Objective. Photoplethysmography is a non-invasive optical technique that measures changes in blood volume within tissues. It is commonly and being increasingly used for a variety of research and clinical applications to assess vascular dynamics and physiological parameters. Yet, contrary to heart rate variability measures, a field which has seen the development of stable standards and advanced toolboxes and software, no such standards and limited open tools exist for continuous photoplethysmogram (PPG) analysis. Consequently, the primary objective of this research was to identify, standardize, implement and validate key digital PPG biomarkers. Approach. This work describes the creation of a standard Python toolbox, denoted pyPPG, for long-term continuous PPG time-series analysis and demonstrates the detection and computation of a high number of fiducial points and digital biomarkers using a standard fingerbased transmission pulse oximeter. Main results. The improved PPG peak detector had an F1-score of 88.19% for the state-of-the-art benchmark when evaluated on 2054 adult polysomnography recordings totaling over 91 million reference beats. The algorithm outperformed the open-source original Matlab implementation by ∼5% when benchmarked on a subset of 100 randomly selected MESA recordings. More than 3000 fiducial points were manually annotated by two annotators in order to validate the fiducial points detector. The detector consistently demonstrated high performance, with a mean absolute error of less than 10 ms for all fiducial points. Significance. Based on these fiducial points, pyPPG engineered a set of 74 PPG biomarkers. Studying PPG time-series variability using pyPPG can enhance our understanding of the manifestations and etiology of diseases. This toolbox can also be used for biomarker engineering in training data-driven models. pyPPG is available on https://physiozoo.com/.

Objective. Electrocardiographic (ECG) lead misplacement can result in distorted waveforms and amplitudes, significantly impacting accurate interpretation. Although lead misplacement is a relatively low-probability event, with an incidence ranging from 0.4% to 4%, the large number of ECG records in clinical practice necessitates the development of an effective detection method. This paper aimed to address this gap by presenting a novel lead misplacement detection method based on deep learning models. Approach. We developed two novel lightweight deep learning model for limb and chest lead misplacement detection, respectively. For limb lead misplacement detection, two limb leads and V6 were used as inputs, while for chest lead misplacement detection, six chest leads were used as inputs. Our models were trained and validated using the Chapman database, with an 8:2 train-validation split, and evaluated on the PTB-XL, PTB, and LUDB databases. Additionally, we examined the model interpretability on the LUDB databases. Limb lead misplacement simulations were performed using mathematical transformations, while chest lead misplacement scenarios were simulated by interchanging pairs of leads. The detection performance was assessed using metrics such as accuracy, precision, sensitivity, specificity, and Macro F1-score. Main results. Our experiments simulated three scenarios of limb lead misplacement and nine scenarios of chest lead misplacement. The proposed two models achieved Macro F1-scores ranging from 93.42% to 99.61% on two heterogeneous test sets, demonstrating their effectiveness in accurately detecting lead misplacement across various arrhythmias. Significance. The significance of this study lies in providing a reliable open-source algorithm for lead misplacement detection in ECG recordings. The source code is available at https://github.com/wjcai/ECG_lead_check.

Objective. This study aimed to examine differences in heart rate variability (HRV) across accelerometer-derived position, self-reported sleep, and different summary measures (sleep, 24 h HRV) in free-living settings using open-source methodology. Approach. HRV is a biomarker of autonomic activity. As it is strongly affected by factors such as physical behaviour, stress, and sleep, ambulatory HRV analysis is challenging. Beat-to-beat heart rate (HR) and accelerometry data were collected using single-lead electrocardiography and trunk- and thigh-worn accelerometers among 160 adults participating in the SCREENS trial. HR files were processed and analysed in the RHRV R package. Start time and duration spent in physical behaviours were extracted, and time and frequency analysis for each episode was performed. Differences in HRV estimates across activities were compared using linear mixed models adjusted for age and sex with subject ID as random effect. Next, repeated-measures Bland–Altman analysis was used to compare 24 h RMSSD estimates to HRV during self-reported sleep. Sensitivity analyses evaluated the accuracy of the methodology, and the approach of employing accelerometer-determined episodes to examine activity-independent HRV was described. Main results. HRV was estimated for 31 289 episodes in 160 individuals (53.1% female) at a mean age of 41.4 years. Significant differences in HR and most markers of HRV were found across positions [Mean differences RMSSD: Sitting (Reference) − Standing (−2.63 ms) or Lying (4.53 ms)]. Moreover, ambulatory HRV differed significantly across sleep status, and poor agreement between 24 h estimates compared to sleep HRV was detected. Sensitivity analyses confirmed that removing the first and last 30 s of accelerometry-determined HR episodes was an accurate strategy to account for orthostatic effects. Significance. Ambulatory HRV differed significantly across accelerometry-assigned positions and sleep. The proposed approach for free-living HRV analysis may be an effective strategy to remove confounding by physical activity when the aim is to monitor general autonomic stress.

Objective. Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution. Approach. We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background. Main results. As a case study, we used ECG-Image-Kit to create a dataset of 21 801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization. Significance. The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.

Objective. This paper aims to investigate the possibility of detecting tonic-clonic seizures (TCSs) with behind-the-ear, two-channel wearable electroencephalography (EEG), and to evaluate its added value to non-EEG modalities in TCS detection. Methods. We included 27 participants with a total of 44 TCSs from the European multicenter study SeizeIT2. The wearable Sensor Dot (Byteflies) was used to measure behind-the-ear EEG, electromyography (EMG), electrocardiography, accelerometry (ACC) and gyroscope. We evaluated automatic unimodal detection of TCSs, using sensitivity, precision, false positive rate (FPR) and F1-score. Subsequently, we fused the different modalities and again assessed performance. Algorithm-labeled segments were then provided to two experts, who annotated true positive TCSs, and discarded false positives. Results. Wearable EEG outperformed the other single modalities with a sensitivity of 100% and a FPR of 10.3/24 h. The combination of wearable EEG and EMG proved most clinically useful, delivering a sensitivity of 97.7%, an FPR of 0.4/24 h, a precision of 43%, and an F1-score of 59.7%. The highest overall performance was achieved through the fusion of wearable EEG, EMG, and ACC, yielding a sensitivity of 90.9%, an FPR of 0.1/24 h, a precision of 75.5%, and an F1-score of 82.5%. Conclusions. In TCS detection with a wearable device, combining EEG with EMG, ACC or both resulted in a remarkable reduction of FPR, while retaining a high sensitivity. Significance. Adding wearable EEG could further improve TCS detection, relative to extracerebral-based systems.

Objective. Sleep spindles contain crucial brain dynamics information. We introduce the novel non-linear time-frequency (TF) analysis tool ‘Concentration of Frequency and Time’ (ConceFT) to create an interpretable automated algorithm for sleep spindle annotation in EEG data and to measure spindle instantaneous frequencies (IFs). Approach. ConceFT effectively reduces stochastic EEG influence, enhancing spindle visibility in the TF representation. Our automated spindle detection algorithm, ConceFT-Spindle (ConceFT-S), is compared to A7 (non-deep learning) and SUMO (deep learning) using Dream and Montreal Archive of Sleep Studies (MASS) benchmark databases. We also quantify spindle IF dynamics. Main results. ConceFT-S achieves F1 scores of 0.765 in Dream and 0.791 in MASS, which surpass A7 and SUMO. We reveal that spindle IF is generally nonlinear. Significance. ConceFT offers an accurate, interpretable EEG-based sleep spindle detection algorithm and enables spindle IF quantification.

Objective. Time–frequency (T–F) analysis of electroencephalographic (EEG) is a common technique to characterise spectral changes in neural activity. This study explores the limitations of utilizing conventional spectral techniques in examining cyclic event-related cortical activities due to challenges, including high inter-trial variability. Approach. Introducing the cycle-frequency (C-F) analysis, we aim to enhance the evaluation of cycle-locked respiratory events. For synthetic EEG that mimicked cycle-locked pre-motor activity, C-F had more accurate frequency and time localization compared to conventional T–F analysis, even for a significantly reduced number of trials and a variability of breathing rhythm. Main results. Preliminary validations using real EEG data during both unloaded breathing and loaded breathing (that evokes pre-motor activity) suggest potential benefits of using the C-F method, particularly in normalizing time units to cyclic activity phases and refining baseline placement and duration. Significance. The proposed approach could provide new insights for the study of rhythmic neural activities, complementing T–F analysis.

Objective. This study aims to assess the sensitivity of epicardial potential-based electrocardiographic imaging (ECGI) to the removal or interpolation of bad leads. Approach. We utilized experimental data from two distinct centers. Langendorff-perfused pig (n = 2) and dog (n = 2) hearts were suspended in a human torso-shaped tank and paced from the ventricles. Six different bad lead configurations were designed based on clinical experience. Five interpolation methods were applied to estimate the missing data. Zero-order Tikhonov regularization was used to solve the inverse problem for complete data, data with removed bad leads, and interpolated data. We assessed the quality of interpolated ECG signals and ECGI reconstructions using several metrics, comparing the performance of interpolation methods and the impact of bad lead removal versus interpolation on ECGI. Main results. The performance of ECG interpolation strongly correlated with ECGI reconstruction. The hybrid method exhibited the best performance among interpolation techniques, followed closely by the inverse-forward and Kriging methods. Bad leads located over high amplitude/high gradient areas on the torso significantly impacted ECGI reconstructions, even with minor interpolation errors. The choice between removing or interpolating bad leads depends on the location of missing leads and confidence in interpolation performance. If uncertainty exists, removing bad leads is the safer option, particularly when they are positioned in high amplitude/high gradient regions. In instances where interpolation is necessary, the inverse-forward and Kriging methods, which do not require training, are recommended. Significance. This study represents the first comprehensive evaluation of the advantages and drawbacks of interpolating versus removing bad leads in the context of ECGI, providing valuable insights into ECGI performance.

Computational simulations are widely adopted in cardiovascular biomechanics because of their capability of producing physiological data otherwise impossible to measure with non-invasive modalities. Objective. This study presents openBF, a computational library for simulating the blood dynamics in the cardiovascular system. Approach. openBF adopts a one-dimensional viscoelastic representation of the arterial system, and is coupled with zero-dimensional windkessel models at the outlets. Equations are solved by means of the finite-volume method and the code is written in Julia. We assess its predictions by performing a multiscale validation study on several domains available from the literature. Main results. At all scales, which range from individual arteries to a population of virtual subjects, openBF’s solution show excellent agreement with the solutions from existing software. For reported simulations, openBF requires low computational times. Significance. openBF is easy to install, use, and deploy on multiple platforms and architectures, and gives accurate prediction of blood dynamics in short time-frames. It is actively maintained and available open-source on GitHub, which favours contributions from the biomechanical community.

Objective. Phonocardiography has recently gained popularity in low-cost and remote monitoring, including passive fetal heart monitoring. The development of methods which analyze phonocardiographic data tries to capitalize on this opportunity, and in recent years a multitude of such algorithms and models have been published. In these approaches there is little to no standardization and multiple parts of these models have to be reimplemented on a case-by-case basis. Datasets containing heart sound recordings also lack standardization in both data storage and labeling, especially in fetal phonocardiography. Approach. We are presenting a toolbox that can serve as a basis for a future standard framework for heart sound analysis. This toolbox contains some of the most widely used processing steps and with these, complex analysis pipelines can be created. These functions can be tested individually. Main results. Due to the interdependence of the steps, we validated the current segmentation stage using two phonocardiogram (PCG) datasets, a fetal dataset comprising 50 one-minute abdominal PCG recordings, which include 6758 S₁ and 6729 S₂ labels and a filtered version of the dataset used in the 2022 PhysioNet Challenge, containing 413 records with 9795 S₁ and 9761 S₂ labels. Our results were compared to other common and publicly available segmentation methods, such as peak detection with the Neurokit2 library, and the hidden semi-Markov model by Springer et al. Our best model achieved a 96.1% F1 score and 11.7 ms mean absolute error for fetal S₁ detection, and 81.3% F1 score and 50.5 ms mean absolute error for PhysioNet S₁ detection. Significance. Our detection method outperformed all other tested methods on the fetal dataset and achieved results comparable to the state of the art on the PhysioNet dataset. Accurate segmentation of signals is critical for the calculation of accurate statistical measures and the creation of classification models. Our toolbox contains functions for both feature extraction and calculation of statistics which are compatible with the previous steps. All of our methods can be fine tuned for specific datasets. pyPCG is available on https://pypcg-toolbox.readthedocs.io/en/latest/.

Objective. In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself. Approach. This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed to address these challenges by converting Python-based AI models into platform-independent hardware description language code accelerators. Specifically designed for convolutional neural networks, tinyHLS seamlessly integrates into the AI developer’s workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit is supported as activation. It targets one-dimensional data, with a particular focus on time series data. Main results. The generated accelerators are validated in detecting atrial fibrillation on ECG data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools. Significance. Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISC-V and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub: https://github.com/Fraunhofer-IMS/tinyHLS

Heart rate variability (HRV) analysis during sleep plays a key role for understanding autonomic nervous system function and assessing cardiovascular health. The UNICA Sleep HRV analysis (UNICA-HRV) tool is a novel, open-source MATLAB tool designed to fill the gap in current HRV analysis tools. In particular, the integration of ECG and HRV data with hypnogram information, which illustrates the progression through the different sleep stages, eases the computation of HRV metrics in polysomnographic recordings. This integration is crucial for accurate phase-specific analysis, as autonomic regulation changes markedly across different sleep stages. The tool supports single- and multiple-subject analyses and is tailored to enhance usability and accessibility for researchers and clinicians without requiring extensive technical expertise. It implements and supports a variety of data inputs and configurations, allowing for flexible, detailed HRV analyses across sleep stages, employing classical and advanced metrics, such as time-domain, frequency-domain, non-linear, complexity, and Poincaré plot indexes. Validation of the tool against established tools like Kubios and PhysioZoo indicates its robustness and precision in generating reliable HRV metrics, that are essential not only for sleep research, but also for clinical diagnostics. The introduction of UNICA-HRV represents a significant simplification for sleep studies, and its open-source nature (licensed under a Creative Commons Attribution 4.0 International License) allows to easily extend the functionality to other needs.

Objective. Heart rate variability (HRV) is an important indicator of cardiac autonomic function. Given its clinical significance, reliable HRV assessment is crucial. Here, we assessed test–retest stability, as a key aspect of reliability, quantifying the consistency of a measure when repeated under the same conditions. Approach. This observational study includes healthy individuals. A 20 min electrocardiogram was recorded at rest in a supine position and during deep breathing in two lab sessions within one week, at the same time of day. HRV indices from time domain, frequency domain, nonlinear dynamics, and information-theoretic complexity were assessed using a validated toolbox. Additionally, heart rate variations per respiratory cycle were evaluated during deep breathing. Lifestyle factors such as perceived stress, mood, physical activity, sleep quality were assessed prior to both sessions. Intra-class correlation (ICC) and coefficients of variation (CVs) were used to assess the concordance between the two measurements and the relative deviation, respectively. Main results. From 62 screened individuals, 51 participants were recruited from the local community. One participant opted out for personal reasons, and another with frequent premature beats was excluded, leaving a final sample of 49 individuals. Most self-rated psychological and lifestyle indicators showed substantial agreement, though participants reported less stress and better mood in the second session. At rest, ICC of HRV ranged from 0.50 to 0.83, with CV from 5% to 41%. Spectral HRV measures were less reliable than time domain parameters. Nonlinear and time domain features had substantial to nearly perfect agreement. Complexity measures had low CVs but limited test–retest correlation. The stability indices of HRV during deep breathing were not significantly different from those during rest. Test–retest differences in root mean square of the successive beat-to-beat interval difference were not sufficiently explained by lifestyle factors. Significance. Test–retest stability of HRV depends considerably on chosen measures. Our data suggest that HRV can be assessed reliably using time-domain indices at rest.

Objective. Sleep staging is a crucial task in clinical and research contexts for diagnosing and understanding sleep disorders. This work introduces PhysioEx (Physiological Signal Explainer), a Python library designed to support the analysis of sleep stages using deep learning (DL) and Explainable AI (XAI). Approach. PhysioEx provides an extensible and modular API for standardizing and automating the sleep staging pipeline, covering data preprocessing, model training, testing, fine-tuning, and explainability. It supports both low-resource devices and high-performance computing clusters and includes pretrained models based on the Sleep Heart Health Study dataset. These models support single-channel EEG and multichannel EEG-EOG-EMG configurations and are easily adaptable to custom datasets. PhysioEx also features a command-line interface toolbox allowing users to streamline the model development and deployment. The library offers a range of XAI post-hoc methods to explain model decisions and align them with expert knowledge. Main results. PhysioEx benchmark state-of-the-art sleep staging models in a standard pipeline. Enabling a fair comparison between them both on the training source and out-of-domain sources. Its XAI techniques provide insights into DL-based sleep staging by linking model decisions to human-understandable concepts, such as American Academy of Sleep Medicine-defined rules. Significance. PhysioEx addresses the need for a standardized and accessible platform for sleep staging analysis, combining DL and XAI. By supporting modular workflows and explainable insights, it bridges the gap between machine learning models and clinical expertise. PhysioEx is publicly available and installable via pip⁶, making it a valuable tool for researchers and practitioners in sleep medicine.

Objective: photoplethysmography is widely used for physiological monitoring, whether in clinical devices such as pulse oximeters, or consumer devices such as smartwatches. A key step in the analysis of photoplethysmogram (PPG) signals is detecting heartbeats. The multi-scale peak & trough detection (MSPTD) algorithm has been found to be one of the most accurate PPG beat detection algorithms, but is less computationally efficient than other algorithms. Therefore, the aim of this study was to develop a more efficient, open-source implementation of the MSPTD algorithm for PPG beat detection, named MSPTDfast (v.2). Approach. five potential improvements to MSPTD were identified and evaluated on four datasets. MSPTDfast (v.2) was designed by incorporating each improvement which on its own reduced execution time whilst maintaining a high F₁-score. After internal validation, MSPTDfast (v.2) was benchmarked against state-of-the-art beat detection algorithms on four additional datasets. Main results. MSPTDfast (v.2) incorporated two key improvements: pre-processing PPG signals to reduce the sampling frequency to 20 Hz; and only calculating scalogram scales corresponding to heart rates >30 bpm. During internal validation MSPTDfast (v.2) was found to have an execution time of between approximately one-third and one-twentieth of MSPTD, and a comparable F₁-score. During benchmarking MSPTDfast (v.2) was found to have the highest F₁-score alongside MSPTD, and amongst one of the lowest execution times with only MSPTDfast (v.1), qppgfast and MMPD (v.2) achieving shorter execution times. Significance. MSPTDfast (v.2) is an accurate and efficient PPG beat detection algorithm, available in an open-source Matlab toolbox.

Objective. Forced expiratory volume in one second (FEV1) is an important metric for patients to track at home for their self-management of asthma and chronic obstructive pulmonary disease (COPD). Unfortunately, the state-of-the-art for measuring FEV1 at home either depends on the patient’s physical effort and motivation, or relies on bulky wearable devices that are impractical for long-term monitoring. This paper explores the feasibility of using a machine learning model to infer FEV1 from 270 seconds of a single-lead electrocardiogram (ECG) signal measured on the fingers with a mobile device. Methods. We evaluated the model’s inferred FEV1 values against the ground truth of hospital-grade spirometry tests, which were performed by twenty-five patients with obstructive respiratory disease. Results. The model-inferred FEV1 compared to the spirometry-measured FEV1 with a correlation coefficient of r = 0.73, a mean absolute percentage error of 23% and a bias of −0.08. Conclusions. These results suggest that the ECG signal contains useful information about FEV1, although a larger, richer dataset might be necessary to train a machine learning model that can extract this information with better accuracy. Significance. The benefit of a mobile ECG-based solution for measuring FEV1 is that it would require minimal effort, thus encouraging patient adherence and promoting successful self-management of asthma and COPD.