Pulse rate variability estimation method based on imaging-photoplethysmography and application to telepsychiatry.

The worldwide adoption of telehealth services may benefit people who otherwise would not be able to access mental health support. In this paper, we present a novel algorithm to obtain reliable pulse and respiration signals from non-contact facial image sequence analysis. The proposed algorithm involved a skin pixel extraction method in the image processing part and signal reconstruction using the spectral information of RGB signal in the signal processing part. The algorithm was tested on 15 healthy subjects in a laboratory setting. The results show that the proposed algorithm can accurately monitor respiration rate (RR), pulse rate (PR), and pulse rate variability (PRV) in rest conditions.Clinical Relevance- The main achievement of this study is enabling non-contact PR and RR signal extraction from facial image sequences, which has potential for future use and support for psychiatrists in telepsychiatry.

Study on the Autonomous Non-contact Measurement of Biometric Signals.

In this study, we developed a robot that can recognize and track a person, and autonomously measure two biological signals, respiration rate and heart rate, in a non-contact manner. Through experiments, we confirmed that both signals can be measured with high accuracy and that the robot can perform the measurement under conditions similar to those in actual workplaces. We also investigated factors that can affect the accuracy of the non-contact measurement and studied a method to evaluate the reliability of the measured signals.

Changes in alpha, theta, and gamma oscillations in distinct cortical areas are associated with altered acute pain responses in chronic low back pain patients.

Introduction: Chronic pain negatively impacts a range of sensory and affective behaviors. Previous studies have shown that the presence of chronic pain not only causes hypersensitivity at the site of injury but may also be associated with pain-aversive experiences at anatomically unrelated sites. While animal studies have indicated that the cingulate and prefrontal cortices are involved in this generalized hyperalgesia, the mechanisms distinguishing increased sensitivity at the site of injury from a generalized site-nonspecific enhancement in the aversive response to nociceptive inputs are not well known. Methods: We compared measured pain responses to peripheral mechanical stimuli applied to a site of chronic pain and at a pain-free site in participants suffering from chronic lower back pain (n = 15) versus pain-free control participants (n = 15) by analyzing behavioral and electroencephalographic (EEG) data. Results: As expected, participants with chronic pain endorsed enhanced pain with mechanical stimuli in both back and hand. We further analyzed electroencephalographic (EEG) recordings during these evoked pain episodes. Brain oscillations in theta and alpha bands in the medial orbitofrontal cortex (mOFC) were associated with localized hypersensitivity, while increased gamma oscillations in the anterior cingulate cortex (ACC) and increased theta oscillations in the dorsolateral prefrontal cortex (dlPFC) were associated with generalized hyperalgesia. Discussion: These findings indicate that chronic pain may disrupt multiple cortical circuits to impact nociceptive processing.

Major Depressive Disorder and Chronic Fatigue Syndrome Show Characteristic Heart Rate Variability Profiles Reflecting Autonomic Dysregulations: Differentiation by Linear Discriminant Analysis.

Major depressive disorder (MDD) and chronic fatigue syndrome (CFS) have overlapping symptoms, and differentiation is important to administer the proper treatment. The present study aimed to assess the usefulness of heart rate variability (HRV) indices. Frequency-domain HRV indices, including high-frequency (HF) and low-frequency (LF) components, their sum (LF+HF), and their ratio (LF/HF), were measured in a three-behavioral-state paradigm composed of initial rest (Rest), task load (Task), and post-task rest (After) periods to examine autonomic regulation. It was found that HF was low at Rest in both disorders, but was lower in MDD than in CFS. LF and LF+HF at Rest were low only in MDD. Attenuated responses of LF, HF, LF+HF, and LF/HF to task load and an excessive increase in HF at After were found in both disorders. The results indicate that an overall HRV reduction at Rest may support a diagnosis of MDD. HF reduction was found in CFS, but with a lesser severity. Response disturbances of HRV to Task were observed in both disorders, and would suggest the presence of CFS when the baseline HRV has not been reduced. Linear discriminant analysis using HRV indices was able to differentiate MDD from CFS, with a sensitivity and specificity of 91.8% and 100%, respectively. HRV indices in MDD and CFS show both common and different profiles, and can be useful for the differential diagnosis.

Temporal pain processing in the primary somatosensory cortex and anterior cingulate cortex.

Pain is known to have sensory and affective components. The sensory pain component is encoded by neurons in the primary somatosensory cortex (S1), whereas the emotional or affective pain experience is in large part processed by neural activities in the anterior cingulate cortex (ACC). The timing of how a mechanical or thermal noxious stimulus triggers activation of peripheral pain fibers is well-known. However, the temporal processing of nociceptive inputs in the cortex remains little studied. Here, we took two approaches to examine how nociceptive inputs are processed by the S1 and ACC. We simultaneously recorded local field potentials in both regions, during the application of a brain-computer interface (BCI). First, we compared event related potentials in the S1 and ACC. Next, we used an algorithmic pain decoder enabled by machine-learning to detect the onset of pain which was used during the implementation of the BCI to automatically treat pain. We found that whereas mechanical pain triggered neural activity changes first in the S1, the S1 and ACC processed thermal pain with a reasonably similar time course. These results indicate that the temporal processing of nociceptive information in different regions of the cortex is likely important for the overall pain experience.

A prototype closed-loop brain-machine interface for the study and treatment of pain.

Chronic pain is characterized by discrete pain episodes of unpredictable frequency and duration. This hinders the study of pain mechanisms and contributes to the use of pharmacological treatments associated with side effects, addiction and drug tolerance. Here, we show that a closed-loop brain-machine interface (BMI) can modulate sensory-affective experiences in real time in freely behaving rats by coupling neural codes for nociception directly with therapeutic cortical stimulation. The BMI decodes the onset of nociception via a state-space model on the basis of the analysis of online-sorted spikes recorded from the anterior cingulate cortex (which is critical for pain processing) and couples real-time pain detection with optogenetic activation of the prelimbic prefrontal cortex (which exerts top-down nociceptive regulation). In rats, the BMI effectively inhibited sensory and affective behaviours caused by acute mechanical or thermal pain, and by chronic inflammatory or neuropathic pain. The approach provides a blueprint for demand-based neuromodulation to treat sensory-affective disorders, and could be further leveraged for nociceptive control and to study pain mechanisms.

The development and clinical application of a novel schizophrenia screening system using yoga-induced autonomic nervous system responses.

Background: In severe cases, schizophrenia can result in suicide and social isolation. Diagnosis delay can lead to worsening symptoms, and often results in prolonged therapy. An estimated 50%-80% of patients with schizophrenia are unaware of their condition. Biomarkers for schizophrenia are important for receiving a diagnosis from a psychiatrist at an early stage. Although previous studies have investigated near-infrared spectroscopy as a biomarker for schizophrenia, the required equipment is expensive and not designed for home use. Hence, we developed a novel home-use schizophrenia screening system that uses a wearable device to measure autonomic nervous system responses induced by yoga, which is frequently adopted in rehabilitation for schizophrenia. Materials and methods: The schizophrenia screening system automatically distinguishes patients with schizophrenia from healthy subjects via yoga-induced transient autonomic responses measured with a wearable wireless electrocardiograph (ECG) using linear discriminant analysis (LDA; Z score ≥ 0 → suspected schizophrenia, Z-score < 0 → healthy). The explanatory variables of LDA are averages of four indicators: components of heart rate variability (HRV): the very low-frequency (VLF), the low-frequency (LF), HR, and standard deviation of the NN intervals (SDNN). In the current study, HRV is defined as frequency domain HRV, which is determined by integrating RRI power spectrum densities from 0.0033 to 0.04 Hz (VLF) and 0.04-0.15 Hz (LF), and as time domain HRV, SDNN of which is calculated as the mean of the standard deviations of the RR intervals. These variables were measured before (5 min), during (15 min), and after (5 min) yoga in a 15-min mindfulness-based yoga program for schizophrenia (MYS). The General Health Questionnaire-28 (GHQ28) score was used to assess the severity of mental disorders for patients with schizophrenia and healthy volunteers. Twelve patients with schizophrenia (eight female and four male, 23-60 years old) and 16 healthy volunteers (seven female and nine male, 22-54 years old) were recruited. Results: The schizophrenia screening system achieved sensitivity of 91% and specificity of 81%. Z-scores of LDA were significantly correlated with GHQ28 scores (r = 0.45, p = 0.01). Conclusion: Our proposed system appears to be promising for future automated preliminary schizophrenia screening at home.

Remote sensing of vital signs by medical radar time-series signal using cardiac peak extraction and adaptive peak detection algorithm: Performance validation on healthy adults and application to neonatal monitoring at an NICU.

BACKGROUND AND OBJECTIVE: Continuous monitoring of vital signs plays a pivotal role in neonatal intensive care units (NICUs). In this paper, we present a system for monitoring fully non-contact medical radar-based vital signs to measure the respiratory rate (RR), heart rate (HR), I:E ratio, and heart rate variability (HRV). In addition, we evaluated its performance in a physiological laboratory and examined its adaptability in an NICU. METHODS: A non-contact medical radar-based vital sign monitoring system that includes 24 GHz radar installed in an incubator was developed. To enable reliable monitoring, an advanced signal processing algorithm (i.e., a nonlinear filter to separate respiration and heartbeat signals from the output of radar), template matching to extract cardiac peaks, and an adaptive peak detection algorithm to estimate cardiac peaks in time-series were proposed and implemented in the system. Nine healthy subjects comprising five males and four females (24 ± 5 years) participated in the laboratory test. To evaluate the adaptability of the system in an NICU setting, we tested it with three hospitalized infants, including two neonates. RESULTS: The results indicate strong agreement in healthy subjects between the non-contact system and reference contact devices for RR, HR, and inter-beat interval (IBI) measurement, with correlation coefficients of 0.83, 0.96, and 0.94, respectively. As anticipated, the template matching and adaptive peak detection algorithms outperformed the conventional approach. These showed a more accurate IBI close to the reference Bland-Altman analysis (proposed: bias of -3 ms, and 95% limits of agreement ranging from -73 to 67 ms; conventional: bias of -11 ms, and 95% limits of agreement ranging from -229 to 207 ms). Moreover, in the NICU clinical setting, the IBI correlation coefficient and 95% limit of agreement in the conventional method are 0.31 and 91 ms. The corresponding values obtained using the proposed method are 0.93 and 21 ms. CONCLUSION: The proposed system introduces a novel approach for NICU monitoring using a non-contact medical radar sensor. The signal processing method combining cardiac peak extraction algorithm with the adaptive peak detection algorithm shows high adaptability in detecting IBI the time series in various application settings.

TFAP4 Activates IGF2BP1 and Promotes Progression of Non-Small Cell Lung Cancer by Stabilizing TK1 Expression through m6A Modification.

Non-small cell lung cancer (NSCLC) is a well-known global health concern. TFAP4 has been reported to function as an oncogene. This study sought to investigate the molecular mechanism of TFAP4 in NSCLC development. Significantly highly-expressed gene IGF2BP1 was screened on online databases and its downstream gene TK1 was predicted. IGF2BP1 promoter sequence was identified. The binding site of TFAP4 and IGF2BP1 was predicted. The expression correlations among TFAP4, IGF2BP1, and TK1 were confirmed. The correlations between TFAP4, IGF2BP1, TK1, and NSCLC prognosis were predicted. NSCLC and paracancerous tissues were collected. The expressions of TFAP4, IGF2BP1, and TK1 were detected. NSCLC cell proliferation, migration, invasion, and apoptosis were detected. The binding of TFAP4 to the IGF2BP1 promoter was verified. m6A modification of TK1 mRNA was detected. The correlation between IGF2BP1 and TK1 was confirmed. A subcutaneous tumor xenograft model was established to validate the effect of TFAP4 in vivo. IGF2BP1 was highly expressed in NSCLC tissues and cells. IGF2BP1 knockdown repressed NSCLC cell proliferation, migration, and invasion and facilitated apoptosis. Mechanically, TFAP4 transcriptionally activated IGF2BP1. IGF2BP1 stabilized TK1 expression via m6A modification and promoted NSCLC cell proliferation, migration, and invasion. In vivo experiments confirmed that TFAP4 knockdown suppressed tumor growth by downregulating IGF2BP1/TK1. IMPLICATIONS: Our findings revealed that TFAP4 activated IGF2BP1 and facilitated NSCLC progression by stabilizing TK1 expression via m6A modification, which offered new insights into the diagnosis and treatment of NSCLC.

An mHealth App for the Non-contact Measurement of Pulmonary Function Using the Smartphone's Built-in Depth Sensor.

The use of smartphones in clinical practice is referred to as mobile health (mHealth). This has attracted great interest in both academia and industry because of its potential to augment healthcare. In this study, we developed an mHealth app for the non-contact measurement of chest-wall movements using the iPhone ' s built-in depth sensor, thereby enabling a pulmonary self-monitoring function for personal use. The depth sensor provides depth values for each pixel and 2D mapping of the chest-wall movements. To extract respiratory signals from the right and left thoracic regions and abdomen, a 2D-depth image-segmentation method was implemented. The method was based on the anatomy and physiology of chest-wall movements, assuming differences in the anterior displacement in the thoracic and abdominal regions. It was observed that the differences were significant in the segmented regions of interest (ROIs) of the right and left thoracic region and abdomen. Respiratory signals extracted from each ROI were compared with the contact bio-impedance signals, which were highly correlated (r=0.94).

Deep Learning Approach for Classifying Bacteria types using Morphology of Bacterial Colony.

The significant bottlenecks in determining bacterial species are much more time-consuming and the biology specialist's long-term experience requirements. Specifically, it takes more than half a day to cultivate a bacterium, and then a skilled microbiologist and a costly specialized machine are utilized to analyze the genes and classify the bacterium according to its nucleotide sequence. To overcome these issues as well as get higher recognition accuracy, we proposed applying convolutional neural networks (CNNs) architectures to automatically classify bacterial species based on some key characteristics of bacterial colonies. Our experiment confirmed that the classification of three bacterial colonies could be performed with the highest accuracy (97.19%) using a training set of 5000 augmented images derived from the 40 original photos taken in the Hanoi Medical University laboratory in Vietnam.

Development of a Novel Vital-Signs-Based Infection Screening Composite-Type Camera With Truncus Motion Removal Algorithm to Detect COVID-19 Within 10 Seconds and Its Clinical Validation.

Background: To conduct a rapid preliminary COVID-19 screening prior to polymerase chain reaction (PCR) test under clinical settings, including patient's body moving conditions in a non-contact manner, we developed a mobile and vital-signs-based infection screening composite-type camera (VISC-Camera) with truncus motion removal algorithm (TMRA) to screen for possibly infected patients. Methods: The VISC-Camera incorporates a stereo depth camera for respiratory rate (RR) determination, a red-green-blue (RGB) camera for heart rate (HR) estimation, and a thermal camera for body temperature (BT) measurement. In addition to the body motion removal algorithm based on the region of interest (ROI) tracking for RR, HR, and BT determination, we adopted TMRA for RR estimation. TMRA is a reduction algorithm of RR count error induced by truncus non-respiratory front-back motion measured using depth-camera-determined neck movement. The VISC-Camera is designed for mobile use and is compact (22 cm × 14 cm × 4 cm), light (800 g), and can be used in continuous operation for over 100 patients with a single battery charge. The VISC-Camera discriminates infected patients from healthy people using a logistic regression algorithm using RR, HR, and BT as explanatory variables. Results are available within 10 s, including imaging and processing time. Clinical testing was conducted on 154 PCR positive COVID-19 inpatients (aged 18-81 years; M/F = 87/67) within the initial 48 h of hospitalization at the First Central Hospital of Mongolia and 147 healthy volunteers (aged 18-85 years, M/F = 70/77). All patients were on treatment with antivirals and had body temperatures <37.5°C. RR measured by visual counting, pulsimeter-determined HR, and BT determined by thermometer were used for references. Result: 10-fold cross-validation revealed 91% sensitivity and 90% specificity with an area under receiver operating characteristic curve of 0.97. The VISC-Camera-determined HR, RR, and BT correlated significantly with those measured using references (RR: r = 0.93, p < 0.001; HR: r = 0.97, p < 0.001; BT: r = 0.72, p < 0.001). Conclusion: Under clinical settings with body motion, the VISC-Camera with TMRA appears promising for the preliminary screening of potential COVID-19 infection for afebrile patients with the possibility of misdiagnosis as asymptomatic.

Closed-loop stimulation using a multiregion brain-machine interface has analgesic effects in rodents.

Effective treatments for chronic pain remain limited. Conceptually, a closed-loop neural interface combining sensory signal detection with therapeutic delivery could produce timely and effective pain relief. Such systems are challenging to develop because of difficulties in accurate pain detection and ultrafast analgesic delivery. Pain has sensory and affective components, encoded in large part by neural activities in the primary somatosensory cortex (S1) and anterior cingulate cortex (ACC), respectively. Meanwhile, studies show that stimulation of the prefrontal cortex (PFC) produces descending pain control. Here, we designed and tested a brain-machine interface (BMI) combining an automated pain detection arm, based on simultaneously recorded local field potential (LFP) signals from the S1 and ACC, with a treatment arm, based on optogenetic activation or electrical deep brain stimulation (DBS) of the PFC in freely behaving rats. Our multiregion neural interface accurately detected and treated acute evoked pain and chronic pain. This neural interface is activated rapidly, and its efficacy remained stable over time. Given the clinical feasibility of LFP recordings and DBS, our findings suggest that BMI is a promising approach for pain treatment.

KBTBD7 promotes non-small cell lung carcinoma progression by enhancing ubiquitin-dependent degradation of PTEN.

The Kelch repeat and BTB domain containing 7 (KBTBD7) was first cloned in 2010. Its function as a transcriptional activator and a substrate adaptor during the ubiquitination process was soon found. KBTBD7 was shown to be involved in excessive inflammation after myocardial infarction, brain development, and neurofibromin stability. However, studies on the role of KBTBD7 in solid tumors, especially lung cancer, are still lacking. Therefore, in this study, we investigate the role of KBTBD7 in non-small cell lung cancer (NSCLC). Immunohistochemical staining of 104 paired NSCLC and peritumoral normal specimens indicated that KBTBD7 was highly expressed in NSCLC tissues and positively correlated with the histological type, P-TNM stage, lymph node metastasis, and tumor size. KBTBD7 was also well-expressed in NSCLC cell lines, and downregulation of KBTBD7 resulted in inhibition of NSCLC cell proliferation and invasion. Further investigation showed that KBTBD7 enhanced ubiquitin-dependent degradation of PTEN, thus activating EGFR/PI3K/AKT signaling and promoting NSCLC cell proliferation and invasion by regulating CCNE1, CDK4, P27, ZEB-1, Claudin-1, ROCK1, MMP-9, and E-cadherin protein levels. Our results indicate that KBTBD7 may be a potential therapeutic target for the treatment of NSCLC.

Interictal EEG and ECG for SUDEP Risk Assessment: A Retrospective Multicenter Cohort Study.

Objective: Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods: This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results: The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73-0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions: Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies.

Medical Radar Signal Dataset for Non-Contact Respiration and Heart Rate Measurement.

Medical radars remotely measure the periodic movements of the chest wall induced by breathing and heartbeat and have been widely recognized in healthcare. To the best of our knowledge, no well-characterized medical radar datasets are shared publicly. Therefore, in this article, we provide non-contact respiratory and cardiac signal datasets measured using a medical radar and simultaneously measured reference signals using electrocardiogram (ECG) and respiratory belt transducer. The datasets were collected from nine healthy subjects using 24.25 GHz and 10.525 GHz Doppler radars at a physiological laboratory in Japan. Furthermore, we generated MATLAB code to pre-process the signals and calculate the respiratory and heart rates. The datasets generated could be reused by biomedical researchers to investigate the signal-processing algorithm for non-contact vital sign measurement.

Proof-of-principle Experiment on 24 GHz Medical Radar for Non-contact Vital Signs Measurement.

Medical radar for non-contact vital signs measurement exhibits great potential in both clinical and home healthcare settings. Especially during the corona virus spreading time, non-contact sensing more clearly shows the advantages. Many previous studies have concentrated on medical radar-based healthcare applications, but pay less attention to the working principles. A clear understanding of medical radars at both the mathematical and physical levels is critically important for developing application-specific signal processing algorithms. Therefore, this study aims to re-define the operating principle of radar, and a proof-of-principle experiment was performed on both actuator and human subjects using 24 GHz Doppler radar system. Experimental results indicate that there is a difference in the radar output signals between the two cases, where the displacement is greater than and less than half of the wavelength. For the former situation, the displacement x = n.λ/2 (n ≥ 1), one peak of radar signals corresponds to n peaks of baseband signals. By contrast, for the latter situation, the displacement x < λ/2, one peak of radar signals corresponds to one peak of baseband signals. Strikingly, with human measurement on the dorsal side, the the number of respiration peaks are seen from the radar raw signals.

Design and Evaluation of Digital Filters for Non-Contact Measuring of HRV using Medical Radar and Its Application in Bedside Patient Monitoring System.

A non-contact bedside monitoring system using medical radar is expected to be applied to clinical fields. Our previous studies have developed a monitoring system based on medical radar for measuring respiratory rate (RR) and heart rate (HR). Heart rate variability (HRV), which is essentially implemented in advanced monitoring system, such as prognosis prediction, is a more challenging biological information than the RR and HR. In this study, we designed a HRV measurement filter and proposed a method to evaluate the optimal cardiac signal extraction filter for HRV measurement. Because the cardiac component in the radar signal is much smaller than the respiratory component, it is necessary to extract the cardiac element from the radar output signal using digital filters. It depends on the characteristics of the filter whether the HRV information is kept in the extracted cardiac signal or not. A cardiac signal extraction filter that is not distorted in the time domain and does not miss the cardiac component must be adopted. Therefore, we focused on evaluating the interval between the R-peak of the electrocardiogram (ECG) and the radar-cardio peak of the cardiac signal measured by radar (R-radar interval). This is based on the fact that the time between heart depolarization and ventricular contraction is measured as the R-radar interval. A band-pass filter (BPF) with several bandwidths and a nonlinear filter, locally projective adaptive signal separation (LoPASS), were analyzed and compared. The optimal filter was quantitatively evaluated by analyzing the distribution and standard deviation of the R-radar intervals. The performance of this monitoring system was evaluated in elderly patient at the Yokohama Hospital, Japan.

Non-contact Measurement of Pulse Rate Variability Using a Webcam and Application to Mental Illness Screening System.

The COVID-19 pandemic is a global health crisis. Mental health is critical in such uncertain situations, particularly when people are required to significantly restrict their movements and change their lifestyles. Under these conditions, many countries have turned to telemedicine to strengthen and expand mental health services. Our research group previously developed a mental illness screening system based on heart rate variability (HRV) analysis, enabling an objective and easy mental health self-check. This screening system cannot be used for telemedicine because it uses electrocardiography (ECG) and contact photoplethysmography (PPG), that are not widely available outside of a clinical setting. The purpose of this study is to enable the extension of the aforementioned system to telemedicine by the application of non-contact PPG using an RGB webcam, also called imaging- photoplethysmography (iPPG). The iPPG measurement errors occur due to changes in the relative position between the camera and the target, and due to changes in light. Conventionally, in image processing, the pixel value of the entire face region is used. We propose skin pixel extraction to eliminate blinks, eye movements, and changes in light and shadow. In signal processing, the green channel signal is conventionally used as a pulse wave owing to the absorption characteristics of blood flow. Taking advantage of the fact that the red and blue channels contain noise, we propose a signal reconstruction method for removing noise and strengthening the signal in the pulse rate variability (PRV) frequency band by weighting the three signals of the RGB camera. We conducted an experiment with 13 healthy subjects, and showed that the PRV index and pulse rate (PR) errors estimated by the proposed method were smaller than those of the conventional method. The correlation coefficients between estimated values by the proposed method and reference values of LF, HF, and PR were 0.86, 0.69, and 0.96, respectively.