Computer Methods and Programs in Biomedicine

ECG waveform data, which is increasingly required for artificial intelligence analyses, is often unavailable in raw data formats. Digitization can approximate original raw data from ECG images, but digitizers reconstruct ECG waveforms only approximately. Exact waveform reconstruction is needed to guarantee that any errors, even if small, do not unexpectedly propagate into downstream analyses. Portable document format (PDF) files containing vector graphics store waveforms derived directly from raw data. This improves reconstruction accuracy, but existing PDF reconstruction methods remain approximate because raw data values are rounded during PDF encoding/generation. Despite rounding, however, there is a 1:1 mapping between raw data and PDF-encoded values which can be reversed to recover the original raw data with no error. We developed open-source software in MATLAB and Python (http://github.com/BIVectors/pdf2ECG) for bit-exact waveform reconstruction of General Electric MUSE ECG PDFs based on double quantization of ECG waveform data. The software supports multiple PDF layouts and voltage gains, automatically flags waveform clipping under which exact reconstruction is not possible, and certifies if parameter values used for waveform reconstruction are consistent with parameter values used during PDF encoding. Accuracy was assessed by comparing PDF reconstructed waveforms to raw XML waveforms, and reconstruction parameters were perturbed to determine the accuracy of waveform certification. 1,632 PDF-XML pairs were assessed in 5 layouts, each at 3 gains. After software-identified waveform clipping was excluded, the software reconstructed 100% of ECG waveforms with zero error compared to ground-truth XML. Certification tests were extremely sensitive to minor perturbation in encoding parameters, and if passed, confirmed bit-exact waveform reconstruction without need for ground-truth comparisons. Although this method does not replace the need for general ECG image digitization, for MUSE generated PDFs this method is preferable to rasterization followed by image-based digitization.

Lines, drains, and airway devices are commonly used in surgical and inpatient care to support treatment and patient monitoring. While these devices are essential, prolonged device retention is associated with complications such as infection, tissue injury, thrombosis, and extended hospital stay. Understanding how long devices remain in place and how duration varies across device types is important for improving patient safety and guiding device management practices. This study analyzes device duration patterns using Patient Lines, Drains, and Airways (LDA) data containing information on device type, placement time, and removal time across multiple patient encounters. Exploratory data analysis and machine learning approaches are used to examine duration distributions, distinguish short and prolonged device retention, and identify structural patterns across device categories. The findings indicate notable variation in device duration patterns across categories, with identifiable differences in device retention behavior across device groups. This study highlights the value of observational electronic health record data for characterizing device exposure patterns and provides a foundation for future data-driven device management and risk assessment.

Predictive biomechanical models of the tricuspid valve require accurate representation of the chordae tendineae, yet subject-specific chordal geometry is difficult to reconstruct from non-invasive imaging. Here, we adopt a framework for generating functionally equivalent synthetic chordae without prior knowledge of in vivo chordal attachments. To this end, we first adapt an anatomy-informed hyperelastic shape-matching method that establishes correspondence between end-diastolic and end-systolic leaflet configurations using chordal-mimicking forces, a rigid contact template, and a Gaussian-smoothed locally corrective pressure field. We then generate synthetic chordal insertion sites using zone-based rejection sampling and calibrate the unloaded length of each chord by combining reaction forces with the chordal stress-stretch relationship. The framework was evaluated using Texas TriValve 1.1, a high-fidelity finite element model of a human tricuspid valve validated against beating-heart echocardiography. We found that shape matching reproduced the target end-systolic geometry with a mean inter-surface distance of 0.29 {+/-} 0.35 mm. Moreover, synthetic chordal insertions faithfully reproduce end-systolic leaflet deformations. We subsequently examined synthetic chordal configurations containing 202, 225, and 450 insertions, informed by measurements from eight explanted human tricuspid valves. Here, increasing insertion number reduced mean inter-surface distance from 0.63 {+/-} 0.52 mm to 0.49 {+/-} 0.44 mm and reduced contact area errors from 3.52% to 0.59%. Across all configurations, mean maximum principal stretch errors in leaflet belly regions remained below 2.4%, while areal strain errors ranged from 0.34% to 10.01%. These results demonstrate that anatomically informed shape matching coupled with stress-based chordal calibration can reproduce tricuspid valve closure without explicit subject-specific chordal geometry. This framework provides a foundation for generating synthetic subvalvular anatomy for future imaging-derived, predictive tricuspid valve models.

Vector flow mapping (VFM) reconstructs left-ventricular (LV) blood velocity from color-Doppler echocardiography by combining the measured beamwise component with physical and regularizing constraints. Analysis of the discrete VFM formulation shows that the inverse problem is intrinsically ill posed: the occurrence of singular modes can be predicted from the geometry of the segmented blood-pool domain, the imposed boundary conditions, and the degree of smoothing. These modes can propagate uncertainty along entire transverse bands of the reconstructed velocity field, yet conventional VFM neither quantifies this uncertainty nor allows for correcting the blood-pool segmentation. We introduce Bayesian VFM (B--VFM), a hierarchical framework that jointly infers radial and transverse velocities, a probabilistic blood-pool mask, their spatially resolved uncertainties, and hyperparameters weighting Doppler and segmentation fidelity, mass conservation, boundary conditions, and smoothness. The discretized posterior admits a closed-form gradient and exact Hessian, enabling computationally efficient, gradient-based MAP estimation, sampling, and direct analysis of ill-posed modes. Posterior inference combines Gibbs sampling of conjugate Gamma-distributed hyperparameters with conditional maximum-a-posteriori estimation and a Laplace approximation for the high-dimensional velocity and mask fields. To accommodate systematic departures from planar mass conservation, B-VFM can learn the covariance of the planar divergence residual from an ensemble of flows and incorporate it as a structured model-discrepancy prior. Independent chains converged reproducibly, while covariance priors learned from flow ensembles illustrated how model discrepancies can be incorporated into the inference. B--VFM was evaluated using Lamb-Chaplygin dipoles under ideal conditions and with Doppler corruption, Doppler voids, and segmentation defects, and using the Hicks-Moffatt family of spherical vortices to assess violations of planar mass conservation. The method produced smooth reconstructions, localized uncertainty near unreliable measurements and regions of model inconsistency, and used flow information to correct segmentation errors. Within the tested vortex family, the data-informed planar divergence prior reduced velocity bias and mask distortion. B--VFM thus provides an uncertainty-aware reconstruction method and a flexible foundation for future VFM formulations incorporating additional priors, observations, and physical models. Future work will evaluate the method using clinical data and more complex three-dimensional benchmark flows.

Optical mapping is a fundamental tool for cardiac electrophysiology research. Processing of these signals can be non-trivial, requiring multiple pre- and post-processing steps to limit interpretation errors. Existing software packages have features siloed across platforms and require users to combine several packages for in-depth analysis. To address this, we developed CADENCE, an open-source MATLAB-based application combining feature breadth (e.g., SVD denoising, conduction velocity, alternans, annotated rotors) and depth (e.g., 15 independent alternans features across both voltage and calcium modalities) in an end-to-end pipeline including data conversion, signal conditioning, feature extraction, and signal analysis. We demonstrate CADENCE's capabilities across datasets spanning four species (rat, rabbit, pig, and human), three tissue preparations (slices, wedge, and whole heart), and three camera configurations (single, dual, and panoramic). CADENCE was validated against three blinded expert observers (15 hearts) and demonstrated agreement comparable to inter-observer variability (SD ratios 1.07/0.95/0.89 for APD80, activation, CaTD80). Dominant frequency was recovered with a median error of 0.03% across 84 of 88 paced recordings with 1:1 capture. CADENCE's code is publicly available and distributed as a compiled standalone application that the end-user can install and run without a MATLAB license to encourage adoption and standardization across laboratories.

Background: Rheumatic mitral stenosis (RMS) disproportionately affects low-resource settings where echocardiography is limited. We evaluated foundation model (FM) feasibility for RMS detection using limited, indirectly labeled ECGs. Methods: An ECG-FM was fine-tuned using 804 RMS-positive ECGs per fold and externally validated across clinical and wearable lead configurations. Results: Internal AUROCs were 0.89, 0.87, and 0.87, for 12-Lead, 6-Lead, and 1-Lead respectively. External AUROCs were 0.82, 0.80, and 0.77. Performance remained comparable across demographic subgroups. Conclusions: FM fine-tuning enables RMS detection using limited ICD-derived labels, supporting further evaluation of reduced-lead ECG screening and echocardiography triage in resource-constrained settings.

Background: Identification of in-hospital cardiac arrest (IHCA) through manual chart abstraction is the gold standard, but its time-consuming and resource-intensive, which naturally limits its practicality. Diagnostic codes provide an accessible automated alternative, but prior work has shown this method of extraction has poor sensitivity and poor positive predictive value. More accurate and scalable automated methods are needed to support IHCA surveillance and research. Methods: We developed large language model (LLM)-based systems that incorporated physician-defined clinical knowledge through guideline-enriched prompting, supervised fine-tuning, and a self-correction procedure. The systems identified IHCA events and their locations from electronic health record notes. Performance was evaluated at the encounter level against physician-adjudicated chart review and compared with ICD-code-based identification. Results: Compared with an ICD-code-based algorithm (precision 0.68, recall 0.91, F1 score 0.78), the supervised fine-tuned LLM offered substantially better performance for IHCA identification on a curated evaluation corpus, reaching a precision of 0.88, a recall of 1.00, and an F1 score of 0.94. When tested on a larger, unselected validation cohort of 45,525 encounters, a separate LLM configuration - relying on guideline-enriched prompting and a self-correction procedure rather than fine-tuning - achieved a precision of 0.79 for encounter-level IHCA identification, meaning most encounters flagged by the model were genuine IHCA cases. The fine-tuned LLM underperformed on this cohort due to its inability to self-correct its decisions, an issue that can be mitigated by having a separate model perform the correction step. Conclusion: Explicit integration of clinical knowledge through prompting and supervised fine-tuning enabled accurate identification of IHCA events and locations from routine clinical documentation. In a two-pass workflow, these systems could prioritize encounters for clinician adjudication, reduce manual screening requirements, and support more scalable IHCA surveillance and registry development.

Explicit timing and context features may complement short electrocardiogram waveforms, but aggregate gains on imbalanced benchmarks can conceal errors in individual classes. We therefore compared Logistic Regression, Random Forest, XGBoost, and a one-dimensional convolutional neural network (CNN) in four cumulative input stages. Stage S1 used a 255-sample beat waveform alone, and stages S2 to S4 added 6, 13, and 21 engineered features. Using the inter-patient division of the MIT-BIH Arrhythmia Database, with 50,992 development and 49,686 evaluation beats in four classes, we estimated 95% intervals with a paired bootstrap over the 22 evaluation recordings. Adding six RR interval features increased macro F1 by 0.025 to 0.093, with intervals excluding zero for every model family. Further context helped Random Forest and XGBoost, whereas later CNN gains fell within resampling uncertainty. At the final stage, XGBoost and CNN reached macro F1 of 0.580 and 0.574, and the interval for their difference included zero. Despite opposite operating points, their precision for fusion beats was similar at matched recall, suggesting that neither separated fusion beats better. The most accurate pipeline, Random Forest at S2 with 94.45% accuracy, detected only 1.4% of supraventricular beats, and development and evaluation favored the same stage for only one family. The results for the minority classes were based on single recordings. Record 213 supplied 203 of the 207 correct CNN fusion detections, and elsewhere both final models detected at most 4 of 26 fusion beats. Record 232 contains 75% of the evaluation supraventricular beats, and nearly all were missed. Excluding this record nearly doubled XGBoost supraventricular F1, from 0.199 to 0.383. These findings are limited to retrospective analysis with annotated beat positions and a single training seed.

BACKGROUND: While the systemic right and left ventricles have different functional prognoses, only a limited number of reports have addressed their myocardial architecture. This study analyzed myofiber orientation of human specimens with various congenital heart diseases using X-ray phase-contrast tomography. METHODS: Three specimens of each normal heart, ventricular septal defect, right atrial isomerism, left atrial isomerism, and ventricular inversion were examined. In reconstructed images of both ventricles, the center of the free wall was resliced parallel to the myocardial surface. A myofiber helical angle was identified in each slice and plotted from epicardium to endocardium. The plotted curves were compared between both ventricles. RESULTS: In all ventricles, the helical angle was changed from left-handed on epicardial slices to right-handed on endocardial slices. Whereas the right ventricle?s helical angle curves showed a plateau with or without a rapid rise on the endocardial side, the left ventricle?s curves had sustained increase with or without a plateau in the middle. The median wall-thickness?scaled helical angle change rates were 53{degrees} and 102{degrees} in the right and left ventricle, respectively, and their distribution of each specimen was higher in the left ventricle than in the right ventricle. CONCLUSIONS: Ventricular myofiber orientation has a consistent transmural helical transition independently of cardiac morphology and looping. Their transitions can have a plateau and rapid changes permitting the identification of layers within the ventricular wall. The left ventricle has more helical fibers and the right ventricle has more circumferential fibers, which may explain their difference of ventricular performance.

Introduction: The femoropopliteal artery undergoes substantial axial compression, bending, torsion, and pinching during limb flexion. When an implanted stent does not accommodate these deformations, repetitive biomechanical mismatch may alter the vascular response to implantation and contribute to restenosis. We tested whether designing a peripheral stent to better accommodate physiologic limb-flexion deformation reduces the subsequent inflammatory and neointimal response. Methods: A nitinol stent was developed using multi-objective computational optimization to maintain arterial apposition while reducing wall stress and luminal pinching during physiologic deformation. Sixteen Yucatan minipigs were studied in independent 3- and 6-month cohorts (n=8 each). Each animal received the optimized stent in one limb and a commercial stent with representative biomechanical behavior contralaterally. CTA quantified in vivo limb-flexion deformation, while CT and histology assessed stenosis, neointimal accumulation, inflammatory-cell burden, SMA-positive tissue, and extracellular-matrix composition. Results: The optimized stent accommodated greater axial shortening than the commercial comparator at both 3 months (11.2{+/-}2.7% vs. 6.6{+/-}2.1%, p=0.003) and 6 months (13.7{+/-}4.4% vs. 6.8{+/-}2.3%, p=0.004). Intimal hyperplasia volume was lower with the optimized stent at 3 months (227.5{+/-}85.2 vs. 350.0{+/-}130.5 mm3, p=0.002) and 6 months (183.6{+/-}46.2 vs. 261.2{+/-}60.6 mm3, p=0.001), with significantly lower maximum, mean, and median stenosis at both timepoints. At 3 months, macrophage and total inflammatory-cell counts were 51% and 45% lower, respectively, with the optimized stent. Histologic tissue area was 28% lower at 3 months and 12% lower at 6 months. SMA-positive tissue fraction was higher with the optimized stent at both timepoints, whereas elastin, glycosaminoglycan, and collagen fractions were similar between devices. Discussion: Improved accommodation of limb-flexion deformation was associated with a smaller inflammatory and neointimal response to stent implantation through 6 months, while overall neointimal matrix composition remained largely unchanged. These findings provide in vivo evidence that biomechanical compatibility with the dynamic lower-limb environment can influence vascular healing and should be considered a mechanistic design criterion for peripheral artery stents.

Patients with implantable cardioverter-defibrillators (ICDs) often are excluded from receiving CMR scans at 3.0T due to ICD-induced image artifacts. This work aims to transfer sequence protocols established for CMR imaging in the presence of ICDs at 1.5T to a first human application at 3.0T. All measurements were performed on a clinical 3T MRI scanner. Phantom measurements were used to establish and optimize wideband PSIR LGE imaging at 3.0T. Volunteer measurements with externally placed ICDs were used for optimization of CINE imaging and wideband PSIR imaging. Thirdly, patients with implanted ICD were examined with the optimized protocols. Human measurements showed that SA stacks obtained with spoiled GRE after contrast agent showed a markedly lower artifact burden than the conventional approach. For scar imaging, a wideband PSIR with a bandwidth of 3kHz and a frequency offset of +750Hz allowed a sufficient suppression of relevant artifacts in the majority of scans. No strong correlation between the image quality and the distance between the cardiac silhouette and the device was detected. The presented work shows the feasibility of clinical cardiac MRI at 3.0T including GRE-CINE and wideband PSIR-LGE for patients with ICDs.

Background: Hypertension is a major risk factor for type B aortic dissections and rupture, with guidelines recommending systolic blood pressure (SBP) control below 130 mmHg to improve outcomes. While post-TEVAR blood pressure is often managed with a focus on mean SBP, little is known about temporal hemodynamic patterns and their association with surgical success. This study investigates blood pressure and heart rate (HR) time-series metrics within 24 hours post-TEVAR and their predictive potential for outcomes. Methods: Blood pressure (n = 560) and HR (n = 680) time-series data from 31 patients were analyzed alongside preoperative aortic geometry metrics. Exploratory data analysis identified correlations between BP variability and outcomes. Stationarity tests were performed on time-series data to assess statistical properties. Logistic regression models incorporating hemodynamic metrics, along with CT-derived features, were used to predict TEVAR outcomes. Results: Successful outcomes correlated with greater diastolic blood pressure variability and strictly stationary SBP. Logistic regression models combining these metrics along with heart rate standard deviation and preoperative aortic geometry achieved 96.67% 5-fold cross-validation accuracy in predicting outcomes. Conclusion: Post-TEVAR behaviors of hemodynamic variables are critical predictors of TEVAR success, with higher DBP standard deviation and strict stationarity of SBP significantly associated with favorable outcomes. These findings highlight the importance of hemodynamic variability and stationarity in optimizing post-TEVAR patient care.

Purpose: Atrial fibrosis is associated with thromboembolic risk in atrial fibrillation, but how fibrosis-related contractile impairment alters blood transport in the left atrium (LA) and left atrial appendage (LAA) remains unclear. Prior multi-physics simulations coupled electromechanical (EM) and computational fluid dynamics (CFD) models to show that fibrosis impairs LA function and flow, but were limited to booster-only contraction and could not separate the effects of fibrosis burden from its spatial distribution. Here we examined how fibrosis burden and spatial pattern independently relate to long-term LA and LAA hemodynamics in full-cycle, multi-beat simulations on a common LA anatomy. Methods: Three fibrosis patterns derived from late gadolinium enhancement MRI were considered: one from the patient providing the common anatomy and two from additional patients, with the latter mapped onto the common anatomy via universal atrial coordinates. All three patterns were applied globally at matched burdens of 15.6% and 31.2%, yielding six global-fibrosis cases and a non-fibrotic reference. Two patterns were also confined to the LAA at three local burdens (10%, 25%, and 50%), yielding six LAA-fibrosis cases. A 3D EM model for the LA anatomy was coupled to a 0D circulatory model, so that the simulations resolved the reservoir, conduit, and booster phases. Full-cycle EM-derived wall motion drove subsequent multi-beat CFD simulations. Region-specific emptying fraction (EF), non-dimensional kinetic energy (KE), and the 90th percentile of blood residence time (TR) were evaluated for the LA and LAA. Results: Left ventricular stroke volume remained nearly constant across cases, while increasing global fibrosis burden progressively reduced LA and LAA EF (LA: 36% to 30-31%; LAA: 44% to 28-38%) and monotonically increased LA TR across all patterns. Non-dimensional LA KE showed an approximately quadratic association with LA EF across patterns, whereas LAA KE was more scattered but still increased with LAA EF. In contrast, the relationship between the 90th percentile of LAA TR and LAA EF showed pattern-specific, non-monotonic trends. Conclusions: Fibrosis burden and spatial distribution jointly shape LA and LAA hemodynamics, but through different mechanisms. LAA EF is a robust functional descriptor of chamber-averaged kinetic energy regardless of fibrosis pattern, whereas LAA blood stasis depends additionally on the spatial distribution of fibrosis beyond what bulk emptying fraction predicts. These findings support incorporating imaging-derived fibrosis pattern, and not only burden, alongside functional metrics when assessing thrombogenic risk in the LAA.

Accurate prediction of adverse events in the intensive care unit (ICU) following cardiothoracic surgery is crucial for timely interventions, improving patient outcomes and optimizing value in healthcare. By leveraging advanced machine learning techniques, this study demonstrates the transformative potential of predictive analytics to enhance postoperative care using a dataset from the Society of Thoracic Surgeons' (STS) database and time-series intraoperative data. We developed a multi-modal late fusion approach integrating static patient variables with intraoperative time-series data, utilizing an ensemble of models including residual neural networks for static features, CNN and Bidirectional GRU for time-series processing, XGBoost, logistic regression, SVM and Gradient Boosting. Through five-fold cross-validation, our ensemble model with balanced threshold selection achieved an AUC of 0.87, sensitivity of 0.76, specificity of 0.83, PPV of 0.40, and NPV of 0.96. Preoperative heart failure, IABP insertion, cardiopulmonary bypass (CPB) duration and white blood cell (WBC) count emerged as key predictors. Training the same pipeline on each modality separately showed that the static registry variables alone reached the same AUC of 0.87, and that the intraoperative signals alone reached 0.83, so on this cohort the two modalities act as substitutes rather than complements and fusion changed the sensitivity and precision trade-off rather than the amount of separable signal. A per-signal ablation found that no individual monitoring channel was load bearing, with mean arterial pressure and central venous pressure the least substitutable. This balanced approach optimizes the trade-off between sensitivity and specificity, providing a screening tool with high negative predictive value for monitoring high-risk patients, and the modality comparison indicates that comparable performance is attainable at sites holding registry data alone.

INTRODUCTION Large language models (LLMs) have demonstrated substantial performance on medical licensing and board examinations, but their application to anesthesiology remains less well studied. Prior evaluations have not compared current-generation models from different developers or assessed performance on figure-dependent questions that earlier models lacked the capability to interpret. This study evaluates the performance of two current-generation LLMs on a comprehensive anesthesiology in-training examination (ITE) review question bank, including figure-dependent items. METHODS A total of 1,001 single-best-answer questions from an anesthesiology ITE review text, spanning 11 content chapters, were administered to Claude Opus 5 and GPT-5.6. No questions were excluded. Each item was presented once in a fresh, stateless context with no tool access, retrieval, answer key, or explanation provided in the prompt. Performance was analyzed by question format, and all 27 figure-dependent items were administered with their published figures supplied. Accuracy between models was compared using McNemar's test. RESULTS Claude Opus 5 answered 947/1,001 items correctly (94.6%; 95% CI, 93.0-95.8), and GPT-5.6 answered 946/1,001 correctly (94.5%; 95% CI, 92.9-95.8); the difference was not significant (McNemar p=1.00). Accuracy was similar across most question formats. On standard questions, accuracy was 94.3% and 94.6% for Claude Opus 5 and GPT-5.6, respectively; on the 18 figure-based questions with figures supplied, accuracy was 94.4% and 83.3%, respectively; and both models achieved 100% accuracy on image-option items. Withholding figures from the same 18 figure-based questions reduced pooled accuracy from 88.9% to 52.8% (exact McNemar p=0.03 and p=0.04 for Claude Opus 5 and GPT-5.6, respectively). The models agreed on 957/1,001 items (95.6%). Of the 33 items both models answered incorrectly, they selected the same incorrect option on 32 (97%). DISCUSSION Current-generation LLMs achieved approximately 95% accuracy, substantially improving on our prior results with earlier-generation models and placing both models within the highest band of the ITE normative framework, corresponding approximately to the 99th percentile across training levels. By comparison, our prior work with previous models placed ChatGPT-3.5 at the 52nd, 3rd, and 1st percentiles and ChatGPT-4.0 at the 99th, 95th, and 84th percentiles across increasing levels of training. Multimodal capability now permits successful interpretation of many figure-dependent questions, although performance declines markedly when required visual information is unavailable, and highly concordant errors remain. These findings support an increasingly promising role for LLMs as accessible, on-demand educational adjuncts for anesthesiology trainees, provided complete source material is supplied and outputs are critically reviewed.

The Muse 2 EEG headset also records forehead photoplethysmography (PPG). We tested whether its pulse intervals can replace Polar H10 RR intervals for ultra-short heart-rate variability in 28 seated recordings (60 s eyes open, then 60 s eyes closed), using fixed processing, no exclusions and eleven sensitivity analyses. Mean heart rate agreed almost perfectly (ICC [≥] 0.999; bias -0.22 and 0.00 beats min-1). SDNN agreement was good to excellent (ICC 0.86 and 0.91; bias +8.6 and +8.2 ms). RMSSD agreement was moderate (ICC 0.60): Muse exceeded Polar in at least 27 of 28 sessions (bias +19.2 and +18.5 ms; about 1.9-fold), and the ratio bias fell as RMSSD rose. Interval differences (SD 23 ms) implied about 16 ms of independent timing error per pulse, which reproduced the RMSSD bias; without ECG, sensor jitter could not be separated from variation in pulse transit time. Tracking of the eyes-closed change in ln RMSSD was not demonstrated ({rho} = 0.35, 95% CI -0.07 to 0.67; detectable {rho} [≥] 0.51). Muse 2 PPG can supply mean heart rate and, with a stated bias, SDNN; its ultra-short RMSSD is not interchangeable with Polar RMSSD and should be reported as pulse-rate variability.

Background: Pacing-induced cardiomyopathy (PICM) is a major complication of chronic right ventricular pacing and develops in up to 25% of patients. Reliable prediction of PICM may facilitate individualized pacing strategy selection; however, currently available approaches demonstrate limited discriminative performance. This study aimed to develop and validate machine learning (ML) models for predicting PICM in patients with atrioventricular block (AVB) underlying heart failure with mildly reduced or preserved ejection fraction. Methods: In this multicenter prospective study derived from the RISK-PICM registry (January 2002 to January 2026), 125 patients with AVB who underwent pacemaker implantation were analyzed. PICM was defined as a ?10% reduction in left ventricular ejection fraction (LVEF) resulting in an LVEF <50%. Four ML algorithms, including logistic regression, support vector machine, random forest, and XGBoost, were trained using stratified 4-fold cross-validation with hyperparameter optimization and model discrimination was evaluated. Results: PICM developed in 41 patients (32.8%) during a median follow-up of 4.8 years. Male sex, pre-implant minimum QTc interval, and post-implant maximum QRS duration were significantly associated with PICM in univariable Cox regression. XGBoost achieved the highest discriminative performance (AUROC 0.831; sensitivity 0.805; specificity 0.845). Feature importance analysis identified baseline LVEF and post-implant maximum QRS duration as the most influential features. Model-derived risk stratification significantly differentiated high-risk and low-risk groups on Kaplan-Meier analysis (P < 0.001). Conclusions: ML-based models, particularly XGBoost, demonstrated clinically meaningful performance for PICM and may support individualized pacing strategy selection in patients with AVB and underlying heart failure with mildly reduced or preserved ejection fraction.

Aims: Myocardial strain enables sensitive assessment of cardiac function, but its clinical application has largely focused on individual chambers or selected patient populations. We evaluated the feasibility and clinical relevance of fully automated multi-chamber strain assessment in consecutive patients undergoing routine transthoracic echocardiography (TTE). Methods and results: This retrospective study included 8,350 consecutive adults undergoing TTE. A hospital-wide artificial intelligence (AI)-based system automatically measured left ventricular (LV) global longitudinal strain (LVGLS), left atrial (LA) reservoir strain (LASr), and right ventricular (RV) free-wall strain (RVFWS). AI-derived LVGLS was available from at least one apical view in 97.1% of patients and from all three views in 94.8%; LASr and RVFWS were available in 94.1% and 94.5%, respectively, resulting in complete multi-chamber strain assessment in 90.3%. Strain measures showed modest correlations with conventional chamber-specific echocardiographic parameters and differential associations with clinical outcomes. Gaussian mixture modeling identified three distinct clusters characterized by preserved multi-chamber function, RV-dominant dysfunction, and pan-chamber dysfunction. Compared with the preserved cluster, pan-chamber dysfunction was associated with the highest risk of all-cause death or heart failure hospitalization (adjusted hazard ratio, 3.44; 95% CI, 2.43-4.88; P<0.001). Prognostic associations remained evident in patients with LV ejection fraction (LVEF) [&ge;]50%, and cluster assignment provided incremental prognostic information beyond clinical factors, LVEF, and RV fractional area change. Conclusions: Fully automated multi-chamber strain assessment was feasible in a large consecutive TTE cohort. Integrating strain across cardiac chambers may provide complementary functional characterization and identify clinically relevant clusters with prognostic information beyond conventional assessment.

Abstract Background Advanced in vitro models of the human heart have become promising tools for studying cardiac diseases and drug discovery. Three-dimensional (3D) engineered heart tissues (EHTs) provide more adult cardiac tissue-like structural organization compared to traditional two-dimensional (2D) in vitro models with straightforward contractile readouts. However, the assessment of the architecture of EHTs, especially the quantification of cellular and tissue structural components, has remained poorly studied. Here we demonstrate the use of light-sheet microscopy for structural imaging of intact EHTs and provide quantification of the EHT cellular and subcellular structures. Methods We developed an in-house inverted selective plane illumination microscopy (iSPIM) platform and combined it with iterative indirect immunofluorescence (IT-IF) staining for better signal acquisition. We developed an image-processing and analysis pipeline dedicated to volumetric EHT analysis. Results With this integrated platform, we achieved volumetric imaging of intact EHTs and quantification of 3D tissue architecture, revealing aligned cardiomyocytes within the imaged volume and increasing cardiac nuclei content towards the core of the tissue. The developed methods allowed the detection of heterogeneities between tissue sections, demonstrating the sensitivity required for future disease modeling or maturation studies. Conclusions The developed integrated platform opens new possibilities for volumetric analysis and characterization of 3D tissue structure using iSPIM, providing new insights into EHT architecture and the use of EHTs as disease modeling tools.

Large epidemiologic studies have historical electrocardiogram (ECG) collections limited to paper tracings or scanned images rather than native digital files, limiting ECG-AI applications. We compared 15 ECGs available as native digital XML files and as PDF tracings digitized using ECGScan software. Both versions were processed using an ensemble of five convolutional neural networks predicting 10-year heart failure risk. Predictions were strongly correlated (Pearson r=0.804; Spearman {rho}=0.893). Predicted probabilities were [mean (SD)] 0.195 (0.048) for native digital ECGs and 0.171 (0.042) for digitized ECGs. These preliminary findings support further evaluation of digitized ECGs for ECG-AI applications.