Computer Methods and Programs in Biomedicine

One goal of Scientific Machine Learning (SciML) is to advance traditional scientific computing frameworks with modern machine learning tools. This includes extending established methods, such as the finite element method, with cardiac function applications due to their complexity and need for very rapid execution times for real time clinical use. In this work, we present an advanced form of the Neural Network Finite Element (NNFE) method specialized for cardiac simulations, termed CARDIAX-NNFE. The NNFE method learns the parameter-to-displacement field map by training over the residual of the hyperelastic material PDE, using the domain represented by finite elements. The implementation is developed in Python using JAX to leverage its automatic differentiation, highly parallel GPU, and JIT-compilation capabilities. To demonstrate CARDIAX-NNFE effectiveness, we trained full cardiac pressure-volume responses using a simplified heart model, spanning the entire cardiac physiological functional range. Results indicated the ability to simulate a family of pressure-volume solutions with average nodal positional error of 0.023 mm and maximal error of 0.054 mm, with a single complete PV loop evaluated in 0.002 seconds. The CARDIAX-NNFE software platform thus provides for a robust platform for cardiac functional simulations. Moreover, it provides the structure for residual-based SciML methods, which can apply to a variety of physics-based biomedical problems that require high execution speed for clinical applications.

Background. Whether predictors of intraoperative hypotension (IOH) add information beyond the mean arterial pressure (MAP) already displayed on the monitor is contested: selection bias in common evaluation designs inflates apparent performance, and the field has called for comparisons against simple MAP-based references under bias-resistant protocols. Existing predictors also depend on proprietary waveform analysis or pulse-contour monitors, restricting both deployment and external validation. Methods. Using 807 non-cardiac surgery patients from the open VitalDB database, we derived an additive gradient boosting model (one split per tree: a learned shape function per variable, no interactions) from three variables computable from an arterial line alone: current MAP, its drift from the patient's own 20-minute baseline, and the growth of its rolling variance (critical slowing down). Evaluation used patient-level 5-fold cross-validation under a strict protocol - exclusion of the 65-75 mmHg grey zone and of all samples already hypotensive at prediction time - with MAP alone (same learner class) as comparator. The frozen model was then validated, without any refitting, on an independent cohort from another continent (MOVER, University of California Irvine) following a pre-registered plan sealed before external data access. Results. In development the pressure-only model reached AUROC 0.907 vs. 0.884 for MAP alone (Delta AUROC +0.023, 95% CI +0.017 to +0.029) at 5 min, with +0.031 and +0.032 at 10 and 15 min, and good calibration (Brier skill +0.418 vs. prevalence). In external validation on 3,069 patients (442,194 samples, 1-minute charting, event prevalence 5.8%), the advantage not only transferred but was larger than in development: AUROC 0.696 vs. 0.638, Delta AUROC +0.058 (95% CI +0.051 to +0.064), meeting both pre-registered gates. Discrimination transferred; calibration did not (external Brier skill -0.014), requiring local recalibration. In the unrestricted scenario, where samples already at threshold are retained, the advantage collapsed (+0.007), reproducing the selection effect this paper documents. A secondary model adding pulse-contour cardiac output and stroke volume variation improved development discrimination further (Delta AUROC +0.035) but could be externally validated in only 39 patients, because those signals are rarely recorded. Conclusions. The dynamics of arterial pressure itself - drift from a patient-specific baseline and variance growth - carry predictive information beyond its current value, in a fully interpretable additive model that requires only an arterial line, no waveform access and no proprietary hardware. The advantage is confirmed in a pre-registered frozen-model external validation of over three thousand patients, and is largest at coarse recording cadence, where instantaneous pressure is least informative.

golgi is an open-source platform that takes a peripheral nerve from image to stimulated fiber population through a single graphical interface, with an equivalent scriptable Python API and command-line interface for batch and high-performance use. It integrates promptable image segmentation, automated multi-region tetrahedral meshing, anisotropic finite-element solution of the extracellular field with an explicit perineurium contact impedance, generation of realistic fiber populations and their three-dimensional trajectories, and biophysical activation thresholds through interchangeable backends-- NEURON (via PyFibers) and a GPU-accelerated surrogate (AxonML). Every study exports as an integrity-hashed bundle whose image-to-recruitment provenance is verifiable byte-for-byte. golgi lowers the barrier to in-silico peripheral nerve stimulation modeling for experimentalists and clinicians, using a fully open finite-element stack with no commercial dependencies.

Ventricular tachycardia (VT) and ventricular fibrillation (VF) are the leading electrical causes of sudden cardiac death, but automated detection is limited by strong class imbalance, where lethal arrhythmias account for fewer than 22% of ECG segments. In this setting, standard classifiers can achieve high accuracy by predicting normal rhythm in most cases while missing many lethal events, a failure mode referred to as rare-class collapse. We evaluated six imbalance-handling approaches: naive logistic regression, inverse-frequency reweighting, label-distribution-aware margin loss (LDAM), cost-sensitive training, two-stage cascade classification, and anomaly detection on 15,614 ECG segments from three PhysioNet databases (VTaC, VFDB, CUDB), with an overall normal-to-lethal ratio of 3.6:1. All methods were assessed at a fixed operating point of 95% specificity using recall, area under the precision-recall curve (AUPRC), and missed-lethal-event rate (MLER). The naive model achieved 45.1% recall (MLER = 0.549), missing 564 of 1,027 lethal events despite 84.1% accuracy. The two-stage cascade performed best, with 65.2% recall, AUPRC of 0.821, and MLER of 0.348, reducing missed events by 37% and achieving the highest decision-curve net benefit. Per-source analysis showed near-complete VF detection (recall up to 0.975) but much lower VT detection (recall 0.183), suggesting a feature-space limitation due to spectral similarity between organized VT and rapid sinus rhythm. Overall, the results show that evaluation metrics strongly influence the visibility of rare-class failure, and that cascade-based methods outperform simpler reweighting approaches for detecting lethal arrhythmias.

Non-valvular atrial fibrillation (AF) is associated with a five-fold increased risk of stroke, mainly due to impaired contractility of the left atrium (LA) leading to blood stasis and subsequent thrombus formation within the left atrial appendage (LAA). Current AF stroke risk stratification schemes, such as the CHA2DS2-VASc/ CHA2DS2-VA score, use comorbidities and do not capture mechanistic factors like blood flow dynamics and hypercoagulability. To address this, we developed a multiphase computational fluid dynamics (CFD) model of the LA, incorporating patient-specific geometries; modelling of the coagulation cascade; and non-Newtonian blood behaviour within the LAA. Using 84 simulation cases generated via Latin Hypercube Sampling of physiological blood parameters and 21 patient-derived LA anatomies, we trained surrogate machine learning models, including Ridge regression, XGBoost, Gaussian Process Emulators (GPEs), and deep learning networks, to predict CFD outputs such as blood viscosity in and fibrin concentrations in the LAA. Deep learning achieved R{superscript 2} values up to 0.90, with the accuracy increasing when both physiological parameters and the raw CT image were included. Other models showed uneven performance with R2 values below 0.7, highlighting the role of nonlinearities between parameters. The study presents a novel CFD model that captures the transition from blood stasis to clot formation, representing the full thrombotic continuum underlying stroke risk in AF, and a deep learning approach to enable efficient prediction of mechanistic outputs of clinical value for stroke risk stratification in AF patients. Author SummaryAtrial fibrillation is a common heart rhythm disorder that greatly increases the risk of stroke. In many patients, blood can pool inside a small pouch of the heart called the left atrial appendage, where clots may form and later travel to the brain. Current clinical tools used to estimate stroke risk mainly rely on a patients medical history and do not directly assess the mechanistic processes that lead to clot formation. In this study, we developed a computer model that simulates how blood flows and clots inside the heart using patient-specific heart anatomies derived from medical imaging. Our model combines blood flow, blood biochemistry, and the changing physical properties of blood during clot formation. We then used machine learning methods to predict these complex simulation results more efficiently. Deep learning models performed best, particularly when both clinical parameters and heart imaging data were included. Our work provides a new way to study the full process linking abnormal blood flow to clot formation in atrial fibrillation. In the future, this approach could support more personalised and mechanistic assessment of stroke risk and help guide treatment decisions.

Early identification of patients with advanced chronic conditions (MACA) remains a critical challenge in clinical practice, often relying on retrospective criteria or clinical judgment, which may delay timely and personalized intervention. The increasing availability of electronic health records (EHR) enables the application of Machine Learning (ML) techniques to support more proactive detection. This study aimed to develop and internally validate a ML-based approach for the identification of MACA patients using collected data from Hospital Universitario Parc Tauli (Sabadell, Spain). A retrospective observational study was conducted using a sample of 163 patients. A total of 80 candidate variables were extracted, including clinical, functional, and healthcare utilization indicators. Feature selection methods were applied, reducing the dataset to ten key predictors. Fourteen supervised classification algorithms were evaluated, including linear, probabilistic, and ensemble methods. Model performance was evaluated using various metrics like accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). The final cohorts include 80 MACA patients and 83 controls. The bagging classifier achieved the most consistent performance with a sensitivity of 0.91 and an AUC of 0.90. Key predictors include absolute dependency, advanced frailty, functional decline, and healthcare utilization indicators. Cross-validation (CV) confirmed the stability of model performance, with mean AUC values exceeding 0.95. These findings highlight the potential of ML-based tools for early detection and the high discriminative capacity for identifying MACA patients.

Background: Cardiac resynchronization therapy (CRT) fails in 30% of patients, often due to suboptimal left ventricular pacing site (LVPS) selection. Current practice lacks tools for pre-procedural, patient-specific LVPS optimization within the accessible coronary sinus (CS) tributaries. This study aimed to develop a digital twin and an explainable ML-based clinical decision support framework to address this issue. Methods: Personalized 3D cardiac models incorporating ventricular anatomy, myocardial fibrosis, and CS anatomy were constructed from CT and LGE-MRI for 74 CRT candidates. Finite-element Eikonal simulations of biventricular pacing generated patient-specific electrophysiological features at candidate LVPS. A Machine Learning (ML) classifier was trained on a hybrid feature set of pre-procedural clinical variables and model-derived indices, validated by leave-one-out cross-validation. SHAP analysis provided a physiologically interpretable rationale for each prediction. The framework was applied to a pilot cohort of 19 patients with reconstructed 3D CS anatomy to generate a spatial likelihood map of CRT response across all clinically implantable pacing sites within each patient's CS. Results: The ML classifier outperformed the reference Feeny clinical calculator under LOO-CV (accuracy 0.78 vs 0.58; F1-score 0.75 vs 0.43), AUC=0.78, sensitivity=0.80, specificity=0.77. Bootstrap analysis yielded mean AUC=0.85 (95% CI 0.70-0.95). In the pilot CS cohort, the framework identified that 8 of 13 clinical non-responders had no accessible CS site predicted to yield a positive response, supporting redirection towards alternative pacing strategies. In the remaining 5, alternative implantable sites with high predicted response probability were identified. SHAP analysis confirmed that dominant predictors were patient-specific in their relative contributions, supporting individualized over heuristic-based LVPS selection. Conclusion: This pilot study demonstrates the feasibility of a digital twin and explainable ML framework as a pre-procedural clinical decision support tool for CRT planning, stratifying patients and identifying optimal implantable sites with transparent anatomical rationale. Prospective validation and regulatory evaluation are required before clinical deployment.

PurposeFunctional tricuspid regurgitation (FTR) is driven by right ventricular (RV) remodeling, annular dilation, and papillary muscle dislocation. Free wall approximation (FWA) has been proposed to treat FTR by addressing RV dilation, but its effects on tricuspid valve (TV) biomechanics remain unclear. We present a real-time 3D echocardiographic (rt3DE)-based finite element framework to quantify TV biomechanics under FTR, and preliminarily apply it to assess FWA effects. MethodsSubject-specific models were developed from rt3DE data of three dilated porcine hearts in an ex-vivo mock-loop. TV geometries at end-diastole and peak systole (PS) were complemented by parametric chordae tendineae and hyperelastic tissue properties. TV closure was simulated under a standard pressure load and image-based annular motion. After tuning chordae length to replicate the PS ground truth in FTR, FWA was simulated as 30% and 60% approximations along three anatomical directions (anterior-posterior, A-P; anterior-septal, A-S; anterior-septal wall, A-SW). ResultsIn FTR simulations, median geometric errors ranged from 1.16 to 1.26 mm; median stress ranged from 56.4 to 74.7 kPa. FWA simulations predicted regurgitant orifice area (ROA) reductions by 53-99%, albeit overestimating the residual ROA vs. in vitro ground truth when starting from particularly extreme FTR conditions; concomitantly, a median stress reduction by 8-43% vs. FTR conditions was predicted. ConclusionPreliminary data suggest that our rt3DE-based framework can reliably quantify FTR-related TV biomechanics and that post-FWA biomechanics depends on initial FTR conditions. A larger cohort is required to verify the method and obtain statistically significant results.

Computational analysis of physiological and biomedical systems necessitate efficient geometry representations for high fidelity model predictions, including patient or device specificity. Particle-based Lagrangian computational approaches comprise a valuable approach to gain insights from quantitative velocity and pressure data from computational models. Examples include particle dynamics and transport in human vasculature for diseases such as stroke, thrombosis, and embolisms; and modern targeted drug delivery systems in the vascular network and respiratory airways. However, current particle simulation approaches can bear significant computational expense that scales with both number of particles and background fluid mesh resolution. A significant determinant of this computational expense is the contact resolution between particles and anatomically realistic vessel wall. Here, we develop an efficient particle dynamics model that leverages an implicit representation of real anatomical features using a signed distance field to efficiently resolve particle-wall contact. We outline the underlying algorithmic details, followed by a systematic illustration of performance and accuracy using simplified and analytically defined geometries and flow fields. Subsequently, we present a representative simulation of embolic particles along a human vascular segment where we compare our distance field-based approach against classical wall-contact checks based on assessing particle boundary intersection with triangulated surface mesh. Our approach transforms the underlying Lagrangian contact detection operation into an equivalent Eulerian operation, significantly speeding up bulk particle dynamics computations without significantly impacting accuracy or geometric fidelity.

Background: Perioperative hypotension is associated with postoperative organ injury. However, trials of hypotension avoidance have not found meaningful improvements in postoperative cardiovascular, renal, neurological or functional outcomes. One possible explanation is that organ perfusion depends on patients individual autoregulatory ranges. Hence, technology enabling monitoring of the autoregulatory status of vital organs, e.g. the brain, could provide a physiologic basis for personalising of blood pressure targets. However, current established methodologies for monitoring cerebral autoregulation in noncardiac surgery, e.g. the cerebral oximetry index (COx), are limited by performance and usability. The Medtronic Cotrending algorithm has been developed to provide automated, near real-time assessment of cerebral autoregulation. While feasibility was demonstrated in cardiac surgery, its applicability in major noncardiac surgery remains unknown. This study aims to evaluate the technical feasibility and clinical implications of Cotrending-based cerebral autoregulation monitoring in major noncardiac surgery. Objectives: Primary objective: To evaluate the technical feasibility of using the Medtronic Cotrending algorithm to monitor intraoperative cerebral autoregulation in real-time during major noncardiac surgery, drawing comparisons to the COx algorithm. Secondary objectives: to investigate the potential clinical implications of Cotrending-based cerebral autoregulation monitoring. Design: Single-centre, prospective cohort study. Setting: Swiss tertiary care centre Patients: Patients enrolled in AUTOREGULATE-NONCARDIAC who were monitored intraoperatively with the Medtronic INVOS(TM) 5100 near-infrared spectroscopy (NIRS) system. Outcomes: Technical feasibility outcomes include success rate of determination of the lower limit of cerebral autoregulation, intraoperative uptime, time to first estimate of the lower limit of cerebral autoregulation, sensitivity to external factors and to data artefacts; agreement of Cotrending-derived lower limit of cerebral autoregulation with COx-derived lower limit of cerebral autoregulation. Conclusions: N/A Trial registration: Clinicaltrials.gov NCT07630129

Breast cancer is the leading cause of cancer-related deaths among women in the Philippines. Over 65% of these cases are diagnosed when they are advanced (Montemayor, 2023). This highlights the need for improved early screening devices. E-HAPLOS, or Electrical Impedance Human-guided Assessment with Pressure for Lump Observation System, is a low-cost glove with sensors designed to improve early detection of suspicious breast lump through touch. It integrates force-sensitive resistors (FSRs) to measure tissue stiffness and Electrical Impedance Spectroscopy (EIS) to analyze conductivity across different frequencies--properties that are closely linked to breast cancer. The prototype uses an ESP32 microcontroller that transmits real-time pressure and impedance data to the website. Tested on gelatin breast models with simulated lump, the FSRs effectively identified lump locations by recording higher mean force values (45.81 kPa vs. 33.57 kPa). This guided approach allowed the combined FSR-EIS system to reach a diagnostic performance with an Area Under the Curve (AUC) above 0.94, a significant improvement over unguided measurement (AUC {approx} 0.78). A two-way ANOVA confirmed a significant difference in diagnostic performance based on the system modality (p < 0.001). Tukeys Honesty Significant Difference (HSD) test showed that the FSR-EIS system was statistically superior to both the unguided EIS (p < 0.001) and FSR-only system (p = 0.041). Results demonstrate the synergistic effect of the integrated system, enabling accurate differentiation of suspicious lumps from normal tissue. The FSR-EIS system of the E-HAPLOS glove shows a great potential for detection of lumps in simulated breasts as a screening tool.

Purpose: Quantifying aortic morphology is central to surgical planning for thoracic endovascular aortic repair (TEVAR), yet no consensus exists on how best to represent three-dimensional aortic shape for outcome prediction. Two broad strategies have emerged: statistical shape analysis (SSA), which relies on statistical methods and dimensionality reduction to capture the most significant shape modes, and geometrically-informed approaches that extract descriptors grounded in differential geometry. Here, we directly compare these paradigms on a cohort of 290 CTA scans classified by surgical outcome (non-pathological, successful TEVAR, failed TEVAR). Methods: For the geometrically-informed approach, we use a two-dimensional feature space using normalized fluctuation in integrated Gaussian curvature $\widetilde{\delta K}$ and mean aortic radius $R$. For SSA, we construct a point-cloud shape model with dimensionality reduction using Principal Component Analysis (PCA) and evaluate classification performance as a function of the number of retained principal components. Results: SSA's leading principal components encode variations in global aortic size and are statistically redundant with ($R$, $\widetilde{\delta K}$), yet they lack a one-to-one correspondence with interpretable anatomical quantities. Testing on an unseen, independent dataset reveals that the geometrically-informed approach provided better generalizability than SSA. Using Gaussian process classification with 10-fold cross-validation, we find that the geometrically-informed approach achieves a higher weighted $F_1$ score than SSA achieves with up to 20 principal components. While SSA's full-dataset accuracy rises above 90\% with increasing dimensionality, this gain is driven by overfitting rather than genuine discriminative power. Conclusion: These results demonstrate that geometrically-informed descriptors offer a more interpretable, robust, and clinically translatable framework for aortic disease classification than data-driven statistical shape representations.

Consumer wearable devices increasingly use single-lead electrocardiograms (ECGs) for cardiac monitoring, but these signals contain substantially less spatial information than the clinical 12-lead standard. Whether this reduction dispro- portionately affects older adults, who often present with more complex cardiac conditions, remains poorly understood. In this study, we evaluated the impact of lead reduction on AI-ECG diagnostic performance across age groups. A 1D resid- ual neural network was trained on 21,091 PTB-XL ECG recordings spanning five diagnostic superclasses and assessed using 12-, 6-, 2-, and 1-lead configurations. Under the full 12-lead setting, model accuracy declined from 84.5% in patients younger than 40 years to 66.2% in patients aged 75 years or older. Progressive lead reduction further widened this gap. Under the 1-lead configuration, accuracy decreased by 14.1 percentage points in the 75+ group but by only 0.4 percent- age points in the <40 group, representing an approximately 40-fold differential degradation confirmed by three independent statistical tests (all p < 0.0001). Older adults also exhibited greater multi-condition diagnostic complexity, pro- viding a plausible explanation for their increased vulnerability to information loss. External validation on the MIT-BIH Arrhythmia Database confirmed cross- dataset model stability. These findings suggest that age-stratified performance reporting should be a minimum standard in wearable AI-ECG validation and regulatory assessment.

Background and Objective: Indications for right ventricular assist device (RVAD) insertion include right heart failure after implantation of a left ventricular assist device or early graft failure following heart transplantation. This study aimed to investigate how the upstream and downstream circulatory network interacts with the Impella RP(R) device. Methods: A numerical model of the Impella RP(R) was implemented within CARDIOSIM(C) software platform for this study. In the numerical configuration, the RVAD aspirated blood from either the right atrium (RA-PA connection) or the right ventricle (RV-PA connection) and delivered it to the pulmonary artery. Only RA-PA connection is the currently used setting for Impella RP(R) in clinical practice. Based on right ventricular (RV) decompression and total flow, our study may help define the need for a direct RV-unloading Impella RP(R). Results: The simulations showed that activating the RVAD in RA-PA mode, regardless of its rotational speed, the mean pulmonary artery pressure (PAP) percentage change was higher than the unsupported condition when the mean systemic venous pressure (SVP) and the pulmonary artery wedge pressure (PAWP) were both set to 20 mmHg. When RV-PA connection was applied, a similar trend was observed although the PAP percentage changes were about halved compared to the RA-PA connection. Conclusions: The Impella RP(R) has the potential to become a valid option for RV support based on current experimental and simulation data. Although already in use, further evaluation in the clinical setting will likely confirm its potential and lead to a more routinely application for RV support.

AO_SCPLOWBSTRACTC_SCPLOWIn this work, we publish the 3D unsteady Navier-Stokes numerical simulations and meshes of coronary arteries reconstructed from invasive X-ray coronary angiograms acquired during in the Fractional Flow Reserve versus Angiography for Multivessel Evaluation 2 (FAME 2) trial. Out of the 914 clinical images, 779 vessels are successfully reconstructed and meshed. The remaining 135 vessels have been discarded since they exhibited self-intersecting geometry during the reconstruction process. The meshes are hexahedral and all of them have the same number of vertices and identical connectivity; their high quality is demonstrated using standard mesh quality indices. The simulations are performed using the Finite Element Method (FEM) with state-of-the-art coronary boundary conditions applied at the outlet. The motivation behind this effort relies from the scarcity of publicly available numerical haemodynamics data, despite the growing interest in data-driven modeling and machine learning techniques. The database is available at the link: https://doi.org/10.7910/DVN/GPCUNS

Objective: To develop and validate a supervised text-embedded transformer matching model to identify fall injuries in Medicare data, and evaluate the model's performance -- alongside a validated rule-based algorithm-- against "ground truth" from an external reference standard (self-reported fall injuries leading to medical attention). Materials and Methods: Text embeddings of ICD-10-CM and CPT codes in Medicare claims/encounters from participants in the Strategies to Reduce Injuries and Develop Confidence in Elders (STRIDE) trial served as model inputs. Trained on annotated claims/encounters occurring within +/- one month of self-reported fall injuries leading to medical attention, the transformer model generated a continuous 0-1 probability that each claim/encounter was for a fall injury. The model was then applied to all claims/encounters in STRIDE and compared alongside the rule-based algorithm to the external reference standard. Results: The model achieved an area under the curve (AUC) of > 0.96 against annotated claims/encounters in 9 out of 10 holdout folds and 0.85 in the remaining fold. In the full STRIDE dataset, the model achieved a peak AUC of 0.86 (95% CI, 0.84-0.87) against the external reference standard, with results comparable to the rule-based algorithm. Discussion: Relative to rule-based approaches, which typically generate binary outcomes, the continuous event probability generated by the transformer model could support clinical endpoint adjudication, with high-probability predictions treated as events, moderate-probability predictions being adjudicated, and low-probability predictions treated as non-events. Conclusion: A text-embedded transformer model identified fall injuries with comparable accuracy to a rule-based algorithm, demonstrating "proof of concept" for use in endpoint adjudication.

The control of uterine activity during pregnancy is a complex process that involves regulating myometrial excitability across multiple scales. While numerous studies have investigated various regulatory mechanisms and established the contributions of ion channels and gap junctions, how these mechanisms interact to produce observed changes in uterine activity remains poorly understood. Pivotal to these efforts are computational models that effectively capture gestational changes in excitability across scales. In this study, we propose a multiscale computational modeling framework that can reproduce measured activity at the cellular and tissue scales at a given gestational stage. At the cellular level, we identify key ion currents underlying the observed electrophysiological properties based on a literature review of their regulation and a sensitivity analysis of the Tong 2011 uterine smooth muscle cell activation model. The conductances of these ion currents are then fit to reproduce characteristic resting membrane potentials and burst properties using Bayesian optimization. To extend to the tissue level, we employ an anisotropic monodomain model, parameterized by the resistivity of late pregnancy uterine muscle, to investigate electrical propagation in a two-dimensional section of uterine tissue. We then apply the multiscale model to study myometrial activation in late pregnancy and elucidate the contributions of ion channel and gap junction regulation in transitioning the uterus from a quiescent state to labor. Our resulting model successfully reproduces measured electrophysiological properties at the cellular level and characteristic single-spike and burst-propagation patterns at the tissue level across the three late-pregnant time points analyzed (days 16/17, 18/19, and 20/21) in a murine model. Furthermore, our results suggest that the regulation of the conductances of the voltage-dependent potassium current (IK1), L-type calcium current (ICaL), and sodium current (INa) is most important in determining preterm uterine excitability. The framework established here will promote the development of more gestationally relevant models to better understand labor progression and the factors involved in dysfunctional labor.

Motor unit (MU) decomposition using high-density surface electromyography (HD-sEMG) has been widely used to characterize MU behavior in neurophysiology and to build neural-machine interfaces for wearable robots. Recently, many open-source software tools for MU decomposition have been made available on GitHub, which could reduce the effort of researchers in the field. However, the consistency among these open-source tools has never been studied, making researchers hesitate to use them. In this study, we collected 7 open-source software tools on GitHub and applied them to decompose MUs from an open-source HD-sEMG dataset (including 11 isometric contraction trials) to investigate the consistency among these tools. To create a comprehensive MU pool for reference, we combined all unique MUs identified by seven tools, visually inspected and removed bad MUs, and manually edited all remaining MU spike trains. Across 7 tools for 11 trials, the number of identified MUs ranges from 167 to 736. The number of valid MUs after expert inspection ranges from 29 to 210, which is 10% to 72% of the reference pool. The rate of agreement between the raw MUSTs and the manually edited MUSTs ranges from 0.86 to 0.94, and the averaged number of edits per MU to correct misalignments ranges from 14 to 39. The results show inconsistency in the implementation and procedures of each tool, which results in an inconsistent number of identified MUs and valid MUs (29 vs 210). In general, a substantial amount of effort is required to process the raw MUSTs from each tool to conduct further research analysis. This study provided a guideline for using open-source software tools for MU decomposition and indicated that it would be beneficial to develop tools to automatically edit the MUSTs.

Deep learning reads 12 lead electrocardiograms at close to expert level on public benchmarks, yet most reports give one accuracy figure for the whole test set and stop there. We trained three architectures that are standard in this field, a 1D ResNet, a convolutional network with a bidirectional LSTM, and a convolutional network with a bidirectional LSTM followed by a transformer encoder, on the PTB-XL dataset to classify the five diagnostic superclasses, and then looked at how each one performed across sex and age. On the held out fold all three reached a macro AUC near 0.92, in line with the strongest published results on this benchmark, and the simplest model, the 1D ResNet, was marginally the best at 0.9241. The averages hid a steady pattern. Every model scored lower for female patients than for male patients, and every model scored lowest for patients aged 80 and over, where the 1D ResNet fell to 0.8878 and the transformer to 0.8693. Adding complexity did not close either gap and slightly widened the gap by age. Overall accuracy on PTB-XL is close to solved for these model families, but the benefit is not shared evenly, and a single headline number hides the patients a model serves worst. We release the full stratified evaluation to support fairness aware reporting.

Background Continuous health monitoring enables early detection of diseases and improves therapeutic outcomes. Non-intrusive biosignal sensors, such as capacitive ECG (cECG), offer a practical solution for daily monitoring in private environments, such as smart homes and vehicles. However, artifacts reduce signal quality and compromise reliability. Methods Following a registered report protocol (Warnecke JM et al. Plos One. 2021; 16(7):e0254780), we record data of 44 subjects and develop an artifact index for cECG. We use three signal quality indices (SQIs): the correlation of QRS complexes (corSQI), the R-peak detection consistency (bSQI) and the absolute amplitude ratio (aSQI). Our index classifies overlapping 10s segments with a step-width of 2s into clean or artifact segments. We label a 2s interval as artifacts if all five overlapping segments indicate artifacts. We record cECGs using an armchair with integrated electrodes in a single-arm study involving 44 subjects performing two activities -- reading and watching television (TV); for 11 minutes each. We record a time-synchronized reference ECG with skin electrodes on the chest. To evaluate the artifact index, we compare it with manually generated ground truth. Moreover, we evaluate the clothing materials cotton, linen, jeans, and polyester in 5 subjects. Results Watching TV results in longer, continuously clean signal durations than reading. On average, 88.3% of the signal has a minimum continuous clean duration of 10s, versus 79.8% during reading. All clothing configurations achieve a clean signal duration exceeding 10s. Among the SQI metrics, bSQI performs best, achieving an accuracy of 90.7% and an F1 score of 79.9%. Combining the three SQI metrics in a voting approach improves accuracy to 92.0% and F1 score to 82.1%. Discussion Our artifact index automatically distinguishes clean from artifact cECG segments, promoting health monitoring in unsupervised real-world settings, earlier disease detection, and preventive health management. A limitation is the investigation of only two scenarios (reading and watching TV).