RESUMO
OBJECTIVE: To investigate a new risk score for acute chest pain with suspected non-ST-segment elevation acute coronary syndrome (NSTE-ACS). METHODS: Patients who suffered from Chest pain and suspected NSTE-ACS were enrolled as subjects. Predictor variables had been analyzed, and a bootstrap technique was used to evaluate the internal validity of the model, and external validation had been assessed for a prospective cohort study. RESULTS: Thousand five hundred and sixty-eight patients had been included in this study. Six predictor variables were found to be significant and were used to develop the model. The C-statistic of the model was 0.83, and internal validation revealed the stability of the model and the absence of over-optimism. Patients were given different triage recommendations, and the risk score was prospectively validated. CONCLUSIONS: A risk score may be a suitable method for assessing the risk of major adverse cardiac events and aiding patient triage in emergency departments among patients with suspected NSTE-ACS.
Assuntos
Síndrome Coronariana Aguda , Síndrome Coronariana Aguda/complicações , Síndrome Coronariana Aguda/diagnóstico , Dor no Peito/diagnóstico , Dor no Peito/etiologia , Eletrocardiografia/métodos , Humanos , Estudos Prospectivos , Medição de Risco/métodos , Fatores de RiscoRESUMO
Objective: We aimed to assess the feasibility and superiority of machine learning (ML) methods to predict the risk of Major Adverse Cardiovascular Events (MACEs) in chest pain patients with NSTE-ACS. Methods: Enrolled chest pain patients were from two centers, Beijing Anzhen Emergency Chest Pain Center Beijing Bo'ai Hospital, China Rehabilitation Research Center. Five classifiers were used to develop ML models. Accuracy, Precision, Recall, F-Measure and AUC were used to assess the model performance and prediction effect compared with HEART risk scoring system. Ultimately, ML model constructed by Naïve Bayes was employed to predict the occurrence of MACEs. Results: According to learning metrics, ML models constructed by different classifiers were superior over HEART (History, ECG, Age, Risk factors, & Troponin) scoring system when predicting acute myocardial infarction (AMI) and all-cause death. However, according to ROC curves and AUC, ML model constructed by different classifiers performed better than HEART scoring system only in prediction for AMI. Among the five ML algorithms, Linear support vector machine (SVC), Naïve Bayes and Logistic regression classifiers stood out with all Accuracy, Precision, Recall and F-Measure from 0.8 to 1.0 for predicting any event, AMI, revascularization and all-cause death ( vs. HEART ≤ 0.78), with AUC from 0.88 to 0.98 for predicting any event, AMI and revascularization ( vs. HEART ≤ 0.85). ML model developed by Naïve Bayes predicted that suspected acute coronary syndrome (ACS), abnormal electrocardiogram (ECG), elevated hs-cTn I, sex and smoking were risk factors of MACEs. Conclusion: Compared with HEART risk scoring system, the superiority of ML method was demonstrated when employing Linear SVC classifier, Naïve Bayes and Logistic. ML method could be a promising method to predict MACEs in chest pain patients with NSTE-ACS.
Assuntos
Síndrome Coronariana Aguda , Infarto do Miocárdio , Humanos , Síndrome Coronariana Aguda/complicações , Síndrome Coronariana Aguda/epidemiologia , Teorema de Bayes , Estudos de Viabilidade , Medição de Risco/métodos , Dor no Peito/etiologia , Infarto do Miocárdio/diagnósticoRESUMO
Objective: The study aimed to use machine learning algorithms to predict the need for revascularization in patients presenting with chest pain in the emergency department. Methods: We obtained data from 581 patients with chest pain, 264 who underwent revascularization, and the other 317 were treated with medication alone for 3 months. Using standard algorithms, linear discriminant analysis, and standard algorithms, we analyzed 41 features relevant to coronary artery disease (CAD). Results: We identified seven robust predictive features. The combination of these predictors gave an area under the curve (AUC) of 0.830 to predict the need for revascularization. By contrast, the GRACE score gave an AUC of 0.68. Conclusions: This machine learning-based approach predicts the need for revascularization in patients with chest pain.
Assuntos
Dor no Peito , Doença da Artéria Coronariana , Doença da Artéria Coronariana/cirurgia , Serviço Hospitalar de Emergência , Humanos , Aprendizado de Máquina , Valor Preditivo dos Testes , Medição de RiscoRESUMO
OBJECTIVE: To validate a modified HEART [History, Electrocardiograph (ECG), Age, Risk factors and Troponin] risk score in chest pain patients with suspected non-ST-segment elevation acute coronary syndrome (NSTE-ACS) in the emergency department (ED). METHODS: This retrospective cohort study used a prospectively acquired database and chest pain patients admitted to the emergency department with suspected NSTE-ACS were enrolled. Data recorded on arrival at the ED were used. The serum sample of high-sensitivity cardiac Troponin I other than conventional cardiac Troponin I used in the HEART risk score was tested. The modified HEART risk score was calculated. The end point was the occurrence of major adverse cardiac events (MACE) defined as a composite of acute myocardial infarction (AMI), percutaneous intervention (PCI), coronary artery bypass graft (CABG), or all-cause death, within three months after initial presentation. RESULTS: A total of 1,300 patients were enrolled. A total of 606 patients (46.6%) had a MACE within three months: 205 patients (15.8%) were diagnosed with AMI, 465 patients (35.8%) underwent PCI, and 119 patients (9.2%) underwent CABG. There were 10 (0.8%) deaths. A progressive, significant pattern of increasing event rate was observed as the score increased (P < 0.001 by χ (2) for trend). The area under the receiver operating characteristic curve was 0.84. All patients were classified into three groups: low risk (score 0-2), intermediate risk (score 3-4), and high risk (score 5-10). Event rates were 1.1%, 18.5%, and 67.0%, respectively (P < 0.001). CONCLUSIONS: The modified HEART risk score was validated in chest pain patients with suspected NSTE-ACS and may complement MACE risk assessment and patients triage in the ED. A prospective study of the score is warranted.
RESUMO
OBJECTIVE: The purpose of the present study was to investigate the relationship between waist-to-height ratio (WHtR) and the hypertriglyceridemic waist (HTGW) phenotype to test the hypothesis that WHtR can identify adolescents at high risk of the HTGW phenotype. METHODS: In 2006, anthropometric measurements were assessed in a cross-sectional population-based study of 3136 Han adolescents aged 13-17 years. Blood samples were collected to measure triacylglycerol concentrations. WHtR was calculated by waist circumference/height. The HTGW phenotype was represented by the simultaneous presence of elevated serum triglycerides and increased waist circumference. The ability of WHtR to accurately define the HTGW phenotype was assessed by area under the curve (AUC). RESULTS: The prevalence of the HTGW phenotype was 3.3% (boys 3.6% vs. girls 2.9%, χ2=1.424, p=0.233). The prevalence of the HTGW phenotype increased with WHtR (p<0.001). The accuracy of WHtR in the identification of the HTGW phenotype (as assessed by AUC) was over 0.85, both in boys and girls (AUC: 0.956 in boys and 0.961 in girls). WHtR cutoff values, chosen to maximize sensitivity plus specificity, for the HTGW phenotype were calculated to be 0.48 in boys and 0.46 in girls. The sensitivities were 98.3% in boys and 97.7% in girls. The specificities were 88.0% in boys and 86.8% in girls. CONCLUSIONS: WHtR is simpler than the HTGW phenotype and does not require blood tests. The prevalence of the HTGW phenotype increased with WHtR. Higher WHtR can identify adolescents with high risk of the HTGW phenotype.