Prognostic values of 4 risk scores in Chinese patients with chest pain

Chen, Xiaohui; Jiang, Hangjin; Li, Yunmei; Chan, Chin Pok; Mo, Junrong; Tian, Chao-Wei; Pan, Lin; Graham, Colin A.; Rainer, Timothy

doi:10.1097/md.0000000000004778

Cited by 24 publications

(20 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our search identified 778 citations (Figure ) and following removal of duplicates, we screened 557 studies, from which 62 studies underwent full‐text review. We included 29 distinct cohorts from 30 studies in the meta‐analysis . All included studies evaluated the prognostic accuracy of the HEART score using a low‐risk threshold (score between 0 and 3).…”

Section: Resultsmentioning

confidence: 99%

“…All included studies evaluated the prognostic accuracy of the HEART score using a low‐risk threshold (score between 0 and 3). Twenty‐one studies also evaluated the prognostic accuracy of the HEART score using a high‐risk threshold (score between 7 and 10) . Eight studies additionally evaluated the prognostic accuracy of a low‐risk TIMI (score of either 0 or 1) for prediction of MACE, while three evaluated the prognostic accuracy of a high‐risk TIMI (score of either 6 or 7) …”

Section: Resultsmentioning

confidence: 99%

“…Sixteen studies evaluated the HEART score for 30‐day incidence of MACE, while 13 evaluated the HEART score for 6‐week incidence of MACE . Most studies included only patients presenting with chest pain, while five studies included patients presenting with “suspected ACS.” In 14 studies, the ECG was interpreted by an ED physician, while in seven studies the ECG was specifically interpreted by a cardiologist . Four studies computed the HEART score using high‐sensitivity troponin assays, while the remaining studies used conventional troponin T or I assays (as used in the original study) …”

Section: Resultsmentioning

confidence: 99%

“…That same patient with a TIMI score below the low‐risk threshold (≤1) would have a posttest probability of 7.8%. It was not possible to assess the prognostic accuracy of the GRACE score, as the included studies that analyzed this score utilized different thresholds for evaluation . These demonstrated findings have important implications for relevant guidelines and clinical policies.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Prognostic Accuracy of the HEART Score for Prediction of Major Adverse Cardiac Events in Patients Presenting With Chest Pain: A Systematic Review and Meta‐analysis

Fernando

Tran

Cheng

et al. 2018

Academic Emergency Medicine

View full text Add to dashboard Cite

Objective: The HEART score has been proposed for emergency department (ED) prediction of major adverse cardiac events (MACE). We sought to summarize all studies assessing the prognostic accuracy of the HEART score for prediction of MACE in adult ED patients presenting with chest pain.Methods: We searched MEDLINE, PubMed, EMBASE, Scopus, Web of Science, and the Cochrane Database of Systematic Reviews from inception through May 2018 and included studies using the HEART score for the prediction of short-term MACE in adult patients presenting to the ED with chest pain. The main outcome was short-term (i.e., 30-day or 6-week) incidence of MACE. We secondarily evaluated the prognostic accuracy of the HEART score for prediction of mortality and myocardial infarction (MI). Where available, accuracy of the Thrombolysis in Myocardial Infarction (TIMI) score was determined. Results:We included 30 studies (n = 44,202) in analysis. A HEART score above the low-risk threshold (≥4) had a sensitivity of 95.9% (95% confidence interval [CI] = 93.3%-97.5%) and specificity of 44.6% (95% CI = 38.8%-50.5%) for MACE. A high-risk HEART score (≥7) had a sensitivity of 39.5% (95% CI = 31.6%-48.1%) and specificity of 95.0% (95% CI = 92.6%-96.6%) for MACE, whereas a TIMI score above the low-risk threshold (≥2) had a sensitivity of 87.8% (95% CI = 80.2%-92.8%) and specificity of 48.1% (95% CI = 38.9%-57.5%) for MACE. A high-risk TIMI score (≥6) was 2.8% sensitive (95% CI = 0.8%-9.6%), but 99.6% (95% CI = 98.5%-99.9%) specific for MACE. A HEART score ≥ 4 had a sensitivity of 95.0% (95% CI = 87.2%-98.2%) for prediction of mortality and 97.5% (95% CI = 93.7%-99.0%) for prediction of MI.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Prognostic Accuracy of the HEART Score for Prediction of Major Adverse Cardiac Events in Patients Presenting With Chest Pain: A Systematic Review and Meta‐analysis

Fernando

Tran

Cheng

et al. 2018

Academic Emergency Medicine

View full text Add to dashboard Cite

show abstract

“…Initially, risk scores such as the Thrombolysis in Myocardial Infarction (TIMI) score [6,7] and the Global Registry of Acute Coronary Events (GRACE) score [8] were developed from post-ACS patients to estimate short-term mortality and recurrence of myocardial infarction. The History, Electrocardiogram (ECG), Age, Risk factors, and initial Troponin (HEART) score was subsequently designed for ED chest pain patients [9], which demonstrated superior performance in many comparison studies on the identification of low-risk chest pain patients [10][11][12][13][14][15][16][17]. Nonetheless, the HEART score has its disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Dimensionality Reduction Showed Marginal Performance Benefit Over Stepwise Regression for Risk Stratification of Chest Pain Patients in the Emergency Department

Liu

Chee

Koh

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Chest pain is among the most common presenting complaints in the emergency department (ED). Swift and accurate risk stratification of chest pain patients in the ED may improve patient outcomes and reduce unnecessary costs. Traditional logistic regression with stepwise variable selection has been used to build risk prediction models for ED chest pain patients. In this study, we aimed to investigate if machine learning dimensionality reduction methods can achieve superior performance than the stepwise approach in deriving risk stratification models. Methods: A retrospective analysis was conducted on the data of patients >20 years old who presented to the ED of Singapore General Hospital with chest pain between September 2010 and July 2015. Variables used included demographics, medical history, laboratory findings, heart rate variability (HRV), and HRnV parameters calculated from five to six-minute electrocardiograms (ECGs). The primary outcome was 30-day major adverse cardiac events (MACE), which included death, acute myocardial infarction, and revascularization. Candidate variables identified using univariable analysis were then used to generate the stepwise logistic regression model and eight machine learning dimensionality reduction prediction models. A separate set of models was derived by excluding troponin. Receiver operating characteristic (ROC) and calibration analysis was used to compare model performance.Results: 795 patients were included in the analysis, of which 247 (31%) met the primary outcome of 30-day MACE. Patients with MACE were older and more likely to be male. All eight dimensionality reduction methods marginally but non-significantly outperformed stepwise variable selection; The multidimensional scaling algorithm performed the best with an area under the curve (AUC) of 0.901. All HRnV-based models generated in this study outperformed several existing clinical scores in ROC analysis.Conclusions: HRnV-based models using stepwise logistic regression performed better than existing chest pain scores for predicting MACE, with only marginal improvements using machine learning dimensionality reduction. Moreover, traditional stepwise approach benefits from model transparency and interpretability; in comparison, machine learning dimensionality reduction models are black boxes, making them difficult to explain in clinical practice.

show abstract

Chest Pain

Raja

2023

Evidence‐Based Emergency Care

View full text Add to dashboard Cite

Prognostic values of 4 risk scores in Chinese patients with chest pain

Abstract: Supplemental Digital Content is available in the text

Cited by 24 publications

References 32 publications

Prognostic Accuracy of the HEART Score for Prediction of Major Adverse Cardiac Events in Patients Presenting With Chest Pain: A Systematic Review and Meta‐analysis

Prognostic Accuracy of the HEART Score for Prediction of Major Adverse Cardiac Events in Patients Presenting With Chest Pain: A Systematic Review and Meta‐analysis

Machine Learning Dimensionality Reduction Showed Marginal Performance Benefit Over Stepwise Regression for Risk Stratification of Chest Pain Patients in the Emergency Department

Chest Pain

Contact Info

Product

Resources

About