# AI-gestuurde fenotypisering van HFpEF onthult vroege en late ziektestadia — EHR-cohortstudie

*geplaatst 2026-10-05 · Hartfalen · Open heart · doi 10.1136/openhrt-2026-004351 · https://hartvaat.nl/2026/09/25/ai-gestuurde-fenotypisering-van-hfpef-onthult-vroege-en-late-ziektestadia-ehr-co/*

In een cohort van 2223 patiënten met hartfalen met behoud van ejectiefractie (HFpEF) identificeerde een AI-gestuurde analyse van elektronische patiëntendossiers vier herhaalbare fenotypen: jong met weinig comorbiditeit, obesitas-gerelateerd, ouderen met atriale dysfunctie en cardiovasculair-nier-metabool (C-K-M). Patiënten in het C-K-M-fenotype hadden het hoogste sterfterisico (HR 1,53), terwijl het fenotype 'jong met weinig comorbiditeit' het meest dynamisch was en vaak overging in een meer gevorderd stadium. Deze longitudinale fenotypisering kan cardiologen helpen om HFpEF-patiënten eerder te stratificeren en mogelijk modificeerbare vroege ziektestadia te herkennen voor gerichte therapie.

## English: Longitudinal phenotyping of heart failure with preserved ejection fraction identifies early- and end-stage disease states.

Using AI-driven analysis of electronic health records in 2,223 patients with HFpEF, researchers identified four reproducible phenotypes: young with low comorbidity, obesity-predominant, elderly with atrial dysfunction, and cardiovascular-kidney-metabolic (C-K-M). The C-K-M phenotype carried the highest mortality risk (HR 1.53), while the young-low comorbidity group showed the highest disease progression rate, often transitioning to more advanced stages. Longitudinal phenotyping may help clinicians stratify HFpEF patients earlier and target therapies to potentially modifiable disease phases.

## Abstract (original, from the publication)

BACKGROUND AND AIMS: Heart failure with preserved ejection fraction (HFpEF) phenotypes have been characterised as static entities in trial populations yet their temporal dynamics remain unexplored in routine clinical practice. We aimed to identify HFpEF phenogroups from real-world electronic health records (EHRs), characterise their longitudinal stability and determine whether phenogroup trajectories were associated with differences in mortality. METHODS: A natural language processing (NLP) pipeline identified HFpEF cases from multisite EHRs (2010-2022). Latent class analysis (LCA) defined baseline phenogroups and annual supervised random forest (RF) classification using time-updated values of the same baseline LCA variables tracked individual transitions over five years. Competing risks regression quantified transition versus death probabilities. Time-varying Cox models assessed mortality risk associated with current (vs baseline) phenogroup status. Phenogroups were independently re-derived by LCA in an external cohort and compared with RF predictions. RESULTS: Among 2223 patients (60% female, median age 75 years (IQR 63-83); left ventricular ejection fraction (LVEF) 60.1%; follow-up 4.0 years (IQR 2.2-6.1), we identified four phenogroups: young-low comorbidity (22%), obesity-predominant (24%), elderly atrial dysfunction (32%) and cardiovascular-kidney-metabolic (23%). Young-low comorbidity had the highest transition probability (47.7%), while cardiovascular-kidney-metabolic and elderly-atrial dysfunction were highly stable (3.2% and 12.1% transitioned, respectively). Within young-low comorbidity, those who transitioned had greater baseline cardiac abnormalities, including higher E/e', left ventricle mass and wall thickness. Adjusted mortality risk was highest in cardiovascular-kidney-metabolic (HR 1.53, 95% CI 1.22 to 1.92, p<0.001); current phenogroup status discriminated mortality risk modestly better than baseline classification alone (C-index 0.659 vs 0.648). In an independent external cohort (n=3349), RF predictions agreed strongly with independently derived LCA phenogroup labels (C-statistics 0.891-0.953). CONCLUSION: Longitudinal NLP-based phenotyping of real-world EHRs identified four reproducible HFpEF phenogroups with distinct trajectories, distinguishing an early progressive disease state from stable advanced phenotypes. Earlier HFpEF detection using artificial intelligence-driven EHR tools could facilitate phenotype-targeted treatment of patients at potentially modifiable stages.

Auteurs: Samuel Brown, Fardad Soltani, Jack Wu, Matthew Ryan, Brett S Bernstein, Brian Tam To, Tom Searle, Maleeha Rizvi, Natalie Fairhurst, George Kaye, Ranu Baral, Dhanushan Vijayakumar, Daksh Mehta, Zeeshan Khawaja, Phil Chowienczyk, James Teo, Richard Jb Dobson, Daniel I Bromage, Gerald Carr-White, Thomas F Lüscher, Ali Vazir, Theresa A McDonagh, Jessica Webb, Christopher A Miller, Ajay M Shah, Dhruva Biswas, Kevin O'Gallagher

---
Bron: Open heart, https://doi.org/10.1136/openhrt-2026-004351. Bijgewerkt 2026-09-28T01:29:37Z. Citeer vrij, met bronvermelding en een link naar hartvaat.nl (de url van het record). Samenvattingen zijn redactioneel werk van HartVaat; de oorspronkelijke publicaties blijven van hun uitgevers (doi). Geen medisch advies.