIpatients. Three feature selection techniques used are Spearman correlation, ReliefF and Minimum RedundancyMaximum Relevance (mRMR) to select 20 top features out of 130 features using correlation with systole bloodpressure (SBP), diastole blood pressure (DBP) values and D-II. The highest accuracy attained by the Adaptiveneural fuzzy system (ANFIS) for classification categories such as normal (NT) vs prehypertension(PHT), NT vs.hypertension type 1 (HT-I), NT vs hypertension type 2 (HT-II) in terms of F1 score are 92.%, 98.5%, 98.3% (SBP)and 83.1%, 95.6%, 86.8% (DBP),respectively. The accuracy achieved by the adaptive-network-based fuzzyinference system (ANFIS) for the classification of normal (non-diabetic) vs. diabetic patients is 99.1%. The hybridlearning algorithm-based classifier achieved higher accuracy for hypertension risk stratification as compared tothe hard computing classifier, which requires parameter tuning and DWT decomposition is robust to the noisysignal, overcoming the limitation of the morphological feature-based model.
基金supported by National Natural Science Foundation of China General Program (82172179)Mathematics Tianyuan Fund (12126604)Central High-level Hospital Clinical Research Project (2022-PUMCH-B-110)
文摘BACKGROUND:Unsustained return of spontaneous circulation(ROSC)is a critical barrier to survival in cardiac arrest patients.This study examined whether end-tidal carbon dioxide(ETCO_(2))and pulse oximetry photoplethysmogram(POP)parameters can be used to identify unsustained ROSC.METHODS:We conducted a multicenter observational prospective cohort study of consecutive patients with cardiac arrest from 2013 to 2014.Patients’general information,ETCO_(2),and POP parameters were collected and statistically analyzed.RESULTS:The included 105 ROSC episodes(from 80 cardiac arrest patients)comprised 51 sustained ROSC episodes and 54 unsustained ROSC episodes.The 24-hour survival rate was significantly higher in the sustained ROSC group than in the unsustained ROSC group(29.2%vs.9.4%,P<0.05).The logistic regression analysis showed that the difference between after and before ROSC in ETCO_(2)(ΔETCO_(2))and the difference between after and before ROCS in area under the curve of POP(ΔAUCp)were independently associated with sustained ROSC(odds ratio[OR]=0.931,95%confi dence interval[95%CI]0.881-0.984,P=0.011 and OR=0.998,95%CI 0.997-0.999,P<0.001).The area under the receiver operating characteristic curve ofΔETCO_(2),ΔAUCp,and the combination of both to predict unsustained ROSC were 0.752(95%CI 0.660-0.844),0.883(95%CI 0.818-0.948),and 0.902(95%CI 0.842-0.962),respectively.CONCLUSION:Patients with unsustained ROSC have a poor prognosis.The combination ofΔETCO_(2) andΔAUCp showed signifi cant predictive value for unsustained ROSC.
文摘Obstructive Sleep Apnea(OSA)is a respiratory syndrome that occurs due to insufficient airflow through the respiratory or respiratory arrest while sleeping and sometimes due to the reduced oxygen saturation.The aim of this paper is to analyze the respiratory signal of a person to detect the Normal Breathing Activity and the Sleep Apnea(SA)activity.In the proposed method,the time domain and frequency domain features of respiration signal obtained from the PPG device are extracted.These features are applied to the Classification and Regression Tree(CART)-Particle Swarm Optimization(PSO)classifier which classifies the signal into normal breathing signal and sleep apnea signal.The proposed method is validated to measure the performance metrics like sensitivity,specificity,accuracy and F1 score by applying time domain and frequency domain features separately.Additionally,the performance of the CART-PSO(CPSO)classification algorithm is evaluated through comparing its measures with existing classification algorithms.Concurrently,the effect of the PSO algorithm in the classifier is validated by varying the parameters of PSO.
基金This work was supported by the National Key Research and Development Program of China(2021YFA0715502)the National Natural Science Foundation of China(61904065,61974052,and 62204091)+5 种基金Key R&D Program of Hubei Province(2021BAA014)International Science and Technology Cooperation Project of Hubei Province(2021EHB010)the fund for Innovative Research Groups of the Natural Science Foundation of Hubei Province(2020CFA034)Scientific Research Project of Wenzhou(G20210013)the China Postdoctoral Science Foundation(2021M691118,and 2022M711237)the Fund from Science,Technology and Innovation Commission of Shenzhen Municipality(GJHZ20210705142540010).
基金Supported by the 2021 Key Research and Development Plan of Shaanxi Province,China(No.2021GXLH-Z-091).
文摘Wearable cardiac monitoring devices can provide uninterrupted monitoring of cardiac activities over a long period of time.They have developed rapidly in recent years in terms of convenience,comfort,and intelligence.Aided by the development of sensor and materials technology,big data and artificial intelligence,wearable cardiac monitoring can become a crucial basis for novel medical models in the future.Herein,the basic concepts and representative devices of wearable cardiac monitoring are first introduced.Subsequently,its core technologies and the latest representative research progress in physiology signal sensing,signal quality enhancement,and signal reliability are systematically reviewed.Finally,an insight and outlook on the future development trends and challenges of wearable cardiac monitoring are discussed.
基金Project (No.81070885) supported by the National Natural Science Foundation of China
文摘The photoplethysmogram(PPG) of a pulse wave,similar in appearance to the arterial blood pressure(ABP) waveform,contains rich information about the cardiovascular system.The decay time constant RC,equal to the product of peripheral resistance R and total arterial compliance C,is a meaningful cardiovascular model parameter in vascular assessment.Using or ameliorating the existing ABP methods does not achieve a satisfactory estimation of RC from the PPG volume pulse(VRC).Thus,a novel non-iterative shape method(NSM) of evaluating VRC is introduced in this paper.The mathematic expression between a novel,readily available morphological parameter called the area difference ratio(ADR) and VRC was established.As it was difficult to calculate VRC from the complicated expression analytically,we recommend estimating it using a piecewise linear interpolation criterion.Also,since the effect of the PPG magnitude is eliminated in the calculation of ADR,precaliberation or normalization is dispensable in the NSM.Results of human experiments indicated that the NSM was computationally efficient,and the simulation experiments confirmed that the NSM was theoretically available for ABP.