Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 51 min ago
Peer-reviewedCC BY-NC-ND 4.0Nature Communications

Multimodal data-driven clustering analysis of heart failure patients identifies two distinct patterns of heart failure with preserved ejection fraction: Results from the PACIFIC-PRESERVED study

  • Jean-Sébastien Hulot1,2
  • Pierre-Yves Hervé3
  • Nicolas Girerd4,5
  • Frédérique Chézalviel-Guilbert6
  • Philip Janiak6
  • Pierre Boutouyrie7,8
  • Jean-Joseph Christophe9
  • Ariel Cohen10
  • Thibaud Damy11
  • Liliane Berkani12
  • Kevin Duarte4
  • Caroline Fraslon6
13 more authors
  • Hüseyin Firat13
  • Olivier Hanon14
  • Richard Isnard15
  • Guillaume Jondeau16
  • Elie Mousseaux7,17
  • Mathieu Pernot18
  • Andrea Ruiz-Velasco7
  • Alfonso Sartorius19
  • Benoit Tyl19
  • Gilles Soulat7,17
  • Philippe Boutinaud3
  • Damien Logeart20
  • PACIFIC consortium
20 affiliations
  1. 1Université Paris Cité, INSERM, PARCC, Paris, France. [email protected].
  2. 2CIC1418 and DMU CARTE, AP-HP, Hôpital Européen Georges-Pompidou, Paris, France. [email protected].
  3. 3Fealinx, 42 route du Pont de Chêne, Francheville, France.
  4. 4CHRU de Nancy, Université de Lorraine, INSERM, Centre d'Investigations Cliniques Plurithématique 1433, Nancy, France.
  5. 5INI-CRCT (Cardiovascular and Renal Clinical Trialists) F-CRIN Network, Nancy, France.
  6. 6Sanofi R&D, Gentilly, France.
  7. 7Université Paris Cité, INSERM, PARCC, Paris, France.
  8. 8Pharmacology and DMU CARTE, AP-HP, Hôpital Européen Georges-Pompidou, Paris, France.
  9. 9CASIS - CArdiac Simulation & Imaging Software, Quetigny, France.
  10. 10Cardiology, AP-HP, Hôpital Saint-Antoine, Sorbonne Université, ICAN 1166, Paris, France.
  11. 11Cardiology, AP-HP, Hôpital Henri Mondor, Créteil, France.
  12. 12Clinical research unit, AP-HP, Hôpital Européen Georges-Pompidou, Paris, France.
  13. 13Firalis, Huningue, France.
  14. 14UMR 1144, Université Paris Cité, Department of Geriatrics, AP-HP, Hôpital Broca, Paris, France.
  15. 15Cardiology, AP-HP, Hôpital Pitié-Salpêtrière, Paris, France.
  16. 16Cardiology, AP-HP, Hôpital Bichat, Paris, France.
  17. 17Cardiac Imaging Radiology, AP-HP, Hôpital Européen Georges-Pompidou, Paris, France.
  18. 18Physics for Medicine Paris, INSERM U1273, ESPCI Paris, PSL University, CNRS FRE 2031, Paris, France.
  19. 19Servier R&D, Suresnes, France.
  20. 20Université Paris Cité, AP-HP, Hôpital Lariboisière, Paris, France.
Read full textPDFDOICite

Abstract

Heart failure with preserved ejection fraction (HFpEF) accounts for over half of heart failure cases but remains poorly defined due to its clinical heterogeneity. In the prospective PACIFIC-Preserved cohort (NCT04189029, n = 155), we applied multimodal deep phenotyping, including high-throughput proteomics, and unsupervised machine learning to identify biologically distinct HFpEF subgroups. Multiview clustering revealed two major HFpEF phenogroups: PEF1, characterized by inflammatory signaling, TNF receptor activation, cardio-skeletal injury, and greater renal dysfunction; and PEF2, marked by endothelial stress and milder perturbations. Conventional diagnostics alone could not reliably distinguish these subgroups, but a multimodal classifier integrating clinical, imaging, and proteomic variables achieved high predictive accuracy (F1-score 0.87). External validation in the MEDIA-DHF cohort (n = 456) confirmed that PEF1 was independently associated with adverse outcomes (adjusted HR 2.27, 95% CI 1.04-4.94). These findings establish a classifier-driven, biologically informed stratification of HFpEF, providing a framework for precision medicine in heart failure.

Related

  1. Machine learning clustering of multidimensional clinical features identifies four prognostically distinct sepsis subtypes
    Rui Zhang, Yingli Zhang, Xirou Wu +6
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthCrossref
  2. Measurement-level clustering of ligamentum flavum thickness identifies distinct phenotypes associated with lumbar lordosis in adult spinal deformity: a proof-of-concept study.
    Dylan Glaser, Ahmad K AlMekkawi, Ashlesha Bhojane +5
    Frontiers in surgeryPeer-reviewedCC BYFull textSurgery & anaesthesiaEurope PMCPMC
  3. Latent class analysis identifies three biologically distinct phenotypes among patients undergoing endovascular thrombectomy: a derivation and temporal validation study
    Li-Li Yang, Chao Chen, Li-Li Sun +2
    Frontiers in NeurologyPeer-reviewedCC BY 4.0Full textEpidemiology & public healthCrossrefEurope PMCEurope PMCPMC
  4. Novel clustering approach to understanding distinct phenotypes of patients with systemic sclerosis.
    Dinesh Khanna, Mario Ehlers, Lizette Moros +5
    Journal of scleroderma and related disordersPeer-reviewedCC BY-NCFull textGeneral medicineEurope PMCPMC
  5. Neutrophil-to-Lymphocyte Ratio Identifies a Pulmonary Vascular High-Risk Phenotype in Heart Failure with Preserved Ejection Fraction
    M. Bril, E. Parnasa, A. Sufian +3
    medRxivPreprintAll rights reservedFull textCardiovascular medicinemedRxiv

Cite

BibTeXRIS
BibTeX
@article{hulot2026multimodal,
  title = {{Multimodal data-driven clustering analysis of heart failure patients identifies two distinct patterns of heart failure with preserved ejection fraction: Results from the PACIFIC-PRESERVED study}},
  author = {Jean-Sébastien Hulot and Pierre-Yves Hervé and Nicolas Girerd and Frédérique Chézalviel-Guilbert and Philip Janiak and Pierre Boutouyrie and Jean-Joseph Christophe and Ariel Cohen and Thibaud Damy and Liliane Berkani and Kevin Duarte and Caroline Fraslon and Hüseyin Firat and Olivier Hanon and Richard Isnard and Guillaume Jondeau and Elie Mousseaux and Mathieu Pernot and Andrea Ruiz-Velasco and Alfonso Sartorius and Benoit Tyl and Gilles Soulat and Philippe Boutinaud and Damien Logeart and PACIFIC consortium},
  journal = {Nature Communications},
  year = {2026},
  month = sep,
  doi = {10.1038/s41467-026-77642-6},
  url = {https://hal.univ-lorraine.fr/hal-05801681v1},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Multimodal data-driven clustering analysis of heart failure patients identifies two distinct patterns of heart failure with preserved ejection fraction: Results from the PACIFIC-PRESERVED study
AU  - Jean-Sébastien Hulot
AU  - Pierre-Yves Hervé
AU  - Nicolas Girerd
AU  - Frédérique Chézalviel-Guilbert
AU  - Philip Janiak
AU  - Pierre Boutouyrie
AU  - Jean-Joseph Christophe
AU  - Ariel Cohen
AU  - Thibaud Damy
AU  - Liliane Berkani
AU  - Kevin Duarte
AU  - Caroline Fraslon
AU  - Hüseyin Firat
AU  - Olivier Hanon
AU  - Richard Isnard
AU  - Guillaume Jondeau
AU  - Elie Mousseaux
AU  - Mathieu Pernot
AU  - Andrea Ruiz-Velasco
AU  - Alfonso Sartorius
AU  - Benoit Tyl
AU  - Gilles Soulat
AU  - Philippe Boutinaud
AU  - Damien Logeart
AU  - PACIFIC consortium
PY  - 2026
DA  - 2026/09/15
JO  - Nature Communications
DO  - 10.1038/s41467-026-77642-6
UR  - https://hal.univ-lorraine.fr/hal-05801681v1
AB  - Heart failure with preserved ejection fraction (HFpEF) accounts for over half of heart failure cases but remains poorly defined due to its clinical heterogeneity. In the prospective PACIFIC-Preserved cohort (NCT04189029, n = 155), we applied multimodal deep phenotyping, including high-throughput proteomics, and unsupervised machine learning to identify biologically distinct HFpEF subgroups. Multiview clustering revealed two major HFpEF phenogroups: PEF1, characterized by inflammatory signaling, TNF receptor activation, cardio-skeletal injury, and greater renal dysfunction; and PEF2, marked by endothelial stress and milder perturbations. Conventional diagnostics alone could not reliably distinguish these subgroups, but a multimodal classifier integrating clinical, imaging, and proteomic variables achieved high predictive accuracy (F1-score 0.87). External validation in the MEDIA-DHF cohort (n = 456) confirmed that PEF1 was independently associated with adverse outcomes (adjusted HR 2.27, 95% CI 1.04-4.94). These findings establish a classifier-driven, biologically informed stratification of HFpEF, providing a framework for precision medicine in heart failure.
SN  - 2041-1723
SN  - 2041-1723
ER  -