Machine learning to optimize the diagnostic performance of natriuretic peptides for acute heart failure across age groups
N-terminal pro-B-type natriuretic peptide (NT-proBNP) concentrations are influenced by age, which may influence the diagnostic performance of this peptide. Machine learning approaches incorporating NT-proBNP and age as continuous measures may have improved diagnostic performance.We pooled individual...
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Langue: | anglais |
| Publié: |
February 2026
|
| In: |
ESC heart failure
Year: 2026, Volume: 13, Numéro: 1, Pages: 1-10 |
| ISSN: | 2055-5822 |
| DOI: | 10.1093/eschf/xvaf006 |
| Accès en ligne: | Verlag, kostenfrei, Volltext: https://doi.org/10.1093/eschf/xvaf006
|
| Notes sur l'auteur: | Daniel Perez Vicencio, Dimitrios Doudesis, Alexander J.F. Thurston, Camille Chenevier-Gobeaux, Yann-Erick Claessens, Pedro Lopez Ayala, Maria Belkin, Desiree Wussler, Christopher deFilippi, Stephen Seliger, Gordon Moe, Carlos Fernando, Antoni Bayes-Genis, Yigal Pinto, Hanna K. Gaggin, Jan C. Wiemer, Martin Möckel, Joost H.W. Rutten, Luna Gargani, Nicola R. Pugliese, Christopher Pemberton, Irwani Ibrahim, Alfons Gegenhuber, Thomas Mueller, Michael Neumaier, Michael Behnes, Ibrahim Akin, Michele Bombelli, Guido Grassi, Peiman Nazerian, Giovanni Albano, Philipp Bahrmann, A. Mark Richards, John J.V. McMurray, Christian Mueller, James L. Januzzi, Nicholas L. Mills, and Kuan Ken Lee, on behalf of the CoDE-HF investigators |
| Résumé: | N-terminal pro-B-type natriuretic peptide (NT-proBNP) concentrations are influenced by age, which may influence the diagnostic performance of this peptide. Machine learning approaches incorporating NT-proBNP and age as continuous measures may have improved diagnostic performance.We pooled individual patient-level data for 10 369 patients [median age 73 years (25th-75th percentile: 59-82)] with suspected acute heart failure across fourteen studies. The diagnostic performance of guideline-recommended NT-proBNP thresholds (uniform rule-out threshold of 300 pg/mL and age-stratified rule-in thresholds of 450, 900, and 1800 pg/mL for patients <50, 50-75, and >75 years, respectively) and the Collaboration for the Diagnosis and Evaluation of Heart Failure (CoDE-HF) machine learning model were evaluated using random effects meta-analysis across age groups.Overall, 43.9% (4549/10 369) of patients had an adjudicated diagnosis of acute heart failure. The negative predictive value (NPV) of the rule-out threshold of 300 pg/mL was lower in older patients [NPV 88.7% (confidence interval (CI) 84.2-92.1%) in patients ≥80 years vs 98.9% (97.6-99.5%) <50 years]. Conversely, the positive predictive value (PPV) of age-stratified rule-in thresholds was lower in younger patients [PPV 62.0% (56.2-67.5%) in those <50 years vs 79.6% (70.7-86.3%) ≥80 years]. CoDE-HF was more accurate than guideline-recommended thresholds across all age groups, with NPV and PPV ranging from 96.4% to 99.5% (93.8-99.8% CIs) and 81.1% to 84.2% (74.7-90.4% CIs), respectively.The diagnostic performance of guideline-recommended thresholds of NT-proBNP varies significantly with age. A decision-support tool incorporating NT-proBNP with age as a continuous variable provides a more consistent and accurate approach. |
|---|---|
| Description: | Online veröffentlicht: 8. Januar 2026 Gesehen am 05.03.2026 |
| Description matérielle: | Online Resource |
| ISSN: | 2055-5822 |
| DOI: | 10.1093/eschf/xvaf006 |