Clin Res Cardiol (2023). https://doi.org/10.1007/s00392-023-02180-w |
||
Prognostic utility of a multibiomarker panel in a contemporary cohort of patients with suspected myocardial infarction | ||
B. Toprak1, J. Weimann1, J. Lehmacher1, T. Hartikainen2, P. Haller1, A. Schock1, M. Karakas3, T. Renné4, T. Zeller1, D. Westermann2, S. Blankenberg1, R. Twerenbold1, N. A. Sörensen1, J. T. Neumann1, für die Studiengruppe: BACC | ||
1Klinik für Kardiologie, Universitäres Herz- und Gefäßzentrum Hamburg, Hamburg; 2Klinik für Kardiologie und Angiologie, Universitäts-Herzzentrum Freiburg / Bad Krozingen, Bad Krozingen; 3Klinik für Intensivmedizin, Universitätsklinikum Hamburg-Eppendorf, Hamburg; 4Institut für Klinische Chemie und Laboratoriumsmedizin, Universitätsklinikum Hamburg-Eppendorf, Hamburg; | ||
Introduction: Rapid and accurate evaluation of patients presenting with suspected myocardial infarction (MI) to the emergency department (ED) is crucial. Despite the routine use of circulating biomarkers, among which high-sensitivity cardiac troponin currently dictates diagnostic protocols in chest pain patients, it still remains unclear which biomarkers are of highest utility for prognostic purposes in this patient collective. Purpose: Therefore, we sought to investigate the prognostic utility of a multibiomarker panel with 29 different biomarkers in a contemporary cohort of patients with suspected MI by using a machine learning based approach. Methods: The multibiomarker panel was measured in stored blood samples that were collected directly at admission from 748 prospectively enrolled patients who presented to the ED of a German tertiary care center with symptoms suggestive of MI between 2013 and 2017. Biomarker values were log transformed to achieve a near-normal distribution. Incident major cardiovascular events (MACE) were subsumed as the composite of cardiovascular death, non-fatal MI (excluding index events), revascularization and cardiac rehospitalization within 1 year after admission. The selection of the best multimarker model, adjusted for age and sex, was performed using Least Absolute Shrinkage and Selection Operator (LASSO) with 5-fold cross-validation.The independent and additive utility of LASSO-selected biomarkers was compared to a clinical reference model (including age, sex, systolic blood pressure, hyperlipoproteinemia, current smoker and diabetes status) and the Global Registry of Acute Coronary Events (GRACE) Score, respectively. Results: Out of 748 patients with available multibiomarker panel, 138 (18.5%) were diagnosed with MI. Median age at admission was 64 (interquartile range [IQR] 50-75) years in the overall cohort, 63.1% were male. At 1 year of follow-up, 160 cases of incident MACE were documented. 16 of the investigated 29 biomarkers were significantly associated with 1-year MACE, amongst which NT-proBNP was the strongest predictor (hazard ratio [HR] per standard deviation [SD] 1.74, 95% confidence interval [CI] 1.44-2.09, p<0.0001; Figure 1). Using LASSO, three biomarkers including NT-proBNP (HR per SD 1.24), Apo A-I (HR per SD 0.98) and with KIM-1 (HR per SD 1.06) were identified as independent predictors of 1-year MACE. The discriminative ability of the LASSO-selected multibiomarker model (bootstrap-corrected C-index 0.63) was rather moderate. Adding the selected biomarkers to the clinical reference model (C-index 0.617) and the GRACE Score (C-index 0.629), however, led to a marked improvement of model performances (C-indices 0.664 and 0.669, respectively) and reclassification yields (category-free Net reclassification improvement 0.41, 95% CI 0.24-0.60 and 0.35, 95% CI 0.17-0.52, respectively). Conclusion: Among 29 biomarkers depicting different pathophysiological axes, NT-proBNP, Apo A-I and KIM-1 emerged as the strongest independent predictors of 1-year MACE. Their routine assessment and integration into clinical risk prediction models may improve personalized risk stratification in patients with symptoms suggestive of MI. |
||
https://dgk.org/kongress_programme/jt2023/aP1703.html |