Machine learning to optimize the diagnostic performance of natriuretic peptides for acute heart failure across age groups
Por:
Vicencio, DP, Doudesis, D, Thurston, AJF, Chenevier-Gobeaux, C, Claessens, YE, Ayala, PL, Belkin, M, Wussler, D, DeFilippi, C, Seliger, S, Moe, G, Fernando, C, Bayes-Genis, A, Pinto, Y, Gaggin, HK, Wiemer, JC, Möckel, M, Rutten, JHW, Gargani, L, Pugliese, NR, Pemberton, C, Ibrahim, I, Gegenhuber, A, Mueller, T, Neumaier, M, Behnes, M, Akin, I, Bombelli, M, Grassi, G, Nazerian, P, Albano, G, Bahrmann, P, Richards, AM, McMurray, JJ, Mueller, C, Januzzi, JL, Mills, NL, Lee, KK and CoDE HF investigators
Publicada:
1 feb 2026
Resumen:
Background and Aims 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. Methods 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. Results 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. Conclusion 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.
Filiaciones:
Vicencio, DP:
Univ Edinburgh, Ctr Cardiovasc Sci, British Heart Fdn, Edinburgh EH16 4SA, Scotland
Univ Edinburgh, Usher Inst, Edinburgh, Scotland
Doudesis, D:
Univ Edinburgh, Ctr Cardiovasc Sci, British Heart Fdn, Edinburgh EH16 4SA, Scotland
Univ Edinburgh, Usher Inst, Edinburgh, Scotland
Thurston, AJF:
Univ Edinburgh, Ctr Cardiovasc Sci, British Heart Fdn, Edinburgh EH16 4SA, Scotland
Chenevier-Gobeaux, C:
Cochin Hosp, Assistance Publ Hop Paris, Dept Biochem, Paris, France
Claessens, YE:
Princess Grace Hosp Ctr, Dept Emergency Med, Monaco, Monaco
Ayala, PL:
Univ Hosp Basel, Cardiovasc Res Inst Basel, Dept Cardiol, Basel, Switzerland
Belkin, M:
Univ Hosp Basel, Cardiovasc Res Inst Basel, Dept Cardiol, Basel, Switzerland
Wussler, D:
Univ Hosp Basel, Cardiovasc Res Inst Basel, Dept Cardiol, Basel, Switzerland
Univ British Columbia, Vancouver Gen Hosp, Dept Cardiol, Vancouver, BC, Canada
DeFilippi, C:
Univ Maryland, Sch Med, Div Cardiol, Baltimore, MD USA
Seliger, S:
Univ Maryland, Sch Med, Div Nephrol, Baltimore, MD USA
Moe, G:
Univ Toronto, St Michaels Hosp, Dept Med, Toronto, ON, Canada
Fernando, C:
Univ Toronto, St Michaels Hosp, Dept Med, Toronto, ON, Canada
:
Hosp Univ Germans Trias I Pujol, Heart Inst, Cardiol Dept, CIBERCV, Badalona, Spain
Pinto, Y:
Univ Amsterdam, Dept Expt Cardiol, Amsterdam Cardiovasc Sci, Amsterdam, Netherlands
Gaggin, HK:
Harvard Med Sch, Dept Med, Boston, MA USA
Massachusetts Gen Hosp, Div Cardiol, Boston, MA USA
Wiemer, JC:
Thermo Fisher Sci, BRAHMS, Hennigsdorf, Germany
Möckel, M:
Charite Univ Med Berlin, Div Emergency & Acute Med, Chest Pain Units, Campus Mitte & Virchow, Berlin, Germany
Rutten, JHW:
Radboud Univ Nijmegen, Med Ctr, Dept Internal Med, Nijmegen, Netherlands
Gargani, L:
Univ Pisa, Dept Surg Med & Mol Pathol Crit & Care Med, Pisa, Italy
Pugliese, NR:
Univ Pisa, Dept Clin & Expt Med, Pisa, Italy
Pemberton, C:
Univ Otago, Christchurch Heart Inst, Christchurch, New Zealand
Ibrahim, I:
Natl Univ Singapore Hosp, Emergency Med Dept, Singapore, Singapore
Gegenhuber, A:
Krankenhaus Bad Ischl, Dept Internal Med, Bad Ischl, Austria
Mueller, T:
Hosp Voecklabruck, Dept Lab Med, Voecklabruck, Austria
Neumaier, M:
Heidelberg Univ, Univ Med Ctr Mannheim, Inst Clin Chem, Fac Med Mannheim, Mannheim, Germany
Behnes, M:
Heidelberg Univ, Fac Med Mannheim, Univ Med Ctr Mannheim, Dept Med 1, Mannheim, Germany
Akin, I:
Heidelberg Univ, Fac Med Mannheim, Univ Med Ctr Mannheim, Dept Med 1, Mannheim, Germany
Bombelli, M:
Univ Milano Bicocca, Clin Med, Monza, Italy
Grassi, G:
Univ Milano Bicocca, Clin Med, Monza, Italy
Nazerian, P:
Azienda Osped Univ Careggi, Dept Emergency Med, Florence, Italy
Albano, G:
Azienda Osped Univ Careggi, Dept Emergency Med, Florence, Italy
Bahrmann, P:
Friedrich Alexander Univ, Inst Biomed Aging, Nurnberg, Germany
Richards, AM:
Univ Otago, Christchurch Heart Inst, Christchurch, New Zealand
Natl Univ Heart Ctr Singapore, Cardiovasc Res Inst, Singapore, Singapore
McMurray, JJ:
Univ Glasgow, BHF Cardiovasc Res Ctr, Glasgow, Scotland
Mueller, C:
Univ Hosp Basel, Cardiovasc Res Inst Basel, Dept Cardiol, Basel, Switzerland
Januzzi, JL:
Harvard Med Sch, Dept Med, Boston, MA USA
Massachusetts Gen Hosp, Div Cardiol, Boston, MA USA
Mills, NL:
Univ Edinburgh, Ctr Cardiovasc Sci, British Heart Fdn, Edinburgh EH16 4SA, Scotland
Univ Edinburgh, Usher Inst, Edinburgh, Scotland
Lee, KK:
Univ Edinburgh, Ctr Cardiovasc Sci, British Heart Fdn, Edinburgh EH16 4SA, Scotland
Green Submitted, Green Published, gold
|