Computers in Biology and Medicine

Drug-induced liver injury (DILI) is an acute inflammatory liver disease caused not only by prescription and over-the-counter medications but also by health foods and dietary supplements. Typically, DILI patients recover once the causative substance is identified and discontinued. In contrast, autoimmune hepatitis (AIH) results from the immune-mediated destruction of hepatocytes due to a breakdown of self-tolerance mechanisms. Patients presenting with acute-onset AIH often lack characteristic clinical features, such as autoantibodies, and require prompt steroid treatment to prevent progression to liver failure. Liver biopsy currently remains the gold standard to differentiate acute DILI from AIH; however, general pathologists face significant diagnostic challenges due to overlapping histopathological features. This study integrates pathology expertise with deep learning-based artificial intelligence (AI) to differentiate DILI from AIH using histopathological images. Our AI model demonstrates promising classification accuracy (Accuracy 74%, AUC 0.81). This paper presents a detailed pathological analysis alongside AI methods, discusses the current model performance and limitations, and proposes directions for future improvements.

Small airways are the primary sites of airflow obstruction in chronic obstructive pulmonary disease. Effective delivery of aerosolized drug particles to these regions is crucial to maximize treatment efficacy while minimizing side effects. However, conventional inhalation therapy approaches (i.e., full-mouth particle release and inhalation (FMD)) typically result in insufficient drug deposition in the small airways and an uneven distribution across the five lung lobes. To address such deficiencies, the goals of this study are triple folds: (1) to develop a fast and accurate framework to secure target drug delivery (TDD) nozzle diameter and location based on the conventional computational fluid particle dynamics (CFPD)-FMD simulations, (2) to develop a CFPD-informed machine learning (ML) inverse-design framework that predicts optimal inhaler nozzle parameters based on patient-specific breathing patterns and drug properties, and (3) to demonstrate the feasibility of embedding this framework into a user-centered smart inhaler prototype to improve uniform TTD to the small airways across all five lung lobes. Specifically, a subject-specific mouth-to-generation-10 human respiratory system was employed, and 108 high-fidelity CFPD-FMD simulations were performed under varied physiological and design parameters, including tidal volume, particle diameter, release location, and release timing. Particle release maps generated from those CFPD-FMD simulations via backtracking identified optimal nozzle diameters and locations that promote uniform multi-lobe drug delivery while limiting off-target deposition. Accordingly, a dataset was compiled with inputs (i.e., flow rate, particle size, release z-coordinate, release time) and targets (i.e., nozzle center x- and y-coordinates, nozzle diameter). These inputs and targets form the CFPD-TDD dataset, on which 16 ML models were trained to learn inverse mapping from patient- and drug-specific inputs to optimal nozzle design parameters. Performance was evaluated using mean squared error (MSE) and mean absolute error (MAE) overall and per target feature. Parametric analysis using CFPD-FMD simulations was conducted to determine how patient-specific and drug-specific factors affect pulmonary air-particle transport dynamics and to explain why achieving CFPD-TDD in small airways with CFPD-FMD strategies remains challenging. Furthermore, the ML evaluation in this feasibility study demonstrated robust learning of the inverse mapping from patient-specific inputs to optimal nozzle parameters. Four top-performing models showed consistently low MSE/MAE across cases, and an ensemble (i.e., mixed model (MixModel)) combining their strengths was formulated. Independent CFPD-TDD simulations beyond the training and testing datasets were used as the ground truth to validate ML-predicted nozzle configurations. Compared with conventional CFPD-FMD strategies, ML-guided nozzle designs significantly improved inter-lobar deposition uniformity and reduced off-target deposition in the upper airways, demonstrating the feasibility of ML-enabled TDD to the small airways. Overall, this study establishes a CFPD-informed ML inverse-design framework as a viable algorithmic foundation for user-centered smart inhalers, enabling adaptive, patient-specific TDD to the small airways with improved deposition uniformity across all five lung lobes. By integrating first-principle-based CFPD with ML, this work provides a methodological pathway toward next-generation smart inhalers for more effective treatment of small airway diseases.

Non-alcoholic fatty liver disease (NAFLD) is a globally prevalent hepatic condition caused by the buildup of fat in the liver. It is frequently associated with metabolic comorbidities such as hypertension, cardiovascular disease (CVD), and prediabetes. However, early detection remains challenging due to the asymptomatic progression, and existing primary diagnostic methods, such as imaging or liver biopsy, are often expensive and inaccessible in rural areas. This study proposes a two-stage, interpretable machine learning pipeline for the non-invasive and cost-effective prediction of NAFLD and its key comorbidities using routine clinical parameters. The NAFLD prediction model was developed using the XGBoost algorithm, trained on a hybrid dataset that combines real patient data with rule-based synthetic data generated by simulating clinically plausible cases. Upon NAFLD-positive prediction, three separate XGB models, trained on data labelled based on thresholds, assess individual risks for hypertension, cardiovascular disease, and prediabetes. Explainability is obtained using SHAP (SHapley Additive exPlanations), which provides insight into feature relevance, while biomarker radar plots help in the visual interpretation of comorbidities. A user-friendly Streamlit interface enables real-time interaction with the tool for potential clinical application. The NAFLD model demonstrated robust performance, while the models used for predicting comorbidities achieved perfect performance, which may be a reflection of the limited dataset size used in the second stage. This work underscores the potential of AI-driven tools in NAFLD diagnosis, particularly when combined with explainable AI methods.

Agent-based modeling (ABM) is a computational method for predicting the emergent outcomes of interacting, autonomous individuals in a complex system. Here, ABM is used to simulate interactions between fibroblast and myofibroblast cells during idiopathic pulmonary fibrosis (IPF) in alveolar tissue microenvironments. These microenvironments are derived from histology of a healthy human lung sample and moderate- and severe-IPF lung samples. Fibroblast differentiation, cell migration, and collagen secretion in response to the spatial distribution of the cytokine transforming growth factor-beta are captured in the ABM using NetLogo software. Results are presented from one simulated year without treatment and with mechanisms representing treatment by pirfenidone and pentoxifylline, alone and in combination. A total of 180 in silico experiments are run, analyzed, and compared in a high-throughput workflow. The effects of the initial number of fibroblasts and treatment scenarios on various metrics related to collagen accumulation and collagen invasion into alveolar regions are determined. The ABM and the analysis files are shared to facilitate model reuse. By integrating computational modeling of IPF and therapeutics, this research aims to improve understanding of fibrosis progression and assess the efficacy of novel and existing treatments targeting different mechanisms to inform decision-making for IPF treatment.

Atrial electromechanics plays a key role in cardiac function by regulating ventricular filling and global hemodynamics, yet remains challenging to model consistently across scales. In this work, a multiscale atrial digital twin for simulations of normal and pathological atrial function is presented, formulated as an electromechanical framework for biatrial simulations that couples three-dimensional atrial electrophysiology and mechanics with a closed-loop zero-dimensional circulatory model. The framework is calibrated on a patient-specific biatrial anatomy to reproduce physiological regional activation times, atrial volumes, ejection fractions, and pressure-volume loop characteristics. The simulations capture all atrial functional phases throughout the cardiac cycle, including realistic figure-eight pressure-volume loops, an aspect hard to achieve in computational studies. A systematic sensitivity analysis quantifies the influence of active contraction, passive stiffness, boundary conditions, and circulatory parameters on atrial function. Finally, application to a pathological scenario through induced persistent atrial fibrillation demonstrates how electrophysiological remodelling propagates across scales, leading to loss of effective atrial contraction, altered atrioventricular flow patterns, and a clinically relevant reduction in cardiac output. Overall, this multiphysics and multiscale framework provides a robust platform to investigate how atrial electrical alterations drive mechanical and hemodynamic alterations in both healthy and pathological conditions.

Computational growth and remodeling (G&R) models have been extentively used to investigate abdominal aortic aneurysm (AAA) progression and to support clinical decision-making. However, the development of robust predictive models is often limited by the scarcity of large-scale longitudinal imaging datasets. In this study, we propose a physics-based G&R framework to simulate AAA shape evolution and generate a virtual cohort of aneurysms, thereby addressing data limitations and enabling integration with data-driven machine learning approaches for growth prediction. The proposed arterial G&R model incorporates key mechanisms influencing aneurysm progression, including elastin degradation and stress-mediated collagen production. A modified elastin degradation formulation was introduced to generate realistic aneurysm geometries exhibiting clinically relevant features such as asymmetry and tortuosity. By systematically varying parameters governing elastin damage and collagen production, 200 distinct G&R simulations were performed to produce a diverse set of AAA geometries. The dataset was further expanded using kriging-based spatial interpolation to construct a large in silico cohort. The synthetic dataset, combined with longitudinal imaging data from 25 patients, was used to train and validate four machine learning models: Deep Belief Network (DBN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). A two-step training strategy was adopted to predict maximum aneurysm diameter and growth rate based on prior geometric characteristics. The LSTM model achieved the highest performance for maximum diameter prediction (R{superscript 2} = 0.92), while the RNN demonstrated strong overall performance (R{superscript 2} = 0.90 for maximum diameter and 0.89 for growth rate). The DBN and GRU models also showed competitive predictive capability. Overall, this study demonstrates that integrating physics-based G&R simulations with machine learning enables accurate prediction of AAA growth and maximum diameter. The proposed framework provides a scalable strategy for augmenting limited clinical datasets and offers a promising tool to support personalized risk assessment and treatment planning.

Background & AimsThe increasing global prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) including metabolic dysfunction-associated steatohepatitis (MASH) creates an urgent need for objective methods of histopathological assessment. Conventional histological approaches are time-consuming and rely on interpreters experience. Therefore, the results obtained may suffer from high variability and only offer coarse categorisation. In this study, we propose a fully automated, deep-learning-based pipeline for the segmentation and characterisation of histological liver features for MASH/MASLD assessment. MethodsSegmentation was applied to H&E sections from 45 mice and 44 humans with MASH/MASLD. The method, which we named qHisto (quantitative histology), utilises the nnU-Net framework and quantifies key histological components of the MASH score, including macro- and microvesicular steatosis, fibrosis, inflammation, hepatocellular ballooning and glycogenated nuclei. Additionally, we characterized the tissue using novel features that are inaccessible through manual histology, such as the distribution of fat droplet sizes, aspect ratio of nuclei and heatmaps. ResultsqHisto parameters showed strong positive correlations with conventional histology scores (fat area R=0.91, inflammation density R=0.7, ballooning density R=0.49) and also with quantitative magnetic resonance imaging (fat area vs. hepatic fat fraction R=0.87). Our novel scores showed that deformation of nuclei is driven by large fat droplets rather than the overall amount of fat. ConclusionsA key advantage of our method is spatially resolved, precise histological quantification. These features provide a finely resolved assessment of disease severity than conventional categorical scoring. By automating time-consuming and repetitive readouts, qHisto improves standardisation and reproducibility of MASH/MASLD feature quantification and provides scalable, slide-wide readouts that can support histopathologists and enhance clinical assessment and therapeutic development. Impact and ImplicationsThe proposed method provides an objective, automatic tool for comprehensive, histological liver analysis of MASH/MASLD, which can be extended to other diseases and organs. By offering classic and novel quantitative parameters and scores, our method could support histologists in their daily routines and provide researchers with further insight into steatotic liver diseases.

Thoracic Endovascular Aortic Repair (TEVAR) is a minimally invasive procedure for the treatment of thoracic aortic pathologies, such as Thoracic Aortic Aneurysm (TAA). Computational simulations can provide valuable insights into TEVAR outcomes and complications prior to surgery, making them a useful tool in the procedural planning. In this work, Fluid-Structure Interaction (FSI) computational simulations are carried out in ten pre-TEVAR patient-specific TAA cases, for which post-TEVAR outcomes are known, to quantify the hemodynamic drag forces acting on the aortic wall. Based on these results, this study proposes a new risk factor R to predict the occurrence of type I and III endoleaks. The patient cohort is divided in a calibration set, used to associate specific R values with three different risk levels, and a validation set, to test the risk factor efficacy. Based on the risk factor values obtained for the calibration set, R[&le;] 0.33 is associated with low risk of endoleak formation, 0.33 < R[&le;] 0.67 with moderate risk, and R > 0.67 with high risk. Once it is applied to the validation set,the risk factor is able to predict the formation of a type Ia endoleak. The risk factor proposed in this work is capable of identifying all the endoleak cases analysed, as well as conditions known to increase the risk of TEVAR complications. This study represents a preliminary attempt to determine whether pre-TEVAR hemodynamics can effectively predict post-TEVAR complications and thereby aid clinicians in the pre-operative planning.

Artificial intelligence (AI) based segmentation has many medical applications but limited curated datasets challenge model training; this study compares the impact of dataset annotation quality and quantity on whole liver AI segmentation performance. We obtained 3,089 abdominal computed tomography scans with whole-liver contours from MD Anderson Cancer Center (MDA) and a MICCAI challenge. A total of 249 scans were withheld for testing of which 30, MICCAI challenge data, were reserved for external validation. The remaining scans were divided into mixed-curation and highly-curated groups, randomly sampled into sub-datasets of various sizes, and used to train 3D nnU-Net segmentation models. Dice similarity coefficients (DSC), surface DSC with 2mm margins (SD 2mm), the 95th percentile of Hausdorff distance (HD95), and 2D axial slice DSC (Slice DSC) were used to evaluate model performance. The highly curated, 244-scan model (DSC=0.971, SD 2mm=0.958, HD95=2.98mm) performed insignificantly different on 3D evaluation metrics to the mixed-curation 2,840-scan model (DSC=0.971 [p>.999], SD 2mm=0.958 [p>.999], HD95=2.87mm [p>.999]). The 710-scan mixed-curation (Slice DSC=0.929) significantly outperformed the highly curated, 244-scan model (Slice DSC=0.923 [p=0.012]) on the 30 external scans. Highly curated datasets yielded equivalent performance to datasets that were a full order of magnitude larger. The benefits of larger, mixed-curation datasets are evidenced in model generalizability metrics and local improvements. In conclusion, tradeoffs between dataset quality and quantity for model training are nuanced and goal dependent.

AimsWe aimed to develop and evaluate fully automated artificial intelligence (AI) system. for detection of mitral valve prolapse (MVP) and mitral regurgitation (MR) from echocardiographic studies. Methods and ResultsWe used a dataset of 24,869 echocardiographic studies from the University of California San Francisco (UCSF) to train a multi-view deep neural network (DNN) to detect MVP using apical 4-chamber, 2-chamber, and parasternal long-axis views. A separate dataset of 27,906 studies from UCSF was used to train a second multi-view DNN model to detect moderate-to-severe or severe MR using color Doppler in the same views. External validation was performed on echocardiographic MVP videos from Houston Methodist Hospital. The DNN model for MVP detection achieved an AUC of 0.917 (95% CI: 0.899-0.934), with stronger performance in those with mitral annular disjunction or bileaflet MVP. External validation for MVP detection in a geographically and demographically distinct population yielded an AUC of 0.835 (95% CI: 0.803-0.869). The DNN for detection of moderate-to-severe or severe MR in patients with concurrent MVP achieved an AUC of 0.877 (95% CI: (0.805-0.939). ConclusionsAI algorithms can perform automatic detection of MVP and clinically significant MR from echocardiogram studies with high performance. The MVP DNN performed particularly well for more severe MVP phenotypes such as mitral annular disjunction or bileaflet MVP. These algorithms could provide a novel approach for automated, accurate, and rapid diagnosis of MVP and its common clinical sequelae across institutions. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=123 SRC="FIGDIR/small/26347229v1_ufig1.gif" ALT="Figure 1"> View larger version (41K): org.highwire.dtl.DTLVardef@1d78db8org.highwire.dtl.DTLVardef@995b29org.highwire.dtl.DTLVardef@301b86org.highwire.dtl.DTLVardef@5f1427_HPS_FORMAT_FIGEXP M_FIG C_FIG

Accurate diagnosis of cardiac abnormalities from electrocardiogram signals remains a central challenge in automated cardiovascular assessment. This study investigates the efficiency of time-frequency representations and deep learning architectures in classifying 12-lead ECGs into five diagnostic super-classes using the PTB-XL dataset. Continuous Wavelet Transform is applied to generate time- frequency representations, scalograms and phasograms, representing spectral energy and phase distributions, respectively. We experiment with both early and late information fusion strategies using several convolutional and transformer-based networks of a custom Convolutional Neural Network, Hybrid Deep Learning, transfer learning, feature fusion, and ensemble modeling, and weighted loss strategies. An ensemble fusion of models trained on time-frequency representation and time representation achieved the best overall performance of Area Under Curve of 0.9233 surpassing individual modalities. To improve the results further, weighted focal loss is used to improve the low classification rates in some labels due to imbalanced data. The results highlight the potential of multi-representation wavelet fusion for interpretable and generalizable ECG classification.

BackgroundPressure-volume (PV) loop analysis remains the gold standard for assessing the intrinsic global diastolic properties of the left ventricle (LV). Traditional fitting techniques rely on local, phase-constrained fittings and are limited due to their sensitivity to noise, landmark selection, violation of assumptions, and non-convergence. ObjectiveTo develop and validate DIA-PINN, a physics-informed neural network (PINN) framework capable of calculating intrinsic diastolic properties of the LV from measured instantaneous PV data, combining mechanistic interpretability with machine learning flexibility. MethodsInstantaneous LV diastolic pressure was modeled as the sum of 1) time-dependent relaxation-related pressure and 2) volume-dependent recoil and stiffness-related pressures. DIA-PINN was trained using time, LV pressure and volume as inputs, enforcing data fidelity, model consistency, and physiological plausibility within the loss function. Performance was evaluated in 4,000 Monte Carlo simulations of LV PV-loops, and in clinical data from 59 patients who underwent catheterization (39 with heart failure and normal ejection fraction and 20 controls). DIA-PINN derived indices were compared to those obtained from a previously validated global optimization method (GOM). ResultsOn the simulation data, DIA-PINN accurately recovered all constitutive indices (intraclass correlation coefficients near unity) and improved GOM performance. On the clinical data, diastolic indices derived using DIA-PINN strongly correlated with GOM estimates (R>0.90, p<0.001) but were insensitive to initialization. DIA-PINN performed best under vena cava occlusion, as varying preload improved parameter identifiability. ConclusionsWhen applied to instantaneous pressure-volume data, a generalizable PINN framework, DIA-PINN, provides an improved method for assessing global intrinsic diastolic properties of cardiac chambers. New & NoteworthyOur work introduces DIA-PINN, a physics-informed neural network framework to process instantaneous ventricular pressure-volume data, solving a mechanistic model of diastole with machine learning techniques. Compared to current conventional or optimization-based approaches, the PINN provides the most reliable estimates of diastolic stiffness, relaxation, and elastic recoil, unsensitive to initialization. By embedding physiological constraints into network training, this approach achieves robust, interpretable, and clinically applicable quantification of gold-standard metrics of intrinsic global diastolic chamber properties.

Objective: Skin sympathetic nerve activity (SKNA) has emerged as a promising non-invasive surrogate measure of sympathetic drive, but its relevant physiological characteristics remain ill-defined. This observational study aims to investigate its regulatory patterns during rest and Valsalva maneuver (VM) in healthy participants. Method: Using a two-layer strategy integrating signal analysis and physiological modelling, we analyzed data recorded from 41 subjects performing repeated VMs. The observational layer includes time-domain feature comparisons using linear mixed-effect models, and time-varying spectral coherence analysis. The mechanistic layer proposes a mathematical model to investigate whether baroreflex and respiratory modulation are sufficient to reproduce the observed HR and average SKNA (aSKNA) dynamics. Main Results: Mean integrated SKNA (iSKNA) showed more significant change than HRV for VM induced effects. We also found mean iSKNA increase during VM varies with BMI and sex. The coherence analysis indicated that iSKNA strongly synchronized with EDR under resting conditions. The proposed model successfully reproduced main characteristics of aSKNA dynamics, yielding a high median Pearson correlation coefficient of 0.80 ([Q1, Q3] = [0.60, 0.91]). In contrast, HR dynamics were only partially captured, with a median PCC of 0.37 ([Q1, Q3] = [0.16, 0.55]). These results likely suggest SKNA provides a more direct representation of sympathetic burst dynamics during VM in healthy subjects. Significance: This study provides convergent evidence that SKNA reflects known autonomic regulatory influences in healthy subjects. These findings strengthen the physiological interpretability of SKNA while clarifying its appropriate use as a practical biomarker of sympathetic function.

The present study presents a systematic approach for generating data-driven synthetic cerebral aneurysm geometries and evaluating their hemodynamics through computational fluid dynamics. Seven patient-specific aneurysm geometries from the right internal carotid artery were reconstructed from time-of-flight magnetic resonance angiography images and standardized through orientation alignment, followed by non-rigid registration onto a common spherical point cloud as a template. Principal component analysis (PCA) was then applied to the aligned point-cloud data to quantify morphological variability and parameterize shape deformation. The first four principal components captured over 90% of the total variance; however, higher-order components were required to capture the detailed geometrical features of the original geometries. Computational fluid dynamic simulations were performed on the PCA-based synthetic geometries under pulsatile flow conditions to investigate the influence of shape variations on intra-aneurysmal flow patterns, time-averaged wall shear stress (TAWSS), and oscillatory shear index (OSI). The first principal component score (PCS1), which was associated with changes in aneurysm height and dome width, had the strongest effects on TAWSS and OSI levels. Lower PCS1 values, which corresponded to taller and more oblique domes, produced slower adjacent flow and elevated OSI, whereas higher PCS1 values increased TAWSS. The second principal component score primarily modulated lateral geometric asymmetry and further influenced OSI distribution for the lower PCS1 values. Collectively, these findings indicate that PCA-based shape parameterization provides a practical approach for generating synthetic aneurysm datasets and systematically assessing how specific morphological features govern hemodynamic behavior. The proposed approach is expected to contribute to the future development of surrogate modeling and data-driven hemodynamic prediction.

Sight is one of the five senses essential to human experience, and the eyes are vital organs that require careful protection. These organs are also susceptible to a variety of diseases, some of which may develop without obvious external symptoms, necessitating specialized imaging and diagnostic techniques. Conversely, other conditions present visible signs that can be observed directly. This paper presents a practical approach to the identification of thirteen well-known eye diseases-cataract, corneal neovascularization, corneal ulcer, dry eye, endophthalmitis, globe rupture, Graves ophthalmopathy, ptosis, scleritis, strabismus, stye, uveitis, and xanthelasma-based on visual symptoms. Using transfer learning with the ResNet152V2 deep learning model, we demonstrate an average validation accuracy of 98.8%. The methodology is presented in a reproducible, step-by-step format suitable for educational purposes, allowing opticians, general practitioners, and learners to explore automated eye disease diagnosis. All code, datasets, and procedures are documented to facilitate practical learning and replication.

This research presents multimodal deep learning for structural heart disease prediction. We evaluated multiple deep learning architectures, including TCN, Simple CNN, ResNet1d18, Light transformer and Hybrid model. The models were examined across the three seeds to ensure robustness, and bootstrap confidence interval is used to measure performance differences. TCN consistently outperforms other competing architectures, achieving statistically significant improvements with stable performance across runs. Similarly in predictive analysis, TCN has efficient computation and stable training compared to all competing architectures. Our results show that TCN emphasizes fairness evaluation when developing deep learning models for healthcare applications.

Background: Atrial fibrillation (AFib) is the most common sustained arrhythmia in the world, imposing a heavy clinical and economic burden on global healthcare systems. Early detection of AFib can reduce mortality and morbidity, while helping to alleviate the growing economic burden of cardiovascular diseases. With the increasing availability of digital health technologies, computational solutions have great potential to support the timely diagnosis of cardiac abnormalities. Objectives: With the increasing availability of electrocardiogram (ECG) data from clinical and wearable devices, manual interpretation has become impractical due to its time-consuming and subjective nature. Existing automated approaches often rely on single classifiers or fixed ensembles that primarily optimize predictive accuracy while neglecting model diversity, which leads to limited robustness and generalization across heterogeneous datasets. Therefore, this study aims to develop a robust and diversity-aware framework for automatic AFib detection that simultaneously improves classification performance and model generalizability. To this end, we propose MOE-ECG, a multi-objective ensemble selection and fusion framework that explicitly optimizes both predictive performance and inter-model diversity for reliable AFib detection from ECG recordings. Methods: The proposed multi-objective ensemble (MOE) framework uses ensemble selection as a bi-objective optimization problem and employs multi-objective particle swarm optimization to identify complementary classifiers from a heterogeneous model pool. Unlike conventional ensembles, it explicitly optimizes both predictive performance and diversity and integrates Dempster-Shafer theory for uncertainty-aware decision fusion. After filtering the ECG signals to remove baseline wander and noise, they were segmented into windows of 20, 60, and 120 heartbeats with 50% overlap. The proposed approach was evaluated over five independent runs to assess its stability and generalization. Fifteen statistical and nonlinear features were obtained from the RR-intervals of the pre-processed ECG signals, of which eight features were selected with correlation analysis to capture subtle information from the ECG data. We trained and evaluated the performance of the proposed model in three open source databases, namely, the MIT-BIH Atrial Fibrillation Database, Saitama Heart Database Atrial Fibrillation, and Long-Term AF Database. Results: The proposed approach achieved the best overall performance on 60-beat segments, with an average accuracy of 89.85%, precision of 91.14%, recall of 94.19%, an F1-score of 92.64%, and area under the curve (AUC) of around 0.95. Statistical analysis using Holm-adjusted Wilcoxon tests confirmed significant improvements (p<0.05) compared to both the best individual classifier and the unoptimized average ensemble of all classifiers. These findings show that the proposed selection and evaluation methodology, rather than group aggregation alone, is the key driver of performance improvements. Conclusion: The results obtained demonstrate that the MOE-ECG model offers a robust, accurate, and reliable solution for the detection of AFib from short ECG segments. The empirical findings, in general, confirm that multi-objective ensemble fusion enhances diagnostic performance and offers robust predictions that will open up possibilities for real-time AFib detection in clinical and tele-health settings.

PurposeTo evaluate the hemodynamic impact of restoring a normal sino-tubular junction (STJ) following a novel Hegar dilator-based procedure in patients undergoing root-sparing ascending thoracic aortic aneurysm (ATAA) repair using computational modeling. MethodsWe retrospectively selected an ATAA patient who underwent pre- and postoperative gated computed tomography angiography (CTA). We developed a novel workflow to segment the lumen, thick-walled aorta, and aortic valve from CTA images for subsequent blood flow analysis using computational fluid dynamics (CFD) and fluid-structure interaction (FSI). Morphological and hemodynamic characteristics of the root were quantified and compared against those of a control subject, with no noted ascending aortic dilation. The models sensitivity to graft properties and leaflet material heterogeneity was analyzed. ResultsBoth CFD and FSI results showed that the postoperative geometry reconstructed with a normal STJ profile reintroduces sinus vortices during peak systole, similar to the control subject, but were absent pre-surgery. Accounting for aortic valve leaflets in FSI studies yielded qualitatively similar results to the CFD cases, albeit with locally elevated velocities, time-averaged wall shear stress (TAWSS), and energy dissipation, likely due to the dynamically changing orifice area and differing profiles of the left ventricular outflow tract (LVOT). ConclusionWe demonstrated that the novel Hegar dilator-based STJ reconstruction restores normal blood flow patterns, highlighting the importance of reprofiling the aortic sinuses and STJ. The study also highlights the models sensitivities, particularly the LVOT shape and leaflet morphology and mobility, and may assist planning STJ reconstruction to yield optimal hemodynamics before intervention.

BackgroundEndovascular aortic aneurysm repair (EVAR) is effective in preventing rupture of abdominal aortic aneurysm (AAA), but endoleak remains a serious postoperative complication. Accurate prediction of endoleak risk is a significant clinical challenge. PurposeThis study aimed to evaluate the value of a Point Cloud Neural Network (PCNN) in predicting endoleaks after EVAR by integrating multimodal features. Materials and MethodsWe collected follow-up data from 381 AAA patients. Radiomic characteristics of the procedural intraluminal thrombus and morphological parameters were extracted following medical image segmentation and 3D reconstruction. Hemodynamic parameters, including time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), and relative residence time (RRT), were obtained through a semi-automated computational fluid dynamics (CFD) workflow. Six traditional machine learning models and four PCNN architectures were developed with progressively added feature sets: 1) medical history and morphology (H+M); 2) H+M+R; 3) H+M+CFD; and 4) all features combined (H+M+R+CFD). ResultsTraditional ML models showed limited performance (AUC range: 0.55-0.77). In contrast, PCNN models demonstrated substantially improved predictive capability. The baseline PCNN (H+M) achieved an AUC of 0.81. The RA-PCNN model incorporating radiomic features showed a 6.58% improvement (AUC=0.86). The CFD-PCNN model with hemodynamic parameters exhibited a 13.0% increase (AUC=0.91), with superior F1-score (0.78) and recall (0.88). The multimodal RA-CFD-PCNN model performed best, achieving an AUC of 0.93, accuracy of 0.90, and F1-score of 0.83. ConclusionThis study establishes a PCNN-based framework for endoleak prediction that significantly outperforms traditional machine learning methods, providing an effective approach for assessing endoleaks in AAA patients. Summary statementThis study developed a PCNN-based framework integrating clinical, morphologic al, radiomic, and hemodynamic features from 381 AAA patients to predict endoleaks after EVAR. Results demonstrated superior performance over traditional ML, with hemodynamic parameters providing a major performance boost, highlighting the value of physiological and biomechanical feature integration for vascular disease prediction. Key ResultsThe multimodal PCNN model integrating all features achieved an AUC of 0.93, significantly outperforming traditional machine learning models (AUCs 0.55-0.77). Incorporating hemodynamic parameters provided the greatest performance increase, with the CFD-PCNN models AUC increasing by 13.0% to 0.91 compared to the baseline PCNN (AUC=0.81). The model combining radiomics and hemodynamics (RA-CFD-PCNN) achieved the highest F1-score of 0.83 and AUC of 0.93, demonstrating robust predictive accuracy.

Assessing the human infection potential of emerging coronaviruses remains a critical challenge for global health preparedness. In this study, we developed a machine learning-based framework to predict the human infection potential of coronaviruses and to identify associated sequence motifs using spike (S) protein sequences. A total of 3,904 complete S protein sequences were collected, annotated as human or non-human infection and encoded using trimer-based k-mer features. Model benchmarking was conducted across 27 machine learning algorithms, followed by hyperparameter optimization of the selected model. Robustness and generalizability were evaluated using k-fold cross-validation and independent external validation. Feature interpretability was further assessed using SHAP analysis to identify sequence determinants associated with infection potential. The Random Forest classifier achieved the best performance, with accuracy, sensitivity, and specificity of 97.8%, 99%, and 97.4%, respectively, and demonstrated stable predictive performance across validation datasets. Notably, the KIQ and LEP motifs were strongly associated with human infection coronaviruses and mapped to the HR1 and N-terminal domain regions of the S protein. Overall, this framework provides a practical approach for risk assessment and surveillance of emerging coronaviruses. Author summaryEmerging coronaviruses continue to threaten global public health, but rapidly identifying viruses with the potential to infect humans remains challenging. Traditional experimental approaches are time-consuming and resource-intensive, limiting their use for large-scale surveillance. In this study, we developed a machine learning based workflow to assess the human infection potential of coronaviruses using spike protein sequences. By analyzing sequence patterns across a diverse set of coronaviruses, our framework enables rapid screening of coronaviruses from multiple host species. Unlike previous studies focused on limited coronavirus genera, our approach integrates all four genera and systematically evaluates multiple learning strategies. Importantly, our analysis identifies conserved sequence motifs linked to human infection potential, bridging predictive performance with biological interpretability. Our findings demonstrate computational approaches support early warning systems for identifying high risk coronaviruses, contributing to prioritize viruses for experimental validation, guide surveillance efforts, and strengthen global pandemic preparedness under a One Health perspective.