Article

Representation-first transformer semantic phenotyping reveals hidden burden heterogeneity in adult congenital heart disease

2026-06-01

Abstract excerpt

<title>Abstract</title> <p>Anatomy-based categories cannot fully explain patient-reported burden in adults with congenital heart disease (CHD), yet conventional clustering often relies on tabular distances that may not encode clinical similarity. In this cross-sectional registry analysis, we tested whether deterministic clinical summaries embedded by a schema-adapted transformer encoder could provide a clinically...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 57dca4fb-40d5-5d76-a121-e15f6198df68
DOI: 10.21203/rs.3.rs-9753063/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Representation-first transformer semantic phenotyping reveals hidden burden heterogeneity in adult congenital heart diseaseDOI 10.21203/rs.3.rs-9753063/v1Read

Contrastive Transformer-Driven Discovery of Temporal Hemodynamic Subphenotypes in Cardiac Surgery PatientsSemantic proximity Read

Characterizing Patient Representations for Computational PhenotypingSemantic proximity Read

Identification of Digital Twins to Guide Interpretable AI for Diagnosis and Prognosis in Heart FailureSemantic proximity Read

Characterizing Patient Representations for Computational Phenotyping.Semantic proximity Read

From Black Box to Discovery Engine: A Geometric and Topological Framework for Interpreting Graph Neural Networks in Critical CareSemantic proximity Read

Deep latent variable modelling reveals clinically significant subgroups among transfusion recipientsSemantic proximity Read

Natural Language Processing to Build a Multicenter Computable Phenotype Library for Adults with Congenital Heart DiseaseSemantic proximity Read

A calibrated temporal reference map of disease progressionSemantic proximity Read

The Diagnostic Flow Framework: An Engineering-Based Multi-Domain Architecture for the Classification of Cardiovascular DiseasesSemantic proximity Read

Deep Learning of Electrocardiograms Enables Scalable Human Disease ProfilingSemantic proximity Read

AI-based derivation of atrial fibrillation phenotypes in the general and critical care populations.Semantic proximity Read

A Unified Spatial AI Framework for Cross-Domain Tissue-State Analysis in Trauma, Oral, and Cardiovascular PathologySemantic proximity Read