TY - JOUR
T1 - Machine learning to optimize use of natriuretic peptides in the diagnosis of acute heart failure
AU - on behalf of the CoDE-HF investigators
AU - Doudesis, Dimitrios
AU - Lee, Kuan Ken
AU - Anwar, Mohamed
AU - Singer, Adam J.
AU - Hollander, Judd E.
AU - Chenevier-Gobeaux, Camille
AU - Claessens, Yann Erick
AU - Wussler, Desiree
AU - Weil, Dominic
AU - Kozhuharov, Nikola
AU - Strebel, Ivo
AU - Sabti, Zaid
AU - Defilippi, Christopher
AU - Seliger, Stephen
AU - Mesquita, Evandro Tinoco
AU - Wiemer, Jan C.
AU - Möckel, Martin
AU - Coste, Joel
AU - Jourdain, Patrick
AU - Kimiaki, Komukai
AU - Yoshimura, Michihiro
AU - Ibrahim, Irwani
AU - Ooi, Shirley Beng Suat
AU - Kuan, Win Sen
AU - Gegenhuber, Alfons
AU - Mueller, Thomas
AU - Hanon, Olivier
AU - Vidal, Jean Sébastien
AU - Cameron, Peter
AU - Lam, Louisa
AU - Freedman, Ben
AU - Chung, Tommy
AU - Collins, Sean P.
AU - Lindsell, Christopher J.
AU - Newby, David E.
AU - Japp, Alan G.
AU - Shah, Anoop S.V.
AU - Villacorta, Humberto
AU - Richards, A. Mark
AU - Mcmurray, John J.V.
AU - Mueller, Christian
AU - Januzzi, James L.
AU - Mills, Nicholas L.
AU - Moe, Gordon
AU - Fernando, Carlos
AU - Gaggin, Hanna K.
AU - Bayes-Genis, Antoni
AU - Van Kimmenade, Roland R.J.
AU - Pinto, Yigal
AU - Rutten, Joost H.W.
N1 - Publisher Copyright:
© 2025 The Author(s). Published by Oxford University Press on behalf of the European Society of Cardiology.
PY - 2025/8/1
Y1 - 2025/8/1
N2 - Aims B-type natriuretic peptide (BNP) and mid-regional pro-atrial natriuretic peptide (MR-proANP) testing are guideline-recommended to aid in the diagnosis of acute heart failure. Nevertheless, the diagnostic performance of these biomarkers is uncertain. Methods and results We performed a systematic review and individual patient-level data meta-analysis to evaluate the diagnostic performance of BNP and MR-proANP. We subsequently developed and externally validated a decision-support tool called CoDE-HF that combines natriuretic peptide concentrations with clinical variables using machine learning to report the probability of acute heart failure. Fourteen studies from 12 countries provided individual patient-level data in 8493 patients for BNP and 3899 patients for MR-proANP, in whom, 48.3% (4105/8493) and 41.3% (1611/3899) had an adjudicated diagnosis of acute heart failure, respectively. The negative predictive value (NPV) of guideline-recommended thresholds for BNP (100 pg/mL) and MR-proANP (120 pmol/L) was 93.6% (95% confidence interval 88.4-96.6%) and 95.6% (92.2-97.6%), respectively, whilst the positive predictive value (PPV) was 68.8% (62.9-74.2%) and 64.8% (56.3-72.5%). Significant heterogeneity in the performance of these thresholds was observed across important subgroups. CoDE-HF was well calibrated with excellent discrimination in those without prior acute heart failure for both BNP and MR-proANP [area under the curve of 0.914 (0.906-0.921) and 0.929 (0.919-0.939), and Brier scores of 0.110 and 0.094, respectively]. CoDE-HF with BNP and MR-proANP identified 30% and 48% as low-probability [NPV of 98.5% (97.1-99.3%) and 98.5% (97.7-99.0%)], and 30% and 28% as high-probability [PPV of 78.6% (70.4-85.0%) and 75.1% (70.9-78.9%)], respectively, and performed consistently across subgroups. Conclusion The diagnostic performance of guideline-recommended BNP and MR-proANP thresholds for acute heart failure varied significantly across patient subgroups. A decision-support tool that combines natriuretic peptides and clinical variables was more accurate and supports more individualized diagnosis.
AB - Aims B-type natriuretic peptide (BNP) and mid-regional pro-atrial natriuretic peptide (MR-proANP) testing are guideline-recommended to aid in the diagnosis of acute heart failure. Nevertheless, the diagnostic performance of these biomarkers is uncertain. Methods and results We performed a systematic review and individual patient-level data meta-analysis to evaluate the diagnostic performance of BNP and MR-proANP. We subsequently developed and externally validated a decision-support tool called CoDE-HF that combines natriuretic peptide concentrations with clinical variables using machine learning to report the probability of acute heart failure. Fourteen studies from 12 countries provided individual patient-level data in 8493 patients for BNP and 3899 patients for MR-proANP, in whom, 48.3% (4105/8493) and 41.3% (1611/3899) had an adjudicated diagnosis of acute heart failure, respectively. The negative predictive value (NPV) of guideline-recommended thresholds for BNP (100 pg/mL) and MR-proANP (120 pmol/L) was 93.6% (95% confidence interval 88.4-96.6%) and 95.6% (92.2-97.6%), respectively, whilst the positive predictive value (PPV) was 68.8% (62.9-74.2%) and 64.8% (56.3-72.5%). Significant heterogeneity in the performance of these thresholds was observed across important subgroups. CoDE-HF was well calibrated with excellent discrimination in those without prior acute heart failure for both BNP and MR-proANP [area under the curve of 0.914 (0.906-0.921) and 0.929 (0.919-0.939), and Brier scores of 0.110 and 0.094, respectively]. CoDE-HF with BNP and MR-proANP identified 30% and 48% as low-probability [NPV of 98.5% (97.1-99.3%) and 98.5% (97.7-99.0%)], and 30% and 28% as high-probability [PPV of 78.6% (70.4-85.0%) and 75.1% (70.9-78.9%)], respectively, and performed consistently across subgroups. Conclusion The diagnostic performance of guideline-recommended BNP and MR-proANP thresholds for acute heart failure varied significantly across patient subgroups. A decision-support tool that combines natriuretic peptides and clinical variables was more accurate and supports more individualized diagnosis.
KW - Heart failure
KW - Machine learning
KW - Natriuretic peptide
UR - https://www.scopus.com/pages/publications/105013193240
U2 - 10.1093/ehjacc/zuaf051
DO - 10.1093/ehjacc/zuaf051
M3 - Review article
C2 - 40219913
AN - SCOPUS:105013193240
SN - 2048-8726
VL - 14
SP - 474
EP - 488
JO - European Heart Journal: Acute Cardiovascular Care
JF - European Heart Journal: Acute Cardiovascular Care
IS - 8
ER -