A sleep stage estimation algorithm based on cardiorespiratory signals derived from a suprasternal pressure sensor.

Automatic estimation of sleep structure is an important aspect in moving sleep monitoring from clinical laboratories to people's homes. However, the transition to more portable systems should not happen at the expense of important physiological signals, such as respiration. Here, we propose the use of cardiorespiratory signals obtained by a suprasternal pressure (SSP) sensor to estimate sleep stages. The sensor is already used for diagnosis of sleep-disordered breathing (SDB) conditions, but besides respiratory effort it can detect cardiac vibrations transmitted through the trachea. We collected the SSP sensor signal in 100 adults (57 male) undergoing clinical polysomnography for suspected sleep disorders, including sleep apnea syndrome, insomnia, and movement disorders. Here, we separate respiratory effort and cardiac activity related signals, then input these into a neural network trained to estimate sleep stages. Using the original mixed signal the results show a moderate agreement with manual scoring, with a Cohen's kappa of 0.53 in Wake/N1-N2/N3/rapid eye movement sleep discrimination and 0.62 in Wake/Sleep. We demonstrate that decoupling the two signals and using the cardiac signal to estimate the instantaneous heart rate improves the process considerably, reaching an agreement of 0.63 and 0.71. Our proposed method achieves high accuracy, specificity, and sensitivity across different sleep staging tasks. We also compare the total sleep time calculated with our method against manual scoring, with an average error of -1.83 min but a relatively large confidence interval of ±55 min. Compact systems that employ the SSP sensor information-rich signal may enable new ways of clinical assessments, such as night-to-night variability in obstructive sleep apnea and other sleep disorders.

Quantitative validation of the suprasternal pressure signal to assess respiratory effort during sleep.

Objective.Intra-esophageal pressure (Pes) measurement is the recommended gold standard to quantify respiratory effort during sleep, but used to limited extent in clinical practice due to multiple practical drawbacks. Respiratory inductance plethysmography belts (RIP) in conjunction with oronasal airflow are the accepted substitute in polysomnographic systems (PSG) thanks to a better usability, although they are partial views on tidal volume and flow rather than true respiratory effort and are often used without calibration. In their place, the pressure variations measured non-invasively at the suprasternal notch (SSP) may provide a better measure of effort. However, this type of sensor has been validated only for respiratory events in the context of obstructive sleep apnea syndrome (OSA). We aim to provide an extensive verification of the suprasternal pressure signal against RIP belts and Pes, covering both normal breathing and respiratory events.Approach.We simultaneously acquired suprasternal (207) and esophageal pressure (20) signals along with RIP belts during a clinical PSG of 207 participants. In each signal, we detected breaths with a custom algorithm, and evaluated the SSP in terms of detection quality, breathing rate estimation, and similarity of breathing patterns against RIP and Pes. Additionally, we examined how the SSP signal may diverge from RIP and Pes in presence of respiratory events scored by a sleep technician.Main results.The SSP signal proved to be a reliable substitute for both esophageal pressure (Pes) and respiratory inductance plethysmography (RIP) in terms of breath detection, with sensitivity and positive predictive value exceeding 75%, and low error in breathing rate estimation. The SSP was also consistent with Pes (correlation of 0.72, similarity 80.8%) in patterns of increasing pressure amplitude that are common in OSA.Significance.This work provides a quantitative analysis of suprasternal pressure sensors for respiratory effort measurements.

Extraction of cardiac-related signals from a suprasternal pressure sensor during sleep.

Objective.The accurate detection of respiratory effort during polysomnography is a critical element in the diagnosis of sleep-disordered breathing conditions such as sleep apnea. Unfortunately, the sensors currently used to estimate respiratory effort are either indirect and ignore upper airway dynamics or are too obtrusive for patients. One promising alternative is the suprasternal notch pressure (SSP) sensor: a small element placed on the skin in the notch above the sternum within an airtight capsule that detects pressure swings in the trachea. Besides providing information on respiratory effort, the sensor is sensitive to small cardiac oscillations caused by pressure perturbations in the carotid arteries or the trachea. While current clinical research considers these as redundant noise, they may contain physiologically relevant information.Approach.We propose a method to separate the signal generated by cardiac activity from the one caused by breathing activity. Using only information available from the SSP sensor, we estimate the heart rate and track its variations, then use a set of tuned filters to process the original signal in the frequency domain and reconstruct the cardiac signal. We also include an overview of the technical and physiological factors that may affect the quality of heart rate estimation. The output of our method is then used as a reference to remove the cardiac signal from the original SSP pressure signal, to also optimize the assessment of respiratory activity. We provide a qualitative comparison against methods based on filters with fixed frequency cutoffs.Main results.In comparison with electrocardiography (ECG)-derived heart rate, we achieve an agreement error of 0.06 ± 5.09 bpm, with minimal bias drift across the measurement range, and only 6.36% of the estimates larger than 10 bpm.Significance.Together with qualitative improvements in the characterization of respiratory effort, this opens the development of novel portable clinical devices for the detection and assessment of sleep disordered breathing.

Analysis of physiological and non-contact signals to evaluate the emotional component in consumer preferences.

Emotions are an essential drive in decision making and may influence consumer preference. In this study we assessed the influence of brands in product preference after tasting 2 soft-drinks (Coca Cola vs. Cola beverage), by using physiological measurements, namely the skin conductance, the respiratory rate and heart rate variability (HRV) extracted using contactless sensors. The experimental protocol enrolled twenty-five young subjects which were asked to taste 2 soft drinks in random order, without knowing the brand (blind condition) and then knowing the brand (not blind condition). After each phase the subject was asked to choose the preferred beverage. Our main hypothesis is that if the subject knows the brand there is an arousal effect, independently from the absolute appreciation of the product. In order to evaluate the emotional components, the skin conductance, respiratory and Video-Photoplethysmographic (PPG) signals were continuously recorded throughout the experiment. The Video-PPG was then processed to extract HRV parameters. We observed that the arousal levels changed among beverages and conditions, going from higher arousal for Coca-Cola in the blind condition, to higher arousal for Cola in the not blind condition. Moreover, 44% of the subjects changed their preference when the brand was uncovered: from blind to not blind conditions, 6 subjects went from Cola to Coca-Cola as preferred drink and 5 went from Coca-Cola to Cola. Opposite results were found for the two beverages when comparing the physiological response when the beverage was/was not preferred. Finally, differences were found also between consumers and not consumers of Coca-Cola and the blind/not blind comparison. We conclude that the brand is a fundamental element in a request for choice and it can affect the first emotional response of a subject.

Effects of a cool classroom microclimate on cardiac autonomic control and cognitive performances in undergraduate students.

An inverted U-shape relationship between cognitive performance and indoor temperature with best performance peaking at 21.6 °C was previously described. Little is known on classroom temperature reduction effects on cognitive performances and cardiac autonomic profile, during the cold season. Fifteen students underwent electrocardiogram recording during a lecture in two days in December when classroom temperatures were set as neutral (NEUTRAL, 20-22 °C) and cool (COOL, 16-18 °C). Cognitive performance (memory, verbal ability, reasoning, overall cognitive C-score) was assessed by Cambridge Brain Science cognitive evaluation tool. Cardiac autonomic control was evaluated via the analysis of spontaneous fluctuations of heart period, as the temporal distance between two successive R-wave peaks (RR). Spectral analysis provided the power in the high frequency (HF, 0.15-0.40 Hz) and low frequency (LF, 0.04-0.15 Hz) bands of RR variability. Sympatho-vagal interaction was assessed by LF to HF ratio (LF/HF). Symbolic analysis provided the fraction of RR patterns composed by three heart periods with no variation (0 V%) and two variations (2 V%), taken as markers of cardiac sympathetic and vagal modulations, respectively. The students' thermal comfort was assessed during NEUTRAL and COOL trials. Classroom temperatures were 21.5 ± 0.8 °C and 18.4 ± 0.4 °C during NEUTRAL and COOL. Memory, verbal ability, C-Score were greater during COOL (13.01 ± 3.43, 12.32 ± 2.58, 14.29 ± 2.90) compared to NEUTRAL (9.98 ± 2.26, p = 0.002; 8.57 ± 1.07, p = 0.001 and 10.35 ± 3.20, p = 0.001). LF/HF (2.4 ± 1.7) and 0 V% (23.2 ± 11.1%) were lower during COOL compared to NEUTRAL (3.7 ± 2.8, p = 0.042; 28.1 ± 12.2.1%, p = 0.031). During COOL, 2 V% was greater (30.5 ± 10.9%) compared to NEUTRAL (26.2 ± 11.3, p = 0.047). The students' thermal comfort was slightly reduced during COOL compared to NEUTRAL trial. During cold season, a better cognitive performance was obtained in a cooler indoor setting enabling therefore energy saving too.

Development of a Deep-Learning Pipeline to Recognize and Characterize Macrophages in Colo-Rectal Liver Metastasis.

Quantitative analysis of Tumor Microenvironment (TME) provides prognostic and predictive information in several human cancers but, with few exceptions, it is not performed in daily clinical practice since it is extremely time-consuming. We recently showed that the morphology of Tumor Associated Macrophages (TAMs) correlates with outcome in patients with Colo-Rectal Liver Metastases (CLM). However, as for other TME components, recognizing and characterizing hundreds of TAMs in a single histopathological slide is unfeasible. To fasten this process, we explored a deep-learning based solution. We tested three Convolutional Neural Networks (CNNs), namely UNet, SegNet and DeepLab-v3, with three different segmentation strategies, semantic segmentation, pixel penalties and instance segmentation. The different experiments are compared according to the Intersection over Union (IoU), a metric describing the similarity between what CNN predicts as TAM and the ground truth, and the Symmetric Best Dice (SBD), which indicates the ability of CNN to separate different TAMs. UNet and SegNet showed intrinsic limitations in discriminating single TAMs (highest SBD 61.34±2.21), whereas DeepLab-v3 accurately recognized TAMs from the background (IoU 89.13±3.85) and separated different TAMs (SBD 79.00±3.72). This deep-learning pipeline to recognize TAMs in digital slides will allow the characterization of TAM-related metrics in the daily clinical practice, allowing the implementation of prognostic tools.

Influence of acquisition frame-rate and video compression techniques on pulse-rate variability estimation from vPPG signal.

In this paper, common time- and frequency-domain variability indexes obtained by pulse rate variability (PRV) series extracted from video-photoplethysmographic signal (vPPG) were compared with heart rate variability (HRV) parameters calculated from synchronized ECG signals. The dual focus of this study was to analyze the effect of different video acquisition frame-rates starting from 60 frames-per-second (fps) down to 7.5 fps and different video compression techniques using both lossless and lossy codecs on PRV parameters estimation. Video recordings were acquired through an off-the-shelf GigE Sony XCG-C30C camera on 60 young, healthy subjects (age 23±4 years) in the supine position. A fully automated, signal extraction method based on the Kanade-Lucas-Tomasi (KLT) algorithm for regions of interest (ROI) detection and tracking, in combination with a zero-phase principal component analysis (ZCA) signal separation technique was employed to convert the video frames sequence to a pulsatile signal. The frame-rate degradation was simulated on video recordings by directly sub-sampling the ROI tracking and signal extraction modules, to correctly mimic videos recorded at a lower speed. The compression of the videos was configured to avoid any frame rejection caused by codec quality leveling, FFV1 codec was used for lossless compression and H.264 with variable quality parameter as lossy codec. The results showed that a reduced frame-rate leads to inaccurate tracking of ROIs, increased time-jitter in the signals dynamics and local peak displacements, which degrades the performances in all the PRV parameters. The root mean square of successive differences (RMSSD) and the proportion of successive differences greater than 50 ms (PNN50) indexes in time-domain and the low frequency (LF) and high frequency (HF) power in frequency domain were the parameters which highly degraded with frame-rate reduction. Such a degradation can be partially mitigated by up-sampling the measured signal at a higher frequency (namely 60 Hz). Concerning the video compression, the results showed that compression techniques are suitable for the storage of vPPG recordings, although lossless or intra-frame compression are to be preferred over inter-frame compression methods. FFV1 performances are very close to the uncompressed (UNC) version with less than 45% disk size. H.264 showed a degradation of the PRV estimation directly correlated with the increase of the compression ratio.

Monitoring breathing rate by fusing the physiological impact of respiration on video-photoplethysmogram with head movements.

OBJECTIVE: The simple observation of breathing rate (BR) remains the first and often the most sensitive marker of acute respiratory dysfunction. In fact, there is evidence that drastic changes in BR are a predictive indicator of adverse events (i.e. cardiac arrest). The aim of this study is to develop a camera-based technology that may provide near-continuous estimation of BR considering the effect of respiration on video-PPG (vPPG). APPROACH: The technology has been tested in two different experimental settings, including controlled BR and more challenging scenarios with spontaneous breathing patterns. Video data were processed offline to derive the vPPG signal. The method derives respiration from beat-to-beat PPG rate and morphology changes in amplitude and width driven by the physiological relationships between vPPG and respiration. Moreover, respiratory-induced head movements were used as an additional source of information for the vPPG system. A combination of these methods has been exploited to estimate the respiratory rate every 10 seconds. MAIN RESULTS: According to the results, respiratory frequencies in the central range (0.2-0.4 Hz) may be estimated using the vPPG system with a low relative error, [Formula: see text] and interquartile range of the order [Formula: see text]. However, the vPPG system showed a drop in performance at respiratory range boundaries, around 0.1 Hz and 0.5 Hz. SIGNIFICANCE: This camera-based technology can be used as an ubiquitous BR monitoring system. However, vPPG-based systems should consider the effect of the BR in the estimation, mainly in applications where the respiratory rate is out of the 0.2-0.4 Hz range.

Analysis of Instantaneous Linear, Nonlinear and Complex Cardiovascular Dynamics from Videophotoplethysmography.

BACKGROUND: There is a fast growing interest in the use of non-contact devices for health and performance assessment in humans. In particular, the use of non-contact videophotoplethysmography (vPPG) has been recently demonstrated as a feasible way to extract cardiovascular information. Nevertheless, proper validation of vPPG-derived heartbeat dynamics is still missing. OBJECTIVE: We aim to an in-depth validation of time-varying, linear and nonlinear/complex dynamics of the pulse rate variability extracted from vPPG. METHODS: We apply inhomogeneous pointprocess nonlinear models to assess instantaneous measures defined in the time, frequency, and bispectral domains as estimated through vPPG and standard ECG. Instantaneous complexity measures, such as the instantaneous Lyapunov exponents and the recently defined inhomogeneous point-process approximate and sample entropy, were estimated as well. Video recordings were processed using our recently proposed method based on zerophase principal component analysis. Experimental data were gathered from 60 young healthy subjects (age: 24±3 years) undergoing postural changes (rest-to-stand maneuver). RESULTS: Group averaged results show that there is an overall agreement between linear and nonlinear/complexity indices computed from ECG and vPPG during resting state conditions. However, important differences are found, particularly in the bispectral and complexity domains, in recordings where the subjects has been instructed to stand up. CONCLUSIONS: Although significant differences exist between cardiovascular estimates from vPPG and ECG, it is very promising that instantaneous sympathovagal changes, as well as time-varying complex dynamics, were correctly identified, especially during resting state. In addition to a further improvement of the video signal quality, more research is advocated towards a more precise estimation of cardiovascular dynamics by a comprehensive nonlinear/complex paradigm specifically tailored to the non-contact quantification.

Assessment of instantaneous cardiovascular dynamics from video plethysmography.

Although there is growing interest in estimating cardiovascular information using contactless video plethysmography (VP), an in-depth validation of time-varying, nonlinear dynamics of the related pulse rate variability is still missing. In this study we estimate the heartbeat through VP and standard ECG, and employ inhomogeneous point-process nonlinear models to assess instantaneous heart rate variability measures defined in the time, frequency, and bispectral domains. Experimental data were gathered from 60 young healthy subjects (age: 24±3 years) undergoing postural changes (rest-to-stand maneuver). Video recordings are processed using our recently proposed method based on zero-phase component analysis. Results show that, at a group level, there is an overall agreement between linear and nonlinear indices computed from ECG and VP during resting state conditions. However, significant differences are found, especially in the bispectral domain, when considering data gathered while standing. Although significant differences exist between cardiovascular estimates from VP and ECG, results can be considered very promising as instantaneous sympatho-vagal changes were correctly identified. More research is indeed needed to improve on the precise estimation of nonlinear sympatho-vagal interactions.

Relationships between heart-rate variability and pulse-rate variability obtained from video-PPG signal using ZCA.

In this paper, classical time- and frequency-domain variability indexes obtained by pulse rate variability (PRV) series extracted from video-photoplethysmography signals (vPPG) were compared with heart rate variability (HRV) parameters extracted from ECG signals. The study focuses on the analysis of the changes observed during a rest-to-stand manoeuvre (a mild sympathetic stimulus) performed on 60 young, normal subjects (age: [Formula: see text] years). The objective is to evaluate if video-derived PRV indexes may replace HRV in the assessment of autonomic responses to external stimulation. Video recordings were performed with a GigE Sony XCG-C30C camera and analyzed offline to extract the vPPG signal. A new method based on zero-phase component analysis (ZCA) was employed in combination with a fully-automatic method for detection and tracking of region of interest (ROI) located on the forehead, the cheek and the nose. Results show an overall agreement between time and frequency domain indexes computed on HRV and PRV series. However, some differences exist between resting and standing conditions. During rest, all the indexes computed on HRV and PRV series were not statistically significantly different (p > 0.05), and showed high correlation (Pearson's r > 0.90). The agreement decreases during standing, especially for the high-frequency, respiration-related parameters such as RMSSD (r = 0.75), pNN50 (r = 0.68) and HF power (r = 0.76). Finally, the power in the LF band (n.u.) was observed to increase significantly during standing by both HRV ([Formula: see text] versus [Formula: see text] (n.u.); rest versus standing) and PRV ([Formula: see text] versus [Formula: see text](n.u.); rest versus standing) analysis, but such an increase was lower in PRV parameters than that observed by HRV indexes. These results provide evidence that some differences exist between variability indexes extracted from HRV and video-derived PRV, mainly in the HF band during standing. However, despite these differences video-derived PRV indexes were able to evince the autonomic responses expected by the sympathetic stimulation induced by the rest-to-stand manoeuvre.