A novel methodological framework for the analysis of health trajectories and survival outcomes in heart failure patients

Juliette Murris (1, 2) , Tristan Amadei (3) , Tristan Kirscher (3) , Antoine Klein (3) , Anne-Isabelle Tropeano (4) , Sandrine Katsahian (1, 5, 6)

1 HeKA - Health data- and model- driven Knowledge Acquisition
2 Centre de R&D Pierre Fabre - Centre de Recherche Pierre Fabre
3 ENSAE - Ecole Nationale de la Statistique et de l'Analyse Economique
4 Département d’informatique médicale, de biostatistique et de santé publique
5 CIC 1418 - CIC - HEGP
6 Unité d’épidémiologie et de recherche clinique [Hôpital européen Georges Pompidou]

Heart failure (HF) contributes to circa 200,000 annual hospitalizations in France. With the increasing age of HF patients, elucidating the specific causes of inpatient mortality became a public health problematic. We introduce a novel methodological framework designed to identify prevalent health trajectories and investigate their impact on death. The initial step involves applying sequential pattern mining to characterize patients' trajectories, followed by an unsupervised clustering algorithm based on a new metric for measuring the distance between hospitalization diagnoses. Finally, a survival analysis is conducted to assess survival outcomes. The application of this framework to HF patients from a representative sample of the French population demonstrates its methodological significance in enhancing the analysis of healthcare trajectories.

Mots clés: Methodology (stat.ME); FOS: Computer and information sciences

Domaines: Méthodologie [stat.ME]

Juliette Murris, Tristan Amadei, Tristan Kirscher, Antoine Klein, Anne-Isabelle Tropeano, et al.. A novel methodological framework for the analysis of health trajectories and survival outcomes in heart failure patients. ICLR 2024 Workshop on Learning from Time Series For Health, May 2024, Vienna, Austria. ⟨10.48550/arXiv.2403.03138⟩. ⟨hal-04505220v2⟩