Search Results (103)

Cuffless blood pressure estimation using the finger-pressing method remains sensitive to improper finger centering and inconsistent contact force, which degrade the accuracy of the oscillometric envelope and PPG signal morphology. This paper details the development of a research prototype that integrates three force sensors and a photoplethysmograph (PPG) sensor to quantify the finger–device interaction. This system is intended as a pre-clinical research tool rather than a clinically validated medical device. We implement a weighted centroid algorithm for center of pressure (CoP) feedback to guide geometric centering, alongside a Hybrid Ridge Regression model to estimate the total contact force. The system was evaluated on a pre-clinical pilot cohort of 48 healthy participants (1274 recordings), comparing inflationary (ramp-up) and deflationary (ramp-down) interaction modalities. Force calibration achieved a mean absolute error (MAE) of 1.2 g, with hardware analysis confirming a limited zero-load baseline drift of −0.29% over 50 days. The best single-recording calibrated model achieved a mean absolute error (MAE) of 5.55 mmHg (systolic) and 5.20 mmHg (diastolic), with a mean error (ME) ± standard deviation (SD) of $+0.50\pm 7.25$ and $+1.19\pm 6.47$ mmHg, respectively, in this pilot cohort, demonstrating the feasibility of the three-point force-sensing design with CoP tracking. Full article

Background: With the increasing prevalence of multimorbidity, the demand for palliative and end-of-life care is expected to rise substantially in the coming decades. Digital health technologies may enable automated detection of clinically relevant distress, including symptoms such as pain, breathlessness (dyspnea), anxiety/panic, nausea, and agitation. Remote detection of such distress in cognitively impaired patients who are unable to reliably call for help could enable timely intervention when patients are unattended. Methods: This observational feasibility study will collect multimodal data from a non-invasive sensor system consisting of 3D radar, a photoplethysmographic sensor (wearable), and a microphone. Sensor data will be linked to distress events identified by nurses or physicians during routine clinical care using structured proxy assessments. Adults (≥18 years) admitted to the Palliative Care Center Basel who are unable to reliably call for help due to cognitive impairment will be included based on written informed consent provided by a legal proxy. Aim: The aim of this study is to evaluate the feasibility of multimodal sensor-based monitoring for detecting clinician-identified distress events and to explore associations between sensor-derived variables and distress, informing future validation studies and the development of automated detection approaches in palliative care. Full article

Cardiovascular diseases (CVDs) remain the leading cause of morbidity and mortality in the elderly worldwide. Over the past two decades, there has been a wealth of evidence of a close relationship between autonomic nervous system activity and cardiovascular mortality, including sudden cardiac death. Heart rate variability (HRV), derived from photoplethysmographic (PPG) signals, is increasingly recognized as a promising non-invasive digital marker for evaluating autonomic nervous system function and stratifying CVD risk. The application of machine learning algorithms to PPG-derived HRV analysis offers a promising approach for improving CVD risk stratification and facilitating the development of personalized medicine strategies. Background/Objectives: To evaluate the potential of heart rate variability indicators in predicting the risk of developing CVD in individuals aged 65 years and older. Methods: The study involved individuals aged 65 years and older, divided into two groups: those with a risk of developing CVD (n = 54) and those without risk (n = 46). The first stage included a questionnaire as well as anthropometric and hemodynamic measurements. At the second stage, a PPG was performed using the Eldar computer photoplethysmograph and Eldar-Vario software, followed by an analysis of time-domain and spectral HRV parameters. Statistical data analysis was conducted using the SPSS Statistics 22.0 software package, focusing on the evaluation of associations between HRV indicators and the presence of CVD. Interpretable machine learning models were developed using logistic regression and a random forest algorithm within a nested cross-validation framework. In addition to the discriminatory characteristics, Brier score, LogLoss, calibration analysis, error matrices, permutation importance, and SHAP interpretation were analyzed in the study. Results: In patients with cardiovascular diseases, a statistically significant decrease in heart rate variability was revealed: SDNN by 2 times (26 [Q1–Q3: 15, 35] ms), pNN50 by 3.5 times (4 [3, 5]%), TINN by 5 times (31 [20, 51] ms), and HRV by 2.5 times (6 [4, 8.7]). In addition, a decrease was seen in the spectral components of VLF by one-fold (2450 [Q1–Q3: 2450, 4500] ms²), LF by four-fold (750 [750, 1500] ms²) and HF by five-fold (450 [450, 750] ms²) (p < 0.05). At the same time, there was a significant increase in the VLF/HF and LF/HF ratios, which indicates a predominance of sympathetic activity. According to the results of the correlation analysis, statistically significant associations of HRV indicators with age, physical activity level, body mass index and systolic blood pressure were revealed. The results of machine learning also revealed the association of HRV with arterial hypertension, physical activity and BMI. The best final results were demonstrated by a random forest model with a combined set of clinical and HRV signs of HF and RMSSD (ROC-AUC was 0.9988). The signs of heart rate variability obtained by photoplethysmography demonstrated additional prognostic value in relation to clinical signs. PPG-derived HRV features demonstrated additional discriminatory value for cardiovascular risk stratification. Conclusions: The obtained data demonstrate a close association between the risk of developing cardiovascular disease and autonomic nervous system dysfunction. The decrease in heart rate variability is most pronounced in elderly individuals with existing cardiovascular disease and can be considered a potential tool for developing diagnostic, prognostic, and risk stratification strategies. The use of machine learning demonstrated that heart rate variability features obtained using photoplethysmography improve diagnostic prognostication and classification of cardiovascular diseases compared to models based solely on clinical data. Full article

The growing demand for reliable wearable devices that can continuously monitor vital signs and track health under various conditions imposes challenging constraints on battery life. Wearable devices typically include a Photoplethysmogram (PPG) sensor, which is used for various applications such as monitoring heart rate (HR) and blood oxygenation (${\mathrm{SpO}}_2$). The efficiency of these applications depends on the quality of the PPG sensor, which acquires raw data through the analog front-end and transmits it externally. This paper presents a digital block that evaluates the quality of the PPG signal directly within the ASIC. The proposed Signal Quality Assessment (SQA) module is derived from post-processing algorithms and translated into a real-time, single-sample evaluation approach, providing significant benefits at both the sensor and system levels. The proposed solution achieves performance comparable to state-of-the-art methods, with a sensitivity of 95.2%, a specificity of 88.1%, and an accuracy of 89.52%, while introducing an extremely low energy overhead equal to $5.38$ μ$\mathrm{J}$. Full article

Sleep monitoring and analysis are essential for understanding overall health, improving sleep quality, and detecting potential disorders early. This study presents a multimodal approach for automatic sleep staging and quality assessment using a reduced set of bio-signals: a single electroencephalographic (EEG) lead (F4–F3), a single EOG lead, and the photo-plethysmographic (PPG) signal. The proposed methodology includes a hierarchical sleep staging classifier, an automatic sleep staging algorithm, and a subject-specific Sleep Quality Index (SQI) for objective sleep quality assessment. The 5-class sleep staging classifier employs a cascaded architecture of two sequential 3-class models (Wake-REM-NREM and N1-N2-N3), trained and tested on multimodal features derived from physiological signals (EEG, EOG, and PPG) of the BOAS (Bitbrain Open Access Sleep) dataset. The resulting 5-class classifier achieved 90.8% accuracy with a reduced memory footprint (3.14 MB). To assess subject-independent generalization and prevent data leakage between training and test sets, a Leave-One-Subject-Out (LOSO) validation was performed, confirming the robustness of the proposed classifier across unseen subjects. The classifier was subsequently integrated into an automatic sleep staging algorithm. Validation on 14 unseen subjects yielded accuracies ranging from 80.26% to 91.99% using heuristic post-processing rules, while a Hidden Markov Model (HMM)-based approach further improved performance, reaching a peak accuracy of 91.99%. The proposed SQI combines sleep-related metrics extracted from staging, considering multiple sleep aspects (i.e., duration, intensity, and continuity-fragmentation). A calibration strategy was proposed to customize the SQI based on sleep scoring parameters and the subjective quality score derived from sleep diaries and questionnaires (PSQI). This subject-specific strategy was validated on a public dataset, optimizing weights across multiple nights, followed by an independent test on a subsequent night and demonstrating strong alignment between the calculated SQI and the subjective sleep quality score (MAE = 10.81). Finally, the framework provides resource-efficient sleep staging and custom quality estimation, validating its readiness for practical, long-term sleep monitoring. Full article

Wearable sensors enable continuous recording of electrocardiographic, photoplethysmographic, and inertial signals and have accelerated the development of digital biomarkers in cardiovascular medicine. Transthyretin amyloidosis (ATTR) is a progressive multisystem disease characterized by arrhythmia, conduction disturbances, hemodynamic impairment, autonomic dysfunction, and gait abnormalities, making it theoretically suitable for multimodal wearable monitoring. This review summarizes current knowledge on wearable applications in amyloidosis with ATTR serving as an illustrative case, evaluates the plausibility of extrapolating signal-based biomarkers from related cardiovascular and neurological cohorts, and outlines methodological and implementation challenges. ATTR-specific data remain limited to small observational studies, mainly on long-term rhythm monitoring and supervised functional assessment. More comprehensive findings support the extraction of metrics such as atrial fibrillation burden, activity patterns, gait variability, and heart rate variability. However, ATTR-related structural remodeling and high arrhythmia burden may distort conventional digital biomarkers, necessitating disease-specific preprocessing and prospective validation. Wearable monitoring in ATTR is technically feasible and biologically plausible but remains investigational. Before routine integration into care pathways can be recommended, standardized, phenotype-stratified studies are needed that link wearable-derived characteristics to assessed clinical outcomes. Full article

(1) Background: Heartbeat detection from electrocardiogram (ECG) and photoplethysmograph (PPG) signals is widely used in wearable devices for health monitoring, fitness tracking, and stress assessment. While numerous methods have been proposed, their practical suitability depends not only on accuracy but also on computational and memory constraints inherent to resource-limited systems. (2) Methods: A scoping review of 52 studies published between 2017 and 2024 was conducted, covering time-domain, frequency-domain, matrix-based, and machine learning approaches. The methods were evaluated according to estimation accuracy, computational complexity, memory footprint, and suitability for on-device implementation. (3) Results: Time-domain peak detection methods consistently provide high accuracy (minimum of $79.25$%, maximum of $99.96$%, and median $\ge 99.69$%) for ECG and reliable heart rate estimation for PPG with linear computational complexity, low memory requirements and low energy consumption. Frequency-domain approaches are suitable for average heart rate estimation from PPG but do not preserve inter-beat intervals (error range of [1.07, 6.4] beats per minute (BPM)). Matrix-based and machine learning methods often entail higher computational cost without proportional performance gains in wearable contexts (error range of [1.07, 6.4] BPM for PPG signals; accuracy in range of $[95.4, 99.96]$% for ECG). (4) Conclusions: Lightweight signal-processing techniques offer the most favorable trade-off between accuracy and efficiency for wearable implementations, whereas computationally intensive approaches are better suited for edge- or cloud-based processing. Full article

This work presents a time-domain analog-to-digital conversion method in which the amplitude of a sensor signal is encoded through its crossing instants with a periodic ramp. The proposed architecture departs from conventional ADC and PWM demodulation approaches by shifting quantization entirely to the time domain, enabling waveform reconstruction using only a ramp generator, an analog comparator, and a timer capture module. A theoretical framework is developed to formalize the voltage-to-time mapping, derive expressions for resolution and error, and identify the conditions ensuring monotonicity and single-crossing behavior. Simulation results demonstrate high-fidelity reconstruction for both periodic and non-periodic signals, including real photoplethysmographic (PPG) waveforms, with errors approaching the theoretical quantization limit. A hardware implementation on a PSoC 5LP microcontroller confirms the practicality of the method under realistic operating conditions. Despite ramp nonlinearity, comparator delay, and sensor noise, the system achieves effective resolutions above 12 bits using only native mixed-signal peripherals and no conventional ADC. These results show that accurate waveform reconstruction can be obtained from purely temporal information, positioning time-encoded sensing as a viable alternative to traditional amplitude-based conversion. The minimal analog front end, low power consumption, and scalability of timer-based processing highlight the potential of the proposed approach for embedded instrumentation, distributed sensor nodes, and biomedical monitoring applications. Full article

This study presents the design and validation of an open-source framework for biomedical signal acquisition and interoperable data exchange based on the Health Level Seven—Fast Healthcare Interoperability Resources (HL7 FHIR) standard. The proposed system enables secure, wireless transmission of physiological data from distributed sensing nodes toward a locally hosted monitoring platform. The hardware architecture integrates ESP32-WROOM-32 microcontrollers for multi-parameter acquisition, the MQTT protocol for low-latency communication, and a Home Assistant (Nabu Casa, San Diego, CA, USA)–InfluxDB (InfluxData, San Francisco, CA, USA)–Grafana (Grafana Labs, New York, NY, USA) stack for real-time visualization. The novelty of this work lies in the full-stack implementation of HL7 FHIR Observations within a reproducible, open-source environment, ensuring semantic interoperability without reliance on proprietary middleware or cloud services. A case study involving multi-sensor acquisition of electrocardiographic (ECG), photoplethysmographic (PPG), temperature, and oxygen saturation signals was conducted to evaluate system performance. Validation results confirmed consistent end-to-end data flow, sub-second latency, zero packet loss, and accurate semantic preservation across all processing stages. These findings demonstrate the feasibility of implementing standardized, open, and scalable biomedical Internet of Medical Things (IoMT) systems using non-proprietary components. The proposed framework provides a reproducible foundation for future telemedicine and continuous patient-monitoring applications, aligning with FAIR data principles and the ongoing digital transformation of healthcare. Full article

Atrial fibrillation (AF) is the most common type of heart rhythm disorder worldwide. Early recognition of brief episodes of atrial fibrillation can provide important diagnostic information and lead to prompt treatment. AF is mainly characterized by an irregular heartbeat. Today, many personal devices such as smartphones, smartwatches, smart rings, or small wearable medical devices can detect heart rhythm. Sensors can acquire different types of heart-related signals and extract the sequence of inter-beat intervals, i.e., the instantaneous heart rate. Various algorithms, some of which are very complex and require significant computational resources, are used to recognize AF based on inter-beat intervals (RR). This study aims to verify the possibility of using neural networks algorithms directly on a microcontroller connected to sensors for AF detection. Sequences of 25, 50, and 100 RR were extracted from a public database of electrocardiographic signals with annotated episodes of atrial fibrillation. A custom 1D convolutional neural network (1D-CNN) was designed and then validated via a 5-fold subject-wise split cross-validation scheme. In each fold, the model was tested on a set of 3 randomly selected subjects, which had not previously been used for training, to ensure a subject-independent evaluation of model performance. Across all folds, all models achieved high and stable performance, with test accuracies of 0.963 ± 0.031, 0.976 ± 0.022, and 0.980 ± 0.023, respectively, for models using 25 RR, 50 RR, and 100 RR sequences. Precision, recall, F1-score, and AUC-ROC exhibited similarly high performance, confirming robust generalization across unseen subjects. Performance systematically improved with longer RR windows, indicating that richer temporal context enhances discrimination of AF rhythm irregularities. A complete Edge AI prototype integrating a low-power ECG analog front-end, an ARM Cortex M7 microcontroller and an IoT transmitting module was utilized for realistic tests. Inferencing time, peak RAM usage, flash usage and current absorption were measured. The results obtained show the possibility of using neural network algorithms directly on microcontrollers for real-time AF recognition with very low power consumption. The prototype is also capable of sending the suspicious ECG trace to the cloud for final validation by a physician. The proposed methodology can be used for personal screening not only with ECG signals but with any other signal that reproduces the sequence of heartbeats (e.g., photoplethysmographic, pulse oximetric, pressure, accelerometric, etc.). Full article

This study proposes an enhanced deep learning framework for accurate detection of P-peaks in noisy photoplethysmographic (PPG) signals, utilizing a hybrid architecture that integrates wavelet-based analysis with neural network components. The P-peak detection task is formulated as a binary classification problem, where the model learns to identify the presence of a peak at each time step within fixed-length input windows. A temporal attention mechanism is incorporated to dynamically focus on the most informative regions of the signal, improving both localization and robustness. The proposed architecture combines Discrete Wavelet Transform (DWT) for multiscale signal decomposition, Convolutional Neural Networks (CNNs) for morphological feature extraction, and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies. A temporal attention layer is introduced after the recurrent layers to enhance focus on time steps with the highest predictive value. An evaluation was conducted on 30 model variants, exploring different combinations of input types, decomposition levels, and activation functions. The best-performing model—Type30, which includes DWT (3 levels), CNN, LSTM, and attention—achieves an accuracy of 0.918, precision of 0.932, recall of 0.957, and F1-score of 0.923. The findings demonstrate that attention-enhanced hybrid architectures are particularly effective in handling signal variability and noise, making them highly suitable for real-world applications in wearable PPG monitoring, digital twins for Heart Rate Variability (HRV), and intelligent health systems. Full article

The second derivative of the photoplethysmographic signal presents five relevant points that provide information about the structural properties of arteries. This study investigates the ratio between the amplitude of the d wave (end of systole) and the a wave (beginning of systole) as a potential indicator of vascular aging. The research combines an in vitro study on silicone models with different stiffness and an in vivo study on volunteers aged between 26 and 63 years. The results show a strong negative correlation between the d/a ratio and arterial stiffness, confirming the potential of this parameter as a noninvasive index for assessing vascular health status. Full article

Worldwide less than half of adults with hypertension are diagnosed and treated (only 42%), in addition one in five adults with hypertension (21%) has the condition under control. In the American continent, cardiovascular diseases (CVD) are the leading cause of death and high blood pressure (hypertension) is responsible for 50% of CVD deaths. Only a few countries show a population hypertension control rate of more than 50%. In this experimental study, we trained 15 regression-type machine learning algorithms, including traditional and ensemble methods to assess their effectiveness in estimating arterial pressure using noninvasive photoplethysmographic (PPG) signals extracted from 110 study subjects, to identify the risk of hypertension and its correlation with arteriosclerosis. We analyzed the performance of each algorithm using the metrics MSE, MAE, RMSE, and r². A 10-fold cross-validation showed that the best algorithms for hypertension risk identification were LR, KNN, SVR, RF, LR Baggin, KNNBagging, SVRBagging, and DTBagging. On the other hand, the best algorithms for arterioclesrosis risk identification were LR, KNN, SVR, RF, LR Bagging, and DTBagging. These results suggest that this research is promising and offers valuable information on the acquisition and processing of PPG signals. However, as this is an experimental study, the effectiveness of our model needs to be validated with a larger database. On the other hand, this model represents a support tool for healthcare specialists in the early detection of cardiovascular health, allowing people to self-manage their health and seek medical attention at an early stage. Full article

This study describes the design and validation of an experimental setup for testing photoplethysmographic (PPG) devices intended for the non-invasive monitoring of vascular accesses in hemodialysis patients. Continuous assessment of arteriovenous fistulas is essential to detect pathological conditions such as stenosis, which can compromise patient safety and dialysis efficacy. While PPG-based sensors are capable of detecting such anomalies, their clinical applicability must be supported by controlled in vitro validation. The developed system replicates the anatomical, mechanical, optical, and hemodynamic features of vascular accesses. A 3D fistula model was designed and fabricated via 3D printing and silicone casting. The hydraulic circuit used red India ink and a PWM-controlled pump to simulate physiological blood flow, including stenotic conditions. Quantitative validation confirmed anatomical accuracy within 0.1 mm tolerance. The phantom exhibited an average Shore A hardness of 20.3 ± 1.1, a Young’s modulus of 10.4 ± 0.9 MPa, and a compression modulus of 105 MPa—values consistent with soft tissue behavior. Burst pressure exceeded 2000 mmHg, meeting ISO 7198:2016 standards. Flow rates (400–700 mL/min) showed <1% error. Compliance was 2.4 ± 0.2, and simulated blood viscosity was 3.9 ± 0.3 mPa·s. Systolic and diastolic pressures fell within physiological ranges. Photoplethysmographic signals acquired using a MAX30102 sensor (Analog devices Inc., Wilmington, MA, USA) reproduced key components of in vivo waveforms, confirming the system’s suitability for device testing. Full article

This study presents an algorithm for non-invasive blood pressure (BP) estimation in neonates using photoplethysmography (PPG), suitable for resource-constrained neonatal telecare platforms. Using the Windkessel model, the algorithm processes PPG signals from a MAX 30102 sensor, (Analog Devices (formerly Maxim Integrated), based in San Jose, CA, USA) filtering motion noise and extracting cardiac cycle time and systolic time (ST). These parameters inform a derived blood flow signal, the input for the Windkessel model. Calibration utilizes average parameters based on the newborn’s post-conceptional age, weight, and gestational age. Performance was validated against readings from a standard non-invasive BP cuff at SES Hospital Universitario de Caldas. Two parameter estimation methods were evaluated. The first yielded root mean square errors (RMSEs) of 24.14 mmHg for systolic and 19.13 mmHg for diastolic BP. The second method significantly improved accuracy, achieving RMSEs of 2.31 mmHg and 5.13 mmHg, respectively. The successful adaptation of the Windkessel model to single PPG signals allows for BP calculation alongside other physiological variables within the telecare program. A device analysis was conducted to determine the appropriate device based on computational capacity, availability of programming tools, and ease of integration within an Internet of Things environment. This study paves the way for future research that focuses on parameter variations due to cardiovascular changes in newborns during their first month of life. Full article