AI-Based Phenotyping of Atrial Fibrillation Through Generative Topographic Mapping: Prospective Murcia Atrial Fibrillation Project III Cohort Study

Soler Espejo, E ORCID: 0000-0003-4925-4864, Chen, Y ORCID: 0000-0002-2808-6286, Ramos-Bratos, MP ORCID: 0009-0006-4528-0845, Ortega-Martorell, S ORCID: 0000-0001-9927-3209, Olier, I ORCID: 0000-0002-5679-7501, Rivera-Caravaca, JM ORCID: 0000-0003-0492-6241, Marín, F ORCID: 0000-0001-7246-7708, Roldán, V ORCID: 0000-0002-4945-6602 and Lip, GYH ORCID: 0000-0002-7566-1626 (2026) AI-Based Phenotyping of Atrial Fibrillation Through Generative Topographic Mapping: Prospective Murcia Atrial Fibrillation Project III Cohort Study. Journal of Medical Internet Research, 28. pp. 1-17. ISSN 1439-4456

Preview

Text AIBased Phenotyping of Atrial Fibrillation Through Generative Topographic Mapping.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

The clinical heterogeneity of atrial fibrillation (AF) challenges current classifications and risk scores, limiting their real-world applicability. AI-driven methods may enhance phenotyping and risk stratification. This study aimed to apply a generative topographic mapping (GTM)-based clustering approach to a large, real-world, prospective AF cohort to identify clinically relevant phenotypes and assess their associations with clinical outcomes. We conducted a prospective observational cohort study including consecutive adult outpatients with newly diagnosed AF who initiated oral anticoagulation between January 2016 and November 2021. Cardiometabolic risk was modeled as a multidimensional construct integrating cardiovascular and metabolic comorbidities. GTM was applied to project high-dimensional clinical data into a low-dimensional latent space, enabling probabilistic patient representation and visualization of phenotypic structure. Unsupervised hierarchical clustering using Ward's method was performed on the latent space to identify AF phenotypes, and patients were assigned to clusters based on their highest posterior probability. Clinical outcomes, including thromboembolic events, major bleeding, major adverse cardiovascular events (MACE), cardiovascular death, and all-cause death, were assessed over a maximum follow-up of 2 years. Nonfatal outcomes were analyzed using Fine-Gray competing-risk models and reported as subdistribution hazard ratios (sHRs), whereas cardiovascular and all-cause death were analyzed using adjusted Cox proportional hazards models and reported as adjusted hazard ratios (aHRs). Among 3259 patients with AF (median age 77, IQR 70-83 years; 1721/3259, 52.8% female; mean follow-up 1.81 years), four phenotypes emerged: (1) older with highest cardiometabolic burden, (2) older with lower cardiometabolic risk, (3) comparatively younger with intermediate-high cardiometabolic risk, and (4) comparatively younger with intermediate cardiometabolic risk. Compared with phenotype 1, phenotype 4 demonstrated lower risks of thromboembolic events (sHR 0.70, 95% CI 0.50-0.98), major bleeding (sHR 0.61, 95% CI 0.42-0.89), and MACE (sHR 0.67, 95% CI 0.47-0.94). Regarding cardiovascular and all-cause death, all phenotypes demonstrated a lower risk compared with phenotype 1: phenotype 2 (aHR 0.52, 95% CI 0.33-0.85; and aHR 0.66, 95% CI 0.50-0.87, respectively), phenotype 3 (aHR 0.57, 95% CI 0.32-0.99; and aHR 0.44, 95% CI 0.30-0.65, respectively), and phenotype 4 (aHR 0.49, 95% CI 0.33-0.72; and aHR 0.56, 95% CI 0.44-0.71, respectively). However, these associations were attenuated after further adjustment for age, sex, and major comorbidities, with phenotype 4 retaining a significant association with lower cardiovascular death and phenotypes 3 and 4 retaining significant associations with lower all-cause death. GTM-based clustering analysis identified prognostically distinct AF phenotypes, highlighting the potential of machine learning approaches to support personalized AF care. Further external validation is needed to establish the generalizability of these findings.

Item Type:	Article
Uncontrolled Keywords:	Humans; Atrial Fibrillation; Cluster Analysis; Cohort Studies; Prospective Studies; Phenotype; Artificial Intelligence; Aged; Middle Aged; Female; Male; Generative Artificial Intelligence; Clustering Algorithms; AF; AI; artificial intelligence; atrial fibrillation; clinical outcomes; generative topographic mapping; phenotypes; Humans; Atrial Fibrillation; Female; Phenotype; Prospective Studies; Male; Aged; Clustering Algorithms; Artificial Intelligence; Generative Artificial Intelligence; Middle Aged; Cohort Studies; Cluster Analysis; 32 Biomedical and Clinical Sciences; 3202 Clinical Sciences; Patient Safety; Clinical Research; Hematology; Machine Learning and Artificial Intelligence; Health Disparities and Racial or Ethnic Minority Health Research; Cardiovascular; Heart Disease; 4.1 Discovery and preclinical testing of markers and technologies; Cardiovascular; 3 Good Health and Well Being; 4203 Health Services and Systems; 42 Health Sciences; Hematology; Machine Learning and Artificial Intelligence; Precision Medicine; Heart Disease; Clinical Research; Cardiovascular; 4.1 Discovery and preclinical testing of markers and technologies; 4.2 Evaluation of markers and technologies; Cardiovascular; 3 Good Health and Well Being; Humans; Atrial Fibrillation; Female; Phenotype; Prospective Studies; Male; Aged; Clustering Algorithms; Artificial Intelligence; Generative Artificial Intelligence; Middle Aged; Cohort Studies; Cluster Analysis; 08 Information and Computing Sciences; 11 Medical and Health Sciences; 17 Psychology and Cognitive Sciences; Medical Informatics; 4203 Health services and systems
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > RC Internal medicine R Medicine > RT Nursing
Divisions:	Computer Science and Mathematics Nursing, Public and Allied Health
Publisher:	JMIR Publications Inc.
Date of acceptance:	19 June 2026
Date of first compliant Open Access:	20 August 2026
Date Deposited:	20 Aug 2026 15:47
Last Modified:	20 Aug 2026 15:47
DOI or ID number:	10.2196/90502
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29175

View Item