Photoplethysmography Sensor Research Articles

LSTM‐based real‐time stress detection using PPG signals on raspberry Pi

AbstractStress, widely recognised for its profound adverse effects on both physical and mental health, necessitates the development of innovative real‐time detection methods. In this context, the escalating prevalence of wearable embedded systems, integrated with artificial intelligence (AI) for the continuous monitoring of critical physiological indicators like heart rate and blood pressure, accentuates their growing relevance in the efficient detection of stress. This article presents an innovative methodology employing deep learning algorithms on the Raspberry Pi 3, a platform distinguished by its cost‐effectiveness and limited resources. The authors have developed an advanced AI algorithm that achieves high accuracy in real‐time stress detection using photoplethysmography (PPG) sensors while significantly reducing computational demands. The authors’ method utilises an artificial neural network with long short‐term memory (LSTM) layers, proving highly effective in time‐series data analysis. In this study, the authors implement key TensorFlow toolkit optimisation techniques including quantisation aware training (QAT), Pruning and prune‐preserving quantisation aware training. These techniques are applied to refine the authors’ model, decreasing size and latency without sacrificing accuracy. The results highlight the LSTM‐based model's proficiency in accurately detecting stress using raw PPG sensor data on the Raspberry Pi 3, a comparatively affordable platform. The model attains an accuracy of 89.32% and an F1 score of 89.55% on the diverse wearable stress and affect detection stress‐level dataset. Additionally, the authors’ optimised model exhibits substantial reductions in both size and latency while maintaining high accuracy. This approach shows great potential for various applications, such as stress monitoring in healthcare, sports, and workplace settings. The use of the Raspberry Pi 3 makes the system portable, cost‐effective, and energy‐efficient, enhancing its potential impact and accessibility.

Assessment of Physiological Signals from Photoplethysmography Sensors Compared to an Electrocardiogram Sensor: A Validation Study in Daily Life

Assessment of Physiological Signals from Photoplethysmography Sensors Compared to an Electrocardiogram Sensor: A Validation Study in Daily Life

Comparing peripheral limb and forehead vital sign monitoring in newborn infants at birth.

To study the feasibility of measuring heart rate (HR) and oxygen saturation (SpO2) on the forehead, during newborn transition at birth, and to compare these measurements with those obtained from the wrist. Vital signs were measured and compared between forehead-mounted reflectance (remittance) photoplethysmography sensor (fhPPG) and a wrist-mounted pulse oximeter sensor (wrPO), from 20 enrolled term newborns born via elective caesarean section, during the first 10 min of life. From the datasets available (n = 13), the median (IQR) sensor placement times for fhPPG, ECG and wrPO were 129 (70) s, 143 (68) s, and 159 (76) s, respectively, with data recorded for up to 10 min after birth. The success rate (percentage of total possible HR values reported once sited) of fhPPG (median = 100%) was higher compared to wrPO (median = 69%) during the first 6 min of life (P < 0.005). Both devices exhibited good HR agreement with ECG, achieving >95% agreement by 3 (fhPPG) and 4 (wrPO) min. SpO2 for fhPPG correlated with wrPO (r = 0.88), but there were significant differences in SpO2 between the two devices between 3 and 8 min (P < 0.005), with less variance observed with fhPPG SpO2. In the period of newborn transition at birth in healthy term infants, forehead measurement of vital signs was feasible and exhibited greater HR accuracy and higher estimated SpO2 values compared to wrist-sited pulse oximetry. Further investigation of forehead monitoring based on the potential benefits over peripheral monitoring is warranted. This study demonstrates the feasibility of continuously monitoring heart rate and oxygen saturation from an infant's forehead in the delivery room immediately after birth. Significantly higher SpO2 measurements were observed from the forehead than the wrist during the transition from foetal to newborn life. Continuous monitoring of vital signs from the forehead could become a valuable tool to improve the delivery of optimal care provided for newborns at birth.

Long-term noninvasive cardiac monitoring via Neutralized interfacial design for noise-suppressed near-infrared organic photodetectors

Organic photodetectors (OPDs) are the prime candidates for realizing commercial photoplethysmography (PPG) sensors in the future, although their performance and stability limitations remain as challenges. This study presents a strategy for fabricating high-precision, long-term, sustainable OPDs for non-invasive cardiac monitoring. In this work, the use of appropriate amounts of heterocyclic 1,3-diazoles (solid surfactants) enhances the morphology of PEDOT:PSS films and optimizes its energy level alignment, thus directly reducing the leakage current noise and improving the stability of the OPD. The OPDs with 0.5 wt% heterocyclic 1,3-diazole demonstrate enhanced dark current suppression and detectivity enhancement in the photoconductive and self-powered modes. Improved charge recombination dynamics and optimal resistance ratios lead to better performance of the champion device under low-intensity illumination. The champion device yields a more precise Photoplethysmography (PPG) signal under normal and exercise conditions when using a near-infrared light source, and it maintains a PPG signal intensity of more than 90 % after 315 days (7560 h) of storage in a nitrogen atmosphere. Optimized PPG sensors based on flexible substrates maintain signal intensity after seven days of air storage. The low hysteresis behavior also verifies that the optimized device has higher driving stability. High-reliability, high-validity accelerated photoplethysmography (APG) demonstrated that the champion PPG sensor would be used for accurate cardiovascular diagnostics, even over an extended period.

Unmanned vehicles in health monitoring and medicine delivery with swarm algorithm innovations

The article delves into modern approaches and innovative technologies designed to monitor the health of military personnel using unmanned vehicles, while also assessing their potential for delivering medicines in combat environments. It thoroughly examines the wide range of sensors and technologies that enable remote measurement of vital signs, including but not limited to thermal imaging cameras, photoplethysmography sensors, and radio frequency sensors, highlighting their effectiveness in various operational contexts. The article also reviews numerous real-world applications of drones in both medical and humanitarian projects, showcasing the transformative impact these technologies can have in providing timely healthcare and support in areas where traditional medical infrastructure may be lacking. In addition to discussing the practical benefits of using unmanned vehicles for healthcare delivery, the article also addresses the challenges posed by their integration into military operations, such as logistical, technical, and regulatory hurdles. Furthermore, it presents a detailed example of how these innovative systems can be effectively combined to enhance the medical care provided to military personnel, especially during combat, where traditional access to medical services is often limited or compromised. The article proposes several key areas for future research and development, emphasizing the importance of continued technological advancements to fully harness the potential of unmanned vehicles for medical applications in the military sector. These areas include improving sensor accuracy, developing better communication systems, and creating more autonomous and efficient delivery mechanisms. Here are examples that prove, the article suggests that unmanned vehicles could play a critical role in revolutionizing both battlefield medicine and military logistics, offering new solutions for healthcare delivery in challenging environments.

Wearable quantum dots organic light-emitting diodes patch for high-power near infra-red photomedicene with real-time wavelength control

Wearable photomedical application fields, such as photobiomodulation (PBM), and photoplethysmography (PPG) sensors using organic light-emitting diodes (OLEDs), are promising and attractive due to their flexibility, surface light emission, and ability to apply to various free-form (attachable or implantable) healthcare platforms. However, to maximize the impact on wearable photomedical applications, their spectrum needs to be freely tunable in real-time, and expanded into the near-infrared (NIR) wavelengths which are difficult to achieve in conventional electroluminescent OLED. In this study, we introduce the wavelength selective quantum dots high-power parallel-stacked OLED (QD-OLED) patch. Several NIR QD-OLEDs with 630, 700, and 730 nm peak wavlength were optimized by the high-power (> 100 mW·cm−2 at 6.3 V) parallel-stacked blue OLED with a 465 nm emission peak.The NIR QD-OLED patch platform with multi-functional blue reflective NIR-enhanced (> 60 %) encapsulation film (6 x 10−6 g·m−2·day−1), capable of real-time wavelength control, achieved a high-output NIR power density (>23.28 mW·cm−2). Using this NIR QD-OLED patch, PPG bio-signals were successfully measured. Additionally, this NIR QD-OLED demonstrated that it can increase the proliferation of dermal papilla cells by up to 131 % through NIR wavelength control, thereby optimizing the hair growth effect.

Highly mechanically stable and intrinsically stretchable large-area organic photovoltaics using nanoporous bulk-heterojunction

It is important to develop bulk-heterojunction films that simultaneously exhibit good photovoltaic properties and mechanical robustness to realize intrinsically stretchable organic photovoltaics (IS-OPVs). We developed a strategy for preparing nanoporous bulk-heterojunction (np-BHJ) films at a large area by nonsolvent-induced phase separation assisted by thermoplastic polyurethane. The resulting np-BHJ can form much improved adhesive interfaces with a neighbored stretchable layer in OPV devices and effectively dissipate applied mechanical stress. IS-OPVs using the np-BHJ films showed efficiency of 12.0 %, which is comparable performance to 12.4 % of the controlled BHJ. The IS-OPV device using np-BHJ films much improved mechanical stability and maintained 89 % of its initial efficiency under applied strain of 40 %. The corresponding module showed only 10 % decrease in efficiency after 1,000 cycles in stretching tests at 10 % strain. Because of high scalability of the np-BHJ morphology, IS-OPV modules with efficiency of 7.06 % and active area of 10.17 cm2 and were successfully demonstrated. Photoplethysmography sensors prepared using the IS-OPV module showed strong potential for application in wearable electronics.

Enhancing security through continuous biometric authentication using wearable sensors

The paper presents a novel approach for biometric continuous driver authentication (CDA) for secure and safe transportation using wearable photoplethysmography (PPG) sensors and deep learning. Conventional one-time authentication (OTA) methods, while effective for initial identity verification, fail to continuously verify the driver’s identity during vehicle operation, potentially leading to safety, security, and accountability issues. To address this, we propose a system that employs Long Short-Term Memory (LSTM) models to predict subsequent PPG values from wrist-worn devices and continuously compare them with real-time sensor data for authentication. Our system calculates a confidence level representing the probability that the current user is the authorized driver, ensuring robust availability to genuine users while detecting impersonation attacks. The raw PPG data is directly fed into the LSTM model without pre-processing, ensuring lightweight processing. We validated our system with PPG data from 15 volunteers driving for 15 min in varied conditions. The system achieves an Equal Error Rate (EER) of 4.8%. Our results demonstrate that the system is a viable solution for CDA in dynamic environments, ensuring transparency, efficiency, accuracy, robust availability, and lightweight processing. Thus, our approach addresses the main challenges of classical driver authentication systems and effectively safeguards passengers and goods with robust driver authentication.

Determining the Optimal Window Duration to Enhance Emotion Recognition Based on Galvanic Skin Response and Photoplethysmography Signals

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely, Lyapunov Exponent, Approximate Entropy, and Poincaré indices. We found an optimum window duration of 3 s with 50% overlap and achieved accuracies of 0.75 and 0.74 for both arousal and valence, respectively. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.94 for arousal. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

(Invited) Toward Ultrathin Flexible Quantum Dot Light-Emitting Diodes and Photodetectors for the Wearable Electronics

Flexible optoelectronic devices, encompassing light-emitting diodes (LEDs) and photodetectors, capable of seamlessly transforming their shapes, represent a prominent trend in next-generation electronics. Quantum dots, widely employed as emitters and light absorption layers, are chosen for their high luminous performance, size-dependent color tunability, and excellent light absorption properties. Moreover, their solution processability and ultrathin form factor make them particularly appealing for the development of ultrathin wearable optoelectronic devices.Here, we introduce ultrathin flexible quantum dot light-emitting diodes and photodetectors designed for wearable electronics. Utilizing intaglio transfer printing, we can produce high-definition red-green-blue quantum dot LEDs, suitable for integration into skin-attachable displays. Moreover, our ultrathin, self-powered, heavy-metal-free photodetectors, based on copper indium selenide nanoparticles, showcase outstanding optical performance (specific detectivity: 2.10 × 1012 Jones at zero-bias) and find application in wearable photoplethysmography (PPG) sensors.

Continuous Monitoring of Heart Rate Variability in Free-Living Conditions Using Wearable Sensors: Exploratory Observational Study.

Wearable physiological monitoring devices are promising tools for remote monitoring and early detection of potential health changes of interest. The widespread adoption of such an approach across communities and over long periods of time will require an automated data platform for collecting, processing, and analyzing relevant health information. In this study, we explore prospective monitoring of individual health through an automated data collection, metrics extraction, and health anomaly analysis pipeline in free-living conditions over a continuous monitoring period of several months with a focus on viral respiratory infections, such as influenza or COVID-19. A total of 59 participants provided smartwatch data and health symptom and illness reports daily over an 8-month window. Physiological and activity data from photoplethysmography sensors, including high-resolution interbeat interval (IBI) and step counts, were uploaded directly from Garmin Fenix 6 smartwatches and processed automatically in the cloud using a stand-alone, open-source analytical engine. Health risk scores were computed based on a deviation in heart rate and heart rate variability metrics from each individual's activity-matched baseline values, and scores exceeding a predefined threshold were checked for corresponding symptoms or illness reports. Conversely, reports of viral respiratory illnesses in health survey responses were also checked for corresponding changes in health risk scores to qualitatively assess the risk score as an indicator of acute respiratory health anomalies. The median average percentage of sensor data provided per day indicating smartwatch wear compliance was 70%, and survey responses indicating health reporting compliance was 46%. A total of 29 elevated health risk scores were detected, of which 12 (41%) had concurrent survey data and indicated a health symptom or illness. A total of 21 influenza or COVID-19 illnesses were reported by study participants; 9 (43%) of these reports had concurrent smartwatch data, of which 6 (67%) had an increase in health risk score. We demonstrate a protocol for data collection, extraction of heart rate and heart rate variability metrics, and prospective analysis that is compatible with near real-time health assessment using wearable sensors for continuous monitoring. The modular platform for data collection and analysis allows for a choice of different wearable sensors and algorithms. Here, we demonstrate its implementation in the collection of high-fidelity IBI data from Garmin Fenix 6 smartwatches worn by individuals in free-living conditions, and the prospective, near real-time analysis of the data, culminating in the calculation of health risk scores. To our knowledge, this study demonstrates for the first time the feasibility of measuring high-resolution heart IBI and step count using smartwatches in near real time for respiratory illness detection over a long-term monitoring period in free-living conditions.

Fluid-Solid Interaction Analysis for Developing In-Situ Strain and Flow Sensors for Prosthetic Valve Monitoring.

Transcatheter aortic valve implantation (TAVI) was initially developed for adult patients, but there is a growing interest to expand this procedure to younger individuals with longer life expectancies. However, the gradual degradation of biological valve leaflets in transcatheter heart valves (THV) presents significant challenges for this extension. This study aimed to establish a multiphysics computational framework to analyze structural and flow measurements of TAVI and evaluate the integration of optical fiber and photoplethysmography (PPG) sensors for monitoring valve function. A two-way fluid-solid interaction (FSI) analysis was performed on an idealized aortic vessel before and after the virtual deployment of the SAPIEN 3 Ultra (S3) THV. Subsequently, an analytical analysis was conducted to estimate the PPG signal using computational flow predictions and to analyze the effect of different pressure gradients and distances between PPG sensors. Circumferential strain estimates from the embedded optical fiber in the FSI model were highest in the sinus of Valsalva; however, the optimal fiber positioning was found to be distal to the sino-tubular junction to minimize bending effects. The findings also demonstrated that positioning PPG sensors both upstream and downstream of the bioprosthesis can be used to effectively assess the pressure gradient across the valve. We concluded that computational modeling allows sensor design to quantify vessel wall strain and pressure gradients across valve leaflets, with the ultimate goal of developing low-cost monitoring systems for detecting valve deterioration.

Anomaly Detection of Motion Artifact in Photoplethysmography (PPG) Sensors Using Unsupervised Learning

Anomaly Detection of Motion Artifact in Photoplethysmography (PPG) Sensors Using Unsupervised Learning

A novel cuffless blood pressure monitoring device in hypertension care

Background: Hypertension management is challenged by the dynamic nature of blood pressure (BP) fluctuations. These fluctuations are influenced by factors such as physical activity, emotional changes, and sleep patterns. Traditional guidelines focus on static measurements taken in clinical settings. However, these readings may not accurately represent an individual’s typical BP levels. This approach can lead to misdiagnoses, such as white coat or masked hypertension, resulting in either unnecessary treatment or missed diagnoses.Current Concepts: Recent global hypertension guidelines emphasize the importance of home BP monitoring and 24-hour ambulatory BP measurements for more accurate diagnoses and treatment plans. However, several barriers exist, such as the high cost of ambulatory BP devices and practical challenges associated with home BP monitoring, which limit their widespread utilization. Despite these challenges, integrating BP measurements into mobile devices offers a promising approach to monitoring BP outside the clinical setting. Various innovative approaches have been developed, including smartwatches utilizing photoplethysmography sensors and machine learning algorithms. However, their accuracy and the need for periodic calibration are areas of concern.Discussion and Conclusion: Mobile device BP monitoring represents a significant advancement in hypertension management, offering the potential for continuous, convenient, and less intrusive monitoring. Despite these potential benefits, challenges such as device accuracy verification, large-scale data interpretation, and calibration must be addressed. The future of hypertension management will likely rely on these technologies, along with traditional methods, to provide better insight into individual BP profiles. This integration promises to improve hypertension diagnosis, management, and ultimately patient outcomes, although further research and development are necessary to overcome the current limitations.

Temporal Convolutional Neural Network-Based Prediction of Vascular Health in Elderly Women Using Photoplethysmography-Derived Pulse Wave during Exercise.

(1) Background: The objective of this study was to predict the vascular health status of elderly women during exercise using pulse wave data and Temporal Convolutional Neural Networks (TCN); (2) Methods: A total of 492 healthy elderly women aged 60-75 years were recruited for the study. The study utilized a cross-sectional design. Vascular endothelial function was assessed non-invasively using Flow-Mediated Dilation (FMD). Pulse wave characteristics were quantified using photoplethysmography (PPG) sensors, and motion-induced noise in the PPG signals was mitigated through the application of a recursive least squares (RLS) adaptive filtering algorithm. A fixed-load cycling exercise protocol was employed. A TCN was constructed to classify flow-mediated dilation (FMD) into "optimal", "impaired", and "at risk" levels; (3) Results: TCN achieved an average accuracy of 79.3%, 84.8%, and 83.2% in predicting FMD at the "optimal", "impaired", and "at risk" levels, respectively. The results of the analysis of variance (ANOVA) comparison demonstrated that the accuracy of the TCN in predicting FMD at the impaired and at-risk levels was significantly higher than that of Long Short-Term Memory (LSTM) networks and Random Forest algorithms; (4) Conclusions: The use of pulse wave data during exercise combined with the TCN for predicting the vascular health status of elderly women demonstrated high accuracy, particularly in predicting impaired and at-risk FMD levels. This indicates that the integration of exercise pulse wave data with TCN can serve as an effective tool for the assessment and monitoring of the vascular health of elderly women.

A Guide to Measuring Heart and Respiratory Rates Based on Off-the-Shelf Photoplethysmographic Hardware and Open-Source Software.

The remote monitoring of vital signs via wearable devices holds significant potential for alleviating the strain on hospital resources and elder-care facilities. Among the various techniques available, photoplethysmography stands out as particularly promising for assessing vital signs such as heart rate, respiratory rate, oxygen saturation, and blood pressure. Despite the efficacy of this method, many commercially available wearables, bearing Conformité Européenne marks and the approval of the Food and Drug Administration, are often integrated within proprietary, closed data ecosystems and are very expensive. In an effort to democratize access to affordable wearable devices, our research endeavored to develop an open-source photoplethysmographic sensor utilizing off-the-shelf hardware and open-source software components. The primary aim of this investigation was to ascertain whether the combination of off-the-shelf hardware components and open-source software yielded vital-sign measurements (specifically heart rate and respiratory rate) comparable to those obtained from more expensive, commercially endorsed medical devices. Conducted as a prospective, single-center study, the research involved the assessment of fifteen participants for three minutes in four distinct positions, supine, seated, standing, and walking in place. The sensor consisted of four PulseSensors measuring photoplethysmographic signals with green light in reflection mode. Subsequent signal processing utilized various open-source Python packages. The heart rate assessment involved the comparison of three distinct methodologies, while the respiratory rate analysis entailed the evaluation of fifteen different algorithmic combinations. For one-minute average heart rates' determination, the Neurokit process pipeline achieved the best results in a seated position with a Spearman's coefficient of 0.9 and a mean difference of 0.59 BPM. For the respiratory rate, the combined utilization of Neurokit and Charlton algorithms yielded the most favorable outcomes with a Spearman's coefficient of 0.82 and a mean difference of 1.90 BrPM. This research found that off-the-shelf components are able to produce comparable results for heart and respiratory rates to those of commercial and approved medical wearables.

A 2.3-5.7 μW Tri-Modal Self-Adaptive Photoplethysmography Sensor Interface IC for Heart Rate, SpO2, and Pulse Transit Time Co-Monitoring.

This paper presents a tri-modal self-adaptive photoplethysmography (PPG) sensor interface IC for concurrently monitoring heart rate, SpO2, and pulse transit time, which is a critical intermediate parameter to derive blood pressure. By implementing a highly-reconfigurable analog front-end (AFE) architecture, flexible signal chain timing control, and flexible dual-LED drivers, this sensor interface provides wide operating space to support various PPG-sensing use cases. A heart-beat-locked-loop (HBLL) scheme is further extended to achieve time-multiplexed dual-input pulse transit time extraction based on two PPG sensors placed at fingertip and chest. A self-adaptive calibration scheme is proposed to automatically match the chip's operating point with the current use case, guaranteeing a sufficient signal-to-noise ratio for the user while consuming minimum system power. This paper proposes a DC offset cancellation (DCOC) approach comprised by a logarithmic transimpedance amplifier and an 8-bit SAR ADC, achieving a measured 38 nA residue error and 8.84 μA maximum input current. Fabricated in a 65nm CMOS process, the proposed tri-modal PPG sensor interface consumes 2.3-5.7 μW AFE power and 1.52 mm2 die area with 102dB (SpO2 mode), 110-116 dB (HR & PTT mode) dynamic range. A SpO2 test case and a HR & PTT test case are both demonstrated in the paper, achieving 18.9 μW and 43.7 μW system power, respectively.

Aging related changes in cardiovascular system in healthy female population: photoplethysmography method and DFA analysis

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Ministry of Science Technological Development and Innovation Background The cardiovascular system undergoes dynamic changes during the biological aging in humans, leading to chronic cardiovascular and cerebrovascular diseases. Purpose Developing the novel method for non-invasive monitoring of age induced changes in arterial vessels. Methodology The pilot study was performed on 58 women, in good health, non-smokers, between the ages of 20 and 70, divided into three age groups. All subjects underwent arterial blood pressure measurement using a photoplethysmography sensor. Recordings were performed in left carotid artery and the left index finger area. Arterial blood flow waveform was then analyzed using DFA analysis, calculating the values of the scalar coefficients α1 and α2. Based on the waveform time interval shift between the standing and supine positions, the pulse wave velocity (PWV) ratio was determined. Results Systolic and diastolic arterial pressure showed a slight linear increase with the age, but without significant difference between the three age categories (p &amp;gt; 0.5). Also, the PWV ratio between the supine and standing positions did not show a statistically significant increase between the age groups. Only scalar coefficients ratio α1/α2 demonstrated a significant difference in value between all age categories. Conclusion In subjects included in this pilot study, only the scalar coefficients ratio varied significantly with the age, indicating the occurrence of structural changes in the cardiovascular system caused by biological aging.

Sleep staging algorithm based on smartwatch sensors for healthy and sleep apnea populations

ObjectiveSleep stages can provide valuable insights into an individual's sleep quality. By leveraging movement and heart rate data collected by modern smartwatches, it is possible to enable the sleep staging feature and enhance users' understanding about their sleep and health conditions. MethodIn this paper, we present and validate a recurrent neural network based model with 23 input features extracted from accelerometer and photoplethysmography sensors data for both healthy and sleep apnea populations. We designed a lightweight and fast solution to enable the prediction of sleep stages for each 30-s epoch. This solution was developed using a large dataset of 1522 night recordings collected from a highly heterogeneous population and different versions of Samsung smartwatch. ResultsIn the classification of four sleep stages (wake, light, deep, and rapid eye movements sleep), the proposed solution achieved 71.6 % of balanced accuracy and a Cohen's kappa of 0.56 in a test set with 586 recordings. ConclusionThe results presented in this paper validate our proposal as a competitive wearable solution for sleep staging. Additionally, the use of a large and diverse data set contributes to the robustness of our solution, and corroborates the validation of algorithm's performance. Some additional analysis performed for healthy and sleep apnea population demonstrated that algorithm's performance has low correlation with demographic variables.

A Wireless Noninvasive Blood Pressure Measurement System Using MAX30102 and Random Forest Regressor for Photoplethysmography Signals

Hypertension, often termed “the silent killer”, is associated with cardiovascular risk and requires regular blood pressure (BP) monitoring. However, existing methods are cumbersome and require medical expertise, which is worsened by the need for physical contact, particularly during situations such as the coronavirus pandemic that started in 2019 (COVID-19). This study aimed to develop a cuffless, continuous, and accurate BP measurement system using a photoplethysmography (PPG) sensor and a microcontroller via PPG signals. The system utilizes a MAX30102 sensor and ESP-WROOM-32 microcontroller to capture PPG signals that undergo noise reduction during preprocessing. Peak detection and feature extraction algorithms were introduced, and their output data were used to train a machine learning model for BP prediction. Tuning the model resulted in identifying the best-performing model when using a dataset from six subjects with a total of 114 records, thereby achieving a coefficient of determination of 0.37/0.46 and a mean absolute error value of 4.38/4.49 using the random forest algorithm. Integrating this model into a web-based graphical user interface enables its implementation. One probable limitation arises from the small sample size (six participants) of healthy young individuals under seated conditions, thereby potentially hindering the proposed model’s ability to learn and generalize patterns effectively. Increasing the number of participants with diverse ages and medical histories can enhance the accuracy of the proposed model. Nevertheless, this innovative device successfully addresses the need for convenient, remote BP monitoring, particularly during situations like the COVID-19 pandemic, thus making it a promising tool for cardiovascular health management.