The logistic regression machine learning model predicted all-cause death within 180 days after discharge with an AUC of 0.869, significantly outperforming the GRACE risk score (P < 0.05) in adults with NSTEMI.
Observational (n=4,845)
Yes
Does a machine learning-based predictive model improve prognostic assessment for adverse clinical outcomes compared to the GRACE risk score in patients with NSTEMI?
A machine learning-based predictive model, particularly using logistic regression, significantly outperforms the traditional GRACE risk score in predicting 180-day all-cause mortality and MACCE in patients with NSTEMI.
Effect estimate: AUC 0.869 for the logistic regression ML model; AUC comparison significant vs GRACE risk score, P<0.05
Absolute Event Rate: 3.1% vs 4.1%
p-value: p=<0.05
The machine learning-based prognosis model significantly improves the performance of the current risk assessment model for predicting adverse clinical outcomes in NSTEMI patients.
Rao et al. (Mon,) conducted a observational in Adults aged 18 and older with acute non-ST-segment elevation myocardial infarction (NSTEMI) who survived hospitalization and completed 180-day follow-up after discharge (n=4,845). Machine learning-based predictive model including clinical variables such as coronary artery lesions, reperfusion strategies, laboratory tests and echocardiography parameters vs. GRACE risk score was evaluated on All-cause mortality within 180 days after discharge (AUC 0.869 for the logistic regression ML model; AUC comparison significant vs GRACE risk score, P<0.05, p=<0.05). The logistic regression machine learning model predicted all-cause death within 180 days after discharge with an AUC of 0.869, significantly outperforming the GRACE risk score (P < 0.05) in adults with NSTEMI.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: