TY - JOUR
T1 - Predicting new-onset heart failure hospitalization of patients with atrial fibrillation
T2 - development and external validations of a risk score
AU - Ishii, Kai
AU - Matsue, Yuya
AU - Miyauchi, Katsumi
AU - Miyazaki, Sakiko
AU - Hayashi, Hidemori
AU - Nishizaki, Yuji
AU - Nojiri, Shuko
AU - Saito, Yuki
AU - Nagashima, Koichi
AU - Okumura, Yasuo
AU - Daida, Hiroyuki
AU - Minamino, Tohru
N1 - Publisher Copyright:
© The Author(s) 2022. Published by Oxford University Press on behalf of the European Society of Cardiology. All rights reserved.
PY - 2023/11/1
Y1 - 2023/11/1
N2 - Aim Atrial fibrillation (AF) is a well-known risk factor for heart failure (HF). We sought to develop and externally validate a risk model for new-onset HF admission in patients with AF and those without a history of HF. Methods and results Using two multicentre, prospective, observational AF registries, RAFFINE (2857 patients, derivation cohort) and SAKURA (2516 patients without a history of HF, validation cohort), we developed a risk model by selecting variables with regularized regression and weighing coefficients by Cox regression with the derivation cohort. External validity testing was used for the validation cohort. Overall, 148 (5.2%) and 104 (4.1%) patients in the derivation and validation cohorts, respectively, developed HF during median follow-ups of 1396 (interquartile range [IQR]: 1078–1820) and 1168 (IQR: 844–1309) days, respectively. In the derivation cohort, age, haemoglobin, serum creatinine, and log-transformed brain natriuretic peptide were identified as potential risk factors for HF development. The risk model showed good discrimination and calibration in both derivations (area under the curve [AUC]: 0.80 [95% confidence interval (CI) 0.76–0.84]; Hosmer–Lemeshow, P = 0.257) and validation cohorts (AUC: 0.78 [95%CI 0.74–0.83]; Hosmer–Lemeshow, P = 0.475). Conclusion The novel risk model with four readily available clinical characteristics and biomarkers performed well in predicting new-onset HF admission in patients with AF.
AB - Aim Atrial fibrillation (AF) is a well-known risk factor for heart failure (HF). We sought to develop and externally validate a risk model for new-onset HF admission in patients with AF and those without a history of HF. Methods and results Using two multicentre, prospective, observational AF registries, RAFFINE (2857 patients, derivation cohort) and SAKURA (2516 patients without a history of HF, validation cohort), we developed a risk model by selecting variables with regularized regression and weighing coefficients by Cox regression with the derivation cohort. External validity testing was used for the validation cohort. Overall, 148 (5.2%) and 104 (4.1%) patients in the derivation and validation cohorts, respectively, developed HF during median follow-ups of 1396 (interquartile range [IQR]: 1078–1820) and 1168 (IQR: 844–1309) days, respectively. In the derivation cohort, age, haemoglobin, serum creatinine, and log-transformed brain natriuretic peptide were identified as potential risk factors for HF development. The risk model showed good discrimination and calibration in both derivations (area under the curve [AUC]: 0.80 [95% confidence interval (CI) 0.76–0.84]; Hosmer–Lemeshow, P = 0.257) and validation cohorts (AUC: 0.78 [95%CI 0.74–0.83]; Hosmer–Lemeshow, P = 0.475). Conclusion The novel risk model with four readily available clinical characteristics and biomarkers performed well in predicting new-onset HF admission in patients with AF.
KW - Atrial fibrillation
KW - Heart failure
KW - Machine learning
KW - Prediction model
KW - Risk score
UR - http://www.scopus.com/inward/record.url?scp=85177496035&partnerID=8YFLogxK
U2 - 10.1093/ehjqcco/qcac085
DO - 10.1093/ehjqcco/qcac085
M3 - Article
C2 - 36542406
AN - SCOPUS:85177496035
SN - 2058-5225
VL - 9
SP - 716
EP - 723
JO - European Heart Journal - Quality of Care and Clinical Outcomes
JF - European Heart Journal - Quality of Care and Clinical Outcomes
IS - 7
ER -