PROJECT REPORT ON RESPIRATORY RATE ESTIMATION USING PPG SIGNALS CONTENTS 1.INTRODUCTION What is respiration Respiratory rate 2.Respiration rate monitoring 3.Conventional method 4.Photoplethysmograph 5.Respiratory rate measurments using ppg signal 6.PPG sensor 7.Respiratory measurment 8.Plethysmography 9.Methodology 10.PPG processing 11.Identification of peak points 12.Genration of peak vs time and peak interval vs time data 13.Performing FFT of the signal 14.FFT spectrum of RIFV signal 15.Result 16.Table 17.Challenge in processing the PPG signals 18.Conclusion What is Respiration ? Respiration is a complex metabolic biochemical process where in, the living cells of an organism obtains energy, in the form of Adenosine Triphosphate (ATP) by taking in oxygen and liberating carbon dioxide from the oxidation of complex organic substances Respiratory Rate • Respiration rate is an important vital sign. It is, the number of breaths taken within a set amount of time. Newborn: 30-60 breaths per minute Infant (1 to 12 months): 30-60 breaths per minute Toddler (1-2 years): 24-40 breaths per minute Preschooler (3-5 years): 22-34 breaths per minute School-age child (6-12 years): 18-30 breaths per minute Adolescent (13-17 years): 12-16 breaths per minute RESPIRATION RATE MONITORING Respiratory rate is a critical vial sign that provides early detection of respiratory compromise and patient distress Continous monitoring of respiratory rate is especially important for post–surgical patients receiving patient- controlled analgesia (PCA) for pain management as the sedation can induce respiratory depression and place patients at considerable risk of serious injury or death Conventional Methods • An efficient and accurate method of respiratory measurement is still not present in healthcare sector. • There are different approaches for respiration monitoring, but generally they can be classed as contact or noncontact. For contact methods, the sensing device (or part of the instrument containing it) is attached to the subject's body. • Concerns related to the patient's recording comfort, recording hygiene, and the accuracy of respiration rate monitoring have resulted in the development of a number of noncontact respiration monitoring approaches. What is Photoplethysmograph? • The word plethysmograph is a combination of two ancient Greek words ‘plethysmos’ which means increase and ‘graph’ which is the word for write. Photoplethysmography (PPG) is used to estimate the skin blood flow using infrared light. Researchers from different domains of science have become increasingly interested in PPG because of its advantages as non-invasive, inexpensive, and convenient diagnostic tool. Traditionally, it measures the oxygen saturation, blood pressure, cardiac output, and for assessing autonomic functions. Respiratory rate measurment using PPG signal Photoplethysmography(PPG) is the measurement of blood volumetric changes with each heartbeat. The PPG pulse obtained by the optical sensor is used for various cardiovascular parameter measurement. PPG SENSOR Among the PPG sensors under the category of contact type PPG sensors, the Respiration Measurement • The irregularity in respiration process can cause illness problem to a person. With this regard it can be said that the respiratory rate is one of the earliest indicators of physiological instability including cardiac problem or other health related issues. • The failures in Multi Organ Systems are indicated by changes in respiration pattern as shown in Fig Fig.15 Respiration pattern in normal and disease state Plethysmography: • Plethysmography is a method of evaluating pulmonary ventilation by measuring the movement of the chest and abdominal wall. Plethysmography measures changes in volume in different areas of our body. • It measures these changes with blood pressure cuffsor other sensors. These are attached to a machine called a plethysmograph. Plethysmography is especially effective in detecting changes caused by blood flow. It can also help to determine a blood clot in subject arm or leg. Methodology The proposed methodology consist of the major parts as shown in figure PPG Preprocessing Identification of peak points Estimating the respiratory rate Generation of peak vs Time and peak interval vs time data Performing FFT of the signals PPG preprocessing • • The quality of ppg signal depends on the location and the properties of the subjects skin at measurement, including the individual skin structure, the blood oxygen saturation ,blood flow rate ,skin temperatures and the measuring environment. The PPG signal available in DEAP database is considered for the present work. The original signal is found to contain few artifacts like powerline interference which needs to be filtered out before further processing. As sampling frequency is 250Hz ,5 point Moving average filter has been used for removing power line interference noise. Identification of peak points • • We have developed a peak detection algorithm for accurate determination of respiratory rate ,using ppg signals. Peak points detection is the first step for the analysis of respiratory rate estimation. Identification of peak points of data 1 Generation of peak vs time and peak interval vs time data RIAV(Respiratory induced amplitude variation )signal is obtained by plotting the amplitudes of the peaks against time as shown in figure In order to obtained the RIFV (Respiratory induced frequency variation) signal, the difference between two consecutive peak instance is computed Fig RIAV and RIFV for emotion Excited Performing FFT of the signal The FFT algorithm is used to convert a digital signal with length (N) from the time domain into a signal in the frequency domain. Fig FFT of RIAV signal for emotion Excited The FFT spectrum of RIFV signal is shown in figure: Fig FFT of RIFV signal for emotion Excited RESULT • FFT has been performed over above mention signals for extracting the frequency components. From the spectrum, the frequency having the max amplitude denotes the respiratory rate per second • In order to validate our method we have compared the FFT of RIAV and RIFV with the FFT of the actual respiratory signal. The FFT of the actual respiratory signal for emotion excitation is given in figure. Fig FFT of actual respiratory signal for emotion Excited TABLE • • SUBJECT(Emotion) Respiration Rate from RIAV signal Respiration rate Respiratory Rate from RIFV from actual respiratory signal signal EXCITED (0.3182*60)=19.092 (0.2835*60)=17.0149 (0.2857*60)=17.142 When the values of RR(Respiratory Rate) from RIAV and RIFV are compared with the RR(Respiratory Rate) from the actual respiratory signal they are found to be close to each other. From here we can conclude that our proposed method is capable enough to estimate the respiratory rate from the PPG signal without using any direct respiratory sensor. Challenges in processing the PPG signals • Powerline Interference • Motion Artifact • Low Amplitude PPG Signal • Premature Ventricular Contraction • These factors generate several types of additive artefact which may be contained within the PPG signals. This may affect the extraction of features and hence the overall diagnosis, especially, when the PPG signal and its derivatives will be assessed in an algorithmic fashion. • In order to improve the accuracy of respiratory rate extracted from photoplethysmography (PPG) signal, a method based on moving average filtering is proposed. CONCLUSION • • • • • Extraction of respiratory rate from Photoplethysmographic (PPG) signals will potentially eliminate the use of sensor intended to record respiration. In this report, a novel based algorithm is presented and applied to extract respiratory rate from Photoplethysmographic (PPG ) signals. The derived respiratory signal using principal component was compared with the recorded respiratory signals available in DEAP database and shown a strong correlation. In this contribution, we showed that it is possible to track respiratory rate from PPG signal with high accuracy at a low computational cost. From our work we can conclude that our proposed method is capable enough to estimate the respiratory rate from the ppg signal without using any direct respiratory sensor. Despite the relatively simple structure of the algorithm, the results indicate a strong correlation with the ground truth. Analysis of the PPG signal offers an alternative way of monitoring Respiratory rate ; this indirect estimation can be extremely useful in situations when a continuous monitoring is required THANKYOU