Value of serum albumin, age, serum creatinine, and left ventricular ejection fraction for the assessment of 4-year mortality risk in patients with acute myocardial infarction: parsimonious and better performed
Ge, Z.-Y.; He, Y.; Jiang, T.-B.; Tao, J.-Y.; He, Y.-M.
Show abstract
AimsMortality from acute myocardial infarction (AMI) remains substantial. The current study is aimed at developing a novel simple and easy-to-use risk score for AMI. MethodsThe CatLet extended validation trial (ChiCTR2000033730) and the CatLet validation trial (ChiCTR-POC-17013536), both being registered with chictr.org, served as the derivation and validation datasets, respectively. The derivation dataset included 1018 patients, and the validation dataset included 308 ones. They all suffered from AMI and underwent percutaneous intervention (PCI). The 4-year follow-up was 97% completed for the derivation dataset, and 100% completed for the validation dataset. The endpoint was all-cause death. Lasso regression analysis was used for covariate selection and coefficient estimation. ResultsOf 26 candidate predictor variables, four strongest predictors for 4-year mortality were included in the BACEF score (serum albumin, age, serum creatinine, and LVEF). This score was well calibrated and yielded an AUC (95%CI) statistics of 0.84(0.80-0.87) in internal validation, 0.89(0.83-0.95) in internal-external (temporal) validation, and 0.83(0.77-0.89) in external validation. Notably, it outperformed the ACEF, ACEFII, GRACE risk scores (0.83(0.77-0.89) vs 0.81(0.75-0.88); 0.83(0.77-0.89) vs 0.79(0.73-0.86); and 0.83(0.77-0.89) vs 0.79(0.72-0.86), respectively). ConclusionsA simple risk score for 4-year mortality risk stratification was developed, extensively validated, and calibrated in patients with AMI. This novel BACEF score outperformed the ACEF, ACEFII, and GRACE scores and may be a useful risk stratification tool for patients with AMI. One-sentence summaryA novel simple risk score with an acronym of BACEF, including only four risk factors of serum albumin, age, serum creatinine, and LVEF, has been developed, and outperformed the ACEF, ACEFII, and GRACE scores in terms of four-year mortality prediction for patients with acute myocardial infarction. Take-home figure O_FIG O_LINKSMALLFIG WIDTH=198 HEIGHT=200 SRC="FIGDIR/small/22278501v1_ufig1.gif" ALT="Figure 1"> View larger version (60K): org.highwire.dtl.DTLVardef@73de32org.highwire.dtl.DTLVardef@100ba64org.highwire.dtl.DTLVardef@cd0a1corg.highwire.dtl.DTLVardef@152c203_HPS_FORMAT_FIGEXP M_FIG C_FIG
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Predicting long-term prognosis after percutaneous coronary intervention in patients with acute coronary syndromes: a prospective nested case-control analysis for county-level health services 97%
- Development and Validation of a Nomogram for Predicting Survival in Patients With Cardiogenic Shock 96%
- Impact of cardiac rehabilitation and treatment compliance after ST-segment elevation myocardial infarction (STEMI) in France, the STOP SCA+ study 95%
Similar papers in this journal
- Utility of the CHADS-P 2 A 2 RC score for estimating net adverse clinical events in chronic coronary syndrome patients without atrial fibrillation: insights from the CLIDAS-PCI 97%
- Psychosocial distress and health status as risk factors for ten-year major adverse cardiac events and mortality in patients with non-obstructive coronary artery disease 96%
- Temporal Variations in Ischemic and Bleeding Event Risks after Acute Coronary Syndrome during Dual Antiplatelet Therapy 96%
Similar papers in this journal
- Age-stratified Prevalence and Relative Prognostic Significance of Traditional Atherosclerotic Risk Factors: A Report from the Nationwide Registry of Percutaneous Coronary Interventions in Japan 96%
- Treatment of Slow-flow After Primary Percutaneous Coronary Intervention With Flow-mediated Hyperemia. The Randomized RAIN-FLOW Study 95%
- Prognostic Value of Patient-Reported Outcomes in Predicting Long-term Mortality after Transcatheter Aortic Valve Replacement (TAVR) 94%
Similar papers in this journal
- Heart Rate n-Variability (HRnV) and Its Application to Risk Stratification of Chest Pain Patients in the Emergency Department 95%
- Combining Genetic Proxies of Drug Targets and Time-to-event analyses From Longitudinal Observational Data To Identify Target Patient Populations 95%
- Postoperative glycemic variability as a predictor for one-year mortality following coronary artery bypass grafting: A retrospective cohort study 94%
Similar papers in this journal
- Deep Learning-based Prediction of Early Cerebrovascular Events after Transcatheter Aortic Valve Replacement 96%
- Metabolomic profile for understanding heart failure classifications 95%
- Can machine learning improve risk prediction of incident hypertension? An internal method comparison and external validation of the Framingham risk model using HUNT Study data 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.