Machine learning to define phenotypes and outcomes of patients hospitalized for heart failure with preserved ejection fraction: Findings from ASCEND-HF - 06/12/22
Résumé |
Background |
Heart Failure with Preserved Ejection Fraction (HFpEF) is a heterogenous disease with few therapies proven to provide clinical benefit. Machine learning can characterize distinct phenotypes and compare outcomes among patients with HFpEF who are hospitalized for acute HF.
Methods |
We applied hierarchical clustering using demographics, comorbidities, and clinical data on admission to identify distinct clusters in hospitalized HFpEF (ejection fraction >40%) in the ASCEND-HF trial. We separately applied a previously developed latent class analysis (LCA) clustering method and compared in-hospital and long-term outcomes across cluster groups.
Results |
Of 7141 patients enrolled in the ASCEND-HF trial, 812 (11.4%) were hospitalized for HFpEF and met the criteria for complete case analysis. Hierarchical Cluster 1 included older women with atrial fibrillation (AF). Cluster 2 had elevated resting blood pressure. Cluster 3 had young men with obesity and diabetes. Cluster 4 had low resting blood pressure. Mortality at 180 days was lowest among Cluster 3 (KM event-rate 6.2 [95% CI: 3.5, 10.9]) and highest among Cluster 4 (18.8 [14.6, 24.0], P < .001). Twenty four-hour urine output was higher in Cluster 3 (2700 mL [1800, 3975]) than Cluster 4 (2100 mL [1400, 3055], P < .001). LCA also identified four clusters: A) older White or Asian women, B) younger men with few comorbidities, C) older individuals with AF and renal impairment, and D) patients with obesity and diabetes. Mortality at 180 days was lowest among LCA Cluster B (KM event-rate 5.5 [2.0, 10.3]) and highest among LCA Cluster C (26.3 [19.2, 35.4], P < .001).
Conclusions |
In patients hospitalized for HFpEF, cluster analysis demonstrated distinct phenotypes with differing clinical profiles and outcomes.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Hierarchical clustering identified four distinct phenotypes of patients hospitalized with Heart Failure with Preserved Ejection Fraction (HFpEF) in the ASCEND-HF study population. Cluster 1 was older with high rates of atrial fibrillation, Cluster 2 had a high blood pressure and low heart rate, Cluster 3 was had patients with obesity and diabetes, and Cluster 4 had a low blood pressure, high comorbidity burden, and high heart rate. Risk of 180-day mortality was greatest in Cluster 4 and lowest in Cluster 3.
Plan
| Abbreviated Title: Machine Learning Acute HFpEF Phenotypes |
Vol 254
P. 112-121 - décembre 2022 Retour au numéro
Article précédent
- Association between nitric oxide synthase 3 genetic variant and acute kidney injury following pediatric cardiac surgery
- Sandra Kikano, Joseph Breeyear, Ida Aka, Todd L. Edwards, Sara L. Van Driest, Prince J. Kannankeril
- Development of a unified national database of primary percutaneous coronary intervention centers with co-located emergency departments, 2020
- Darya M. Herscovici, Krislyn M. Boggs, Rebecca E. Cash, Janice A. Espinola, Ashley F. Sullivan, Kohei Hasegawa, John T. Nagurney, Carlos A. Camargo
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?