Risk Factors for Poor Prognosis in Acute Coronary Syndrome Admitted in the Emergency Department: A Retrospective Cohort Study.

BACKGROUND: In the present study, we aimed to identify risk factors of poor prognosis for patients with acute coronary syndrome in the emergency department. METHODS: The study included 2667 patients, who were admitted to the Emergency Department of Chest Pain Center, Fujian Provincial Hospital, due to chest pain from January 1, 2017 to March 31, 2020. Logistic regression was used to identify factors of poor prognosis for patients with ACS in the ED. Receiver operating characteristic (ROC) curve was plotted to assess the performance of the multivariate logistic regression model. Subgroup analysis was used to analyze the difference of SBP in ACS patients with different characteristics. RESULTS: The final analysis included 2667 patients, of whom 2,057 patients (77.8%) had poor prognosis. STEMI (compared with UA) (OR=20.139; 95% CI:12.448-32.581; P < 0.001), NSTEMI (compared with UA) (OR=7.430; 95% CI:5.159-10.700; P < 0.001), respiratory rate ≥20 bpm (compared with <20 bpm) (OR=1.334; 95% CI: 1.060-1.679; P = 0.014), and use of antiplatelets (OR=1.557; 95% CI:1.181-2.053; P = 0.002) was associated with increased likelihood of poor prognosis for ACS patients in ED. SBP ≥140 mmHg (compared with<140mmHg) (OR=0.574; 95% CI: 0.477-0.690; P < 0.001) was associated with decreased likelihood of poor prognosis for ACS patients in the ED. The area under curve (AUC) of the predictive efficacy of logistic regression model was 0.825 (95% CI: 0.795-0.833, P < 0.001). CONCLUSION: This study found that STEMI, NSTEMI, respiratory rate ≥20 bpm, and use of antiplatelets were associated with increased likelihood of poor prognosis for ACS patients in the ED. It also found that SBP≥140 was associated with decreased likelihood of poor prognosis. Our study may be useful for doctors to make clinical decisions for ACS patients.

Machine learning-based in-hospital mortality prediction models for patients with acute coronary syndrome.

OBJECTIVES: The purpose of this study is to identify the risk factors of in-hospital mortality in patients with acute coronary syndrome (ACS) and to evaluate the performance of traditional regression and machine learning prediction models. METHODS: The data of ACS patients who entered the emergency department of Fujian Provincial Hospital from January 1, 2017 to March 31, 2020 for chest pain were retrospectively collected. The study used univariate and multivariate logistic regression analysis to identify risk factors for in-hospital mortality of ACS patients. The traditional regression and machine learning algorithms were used to develop predictive models, and the sensitivity, specificity, and receiver operating characteristic curve were used to evaluate the performance of each model. RESULTS: A total of 6482 ACS patients were included in the study, and the in-hospital mortality rate was 1.88%. Multivariate logistic regression analysis found that age, NSTEMI, Killip III, Killip IV, and levels of D-dimer, cardiac troponin I, CK, N-terminal pro-B-type natriuretic peptide (NT-proBNP), high-density lipoprotein (HDL) cholesterol, and Stains were independent predictors of in-hospital mortality. The study found that the area under the receiver operating characteristic curve of the models developed by logistic regression, gradient boosting decision tree (GBDT), random forest, and support vector machine (SVM) for predicting the risk of in-hospital mortality were 0.884, 0.918, 0.913, and 0.896, respectively. Feature importance evaluation found that NT-proBNP, D-dimer, and Killip were top three variables that contribute the most to the prediction performance of the GBDT model and random forest model. CONCLUSIONS: The predictive model developed using logistic regression, GBDT, random forest, and SVM algorithms can be used to predict the risk of in-hospital death of ACS patients. Based on our findings, we recommend that clinicians focus on monitoring the changes of NT-proBNP, D-dimer, Killip, cTnI, and LDH as this may improve the clinical outcomes of ACS patients.