arXiv subjects

Hannah Smith

Publications and source records attributed to Hannah Smith.

5 recordsLinked to original sources

arXiv2025

Female anatomies disguise ECG abnormalities following myocardial infarction: an AI-enabled modelling and simulation study

The electrocardiogram (ECG) is modulated by torso-heart anatomy, and this challenges patients' diagnosis and risk stratification. This study aims to quantify how torso-heart anatomical factors affect sex-differences in ECG biomarkers in acute and chronic myocardial infarction (MI). We exploit the perfect control of AI-augmented multiscale modelling and simulation, based on clinical magnetic resonance imaging (MRI) data and ECGs for model construction and validation. A cohort of 1720 torso-ventricular anatomies (50% female) was constructed from MRIs of healthy and post-MI participants in the UK Biobank study. 8600 ECG simulations were performed considering anatomical variability and 3 electrophysiological stages (healthy, acutely ischemic, and infarcted). The effect of cardiac size, position, and orientation on each ECG biomarker was quantified. Female anatomies had larger distances between the infarct and ECG electrodes (relative to cardiac size), and larger angles between the infarct normal and ECG lead axes, both primarily caused by their more superior cardiac position. This reduced ST-elevation and caused low-amplitude late depolarisation and repolarisation tails to be missed, shortening QRS duration (QRSd) and T-peak-to-end interval (TpTe). The position and orientation of the heart impacted TpTe more severely than QRSd. AI-enabled mechanistic modelling and simulation identify smaller ventricles, superior cardiac position, and different ventricular orientation as key anatomical contributors of shorter QRS and T waves, and lower ST-elevation, in female versus male anatomies. This provides a blueprint for quantifying the impact of anatomical sex differences on functional markers and enables future work in tailoring clinical guidelines considering unique patient anatomy to reduce biased outcomes.

physics.med-ph↗

arXiv2025

An Automated Computational Pipeline for Generating Large-Scale Cohorts of Patient-Specific Ventricular Models in Electromechanical In Silico Trials

In recent years, human in silico trials have gained significant traction as a powerful approach to evaluate the effects of drugs, clinical interventions, and medical devices. In silico trials not only minimise patient risks but also reduce reliance on animal testing. However, the implementation of in silico trials presents several time-consuming challenges. It requires the creation of large cohorts of virtual patients. Each virtual patient is described by their anatomy with a volumetric mesh and electrophysiological and mechanical dynamics through mathematical equations and parameters. Furthermore, simulated conditions need definition including stimulation protocols and therapy evaluation. For large virtual cohorts, this requires automatic and efficient pipelines for generation of corresponding files. In this work, we present a computational pipeline to automatically create large virtual patient cohort files to conduct large-scale in silico trials through cardiac electromechanical simulations. The pipeline generates the files describing meshes, labels, and data required for the simulations directly from unprocessed surface meshes. We applied the pipeline to generate over 100 virtual patients from various datasets and performed simulations to demonstrate capacity to conduct in silico trials for virtual patients using verified and validated electrophysiology and electromechanics models for the context of use. The proposed pipeline is adaptable to accommodate different types of ventricular geometries and mesh processing tools, ensuring its versatility in handling diverse clinical datasets. By establishing an automated framework for large scale simulation studies as required for in silico trials and providing open-source code, our work aims to support scalable, personalised cardiac simulations in research and clinical applications.

cs.CE↗

arXiv2024

Personalized Topology-Informed Localization of Standard 12-Lead ECG Electrode Placement from Incomplete Cardiac MRIs for Efficient Cardiac Digital Twins

Cardiac digital twins (CDTs) offer personalized in-silico cardiac representations for the inference of multi-scale properties tied to cardiac mechanisms. The creation of CDTs requires precise information about the electrode position on the torso, especially for the personalized electrocardiogram (ECG) calibration. However, current studies commonly rely on additional acquisition of torso imaging and manual/semi-automatic methods for ECG electrode localization. In this study, we propose a novel and efficient topology-informed model to fully automatically extract personalized ECG standard electrode locations from 2D clinically standard cardiac MRIs. Specifically, we obtain the sparse torso contours from the cardiac MRIs and then localize the standard electrodes of 12-lead ECG from the contours. Cardiac MRIs aim at imaging of the heart instead of the torso, leading to incomplete torso geometry within the imaging. To tackle the missing topology, we incorporate the electrodes as a subset of the keypoints, which can be explicitly aligned with the 3D torso topology. The experimental results demonstrate that the proposed model outperforms the time-consuming conventional model projection-based method in terms of accuracy (Euclidean distance: $1.24 \pm 0.293$ cm vs. $1.48 \pm 0.362$ cm) and efficiency ($2$~s vs. $30$-$35$~min). We further demonstrate the effectiveness of using the detected electrodes for in-silico ECG simulation, highlighting their potential for creating accurate and efficient CDT models. The code is available at https://github.com/lileitech/12lead_ECG_electrode_localizer.

eess.IV↗

arXiv2021

Explaining Answers with Entailment Trees

Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If this could be done, new opportunities for understanding and debugging the system's reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees. Given a hypothesis (question + answer), we define three increasingly difficult explanation tasks: generate a valid entailment tree given (a) all relevant sentences (b) all relevant and some irrelevant sentences, or (c) a corpus. We show that a strong language model can partially solve these tasks, in particular when the relevant sentences are included in the input (e.g., 35% of trees for (a) are perfect), and with indications of generalization to other domains. This work is significant as it provides a new type of dataset (multistep entailments) and baselines, offering a new avenue for the community to generate richer, more systematic explanations.

cs.CL↗

arXiv2019

ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition

Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks. In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. Semantic class labels are drawn from a manually-constructed fine-grained typology of 601 classes generated through a data-driven analysis of 4,239 science exam questions. We show an off-the-shelf BERT-based named entity recognition model modified for multi-label classification achieves an accuracy of 0.85 F1 on this task, suggesting strong utility for downstream tasks in science domain question answering requiring densely-labeled semantic classification.

cs.CL↗