Dataset Information

Development of an optimized risk score to predict short-term death among acute myocardial infarction patients in rural China.

ABSTRACT:

Background

Risk stratification of patients with acute myocardial infarction (AMI) is of great clinical significance.

Hypothesis

The present study aimed to establish an optimized risk score to predict short-term (6-month) death among rural AMI patients from China.

Methods

We enrolled 6581 AMI patients and extracted relevant data. Patients were divided chronologically into a derivation cohort (n = 5539), to establish the multivariable risk prediction model, and a validation cohort (n = 1042), to validate the risk score.

Results

Six variables were identified as independent predictors of short-term death and were used to establish the risk score: age, Killip class, blood glucose, creatinine, pulmonary artery systolic pressure, and percutaneous coronary intervention treatment. The area under the ROC curve (AUC) of the optimized risk score was 0.82 within the derivation cohort and 0.81 within the validation cohort. The diagnostic performance of the optimized risk score was superior to that of the GRACE risk score (AUC 0.76 and 0.75 in the derivation and validation cohorts, respectively; p < .05).

Conclusion

These results indicate that the optimized scoring method developed here is a simple and valuable instrument to accurately predict the risk of short-term mortality in rural patients with AMI.

SUBMITTER: Wang SJ

PROVIDER: S-EPMC8119840 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of an optimized risk score to predict short-term death among acute myocardial infarction patients in rural China.

Wang Sheng-Ji SJ Cheng Zhen-Xiu ZX Fan Xiao-Ting XT Lian Yong-Gang YG

Clinical cardiology 20210325 5

<h4>Background</h4>Risk stratification of patients with acute myocardial infarction (AMI) is of great clinical significance.<h4>Hypothesis</h4>The present study aimed to establish an optimized risk score to predict short-term (6-month) death among rural AMI patients from China.<h4>Methods</h4>We enrolled 6581 AMI patients and extracted relevant data. Patients were divided chronologically into a derivation cohort (n = 5539), to establish the multivariable risk prediction model, and a validation c ...[more]

PMID: 33764508

Similar Datasets

Project description:BackgroundThe aim of this study was to investigate the association between inflammatory markers and 28-day mortality in patients with ST-elevation myocardial infarction (STEMI).MethodsIn 398 STEMI patients recorded between 2009 and 2013 by the population-based Myocardial Infarction Registry Augsburg, 92 protein biomarkers were measured in admission arterial blood samples using the OLINK inflammatory panel. In multivariable-adjusted logistic regression models, the association between each marker and 28-day mortality was investigated. The values of the biomarkers most significantly associated with mortality were standardized and summarized to obtain a prediction score for 28-day mortality. The predictive ability of this biomarker score was compared to the established GRACE score using ROC analysis. Finally, a combined total score was generated by adding the standardized biomarker score to the standardized GRACE score.ResultsThe markers IL-6, IL-8, IL-10, FGF-21, FGF-23, ST1A1, MCP-1, 4E-BP1, and CST5 were most significantly associated with 28-day mortality, each with FDR-adjusted (false discovery rate adjusted) p-values of < 0.01 in the multivariable logistic regression model. In a ROC analysis, the biomarker score and the GRACE score showed comparable predictive ability for 28-day mortality (biomarker score AUC: 0.7859 [CI: 0.6735-0.89], GRACE score AUC: 0.7961 [CI: 0.6965-0.8802]). By combining the biomarker score and the Grace score, the predictive ability improved with an AUC of 0.8305 [CI: 0.7269-0.9187]. A continuous Net Reclassification Improvement (cNRI) of 0.566 (CI: 0.192-0.94, p-value: 0.003) and an Integrated Discrimination Improvement (IDI) of 0.083 ((CI: 0.016-0.149, p-value: 0.015) confirmed the superiority of the combined score over the GARCE score.ConclusionsInflammatory biomarkers may play a significant role in the pathophysiology of acute myocardial infarction (AMI) and AMI-related mortality and might be a promising starting point for personalized medicine, which aims to provide each patient with tailored therapy.

Project description:Air pollution remains a major threat to cardiovascular health and most acute myocardial infarction (AMI) deaths occur at home. However, currently established knowledge on the deleterious effect of air pollution on AMI has been limited to routinely monitored air pollutants and overlooked the place of death. In this study, we examined the association between short-term residential exposure to China's routinely monitored and unmonitored air pollutants and the risk of AMI deaths at home. A time-stratified case-crossover analysis was undertaken to associate short-term residential exposure to air pollution with 0.1 million AMI deaths at home in Jiangsu Province (China) during 2016-2019. Individual-level residential exposure to five unmonitored and monitored air pollutants including PM1 (particulate matter with an aerodynamic diameter ≤ 1 μm) and PM2.5 (particulate matter with an aerodynamic diameter ≤ 2.5 μm), SO2 (sulfur dioxide), NO2 (nitrogen dioxide), and O3 (ozone) was estimated from satellite remote sensing and machine learning technique. We found that exposure to five air pollutants, even below the recently released stricter air quality standards of the World Health Organization (WHO), was all associated with increased odds of AMI deaths at home. The odds of AMI deaths increased by 20% (95% confidence interval: 8 to 33%), 22% (12 to 33%), 14% (2 to 27%), 13% (3 to 25%), and 7% (3 to 12%) for an interquartile range increase in PM1, PM2.5, SO2, NO2, and O3, respectively. A greater magnitude of association between NO2 or O3 and AMI deaths was observed in females and in the warm season. The greatest association between PM1 and AMI deaths was found in individuals aged ≤ 64 years. This study for the first time suggests that residential exposure to routinely monitored and unmonitored air pollutants, even below the newest WHO air quality standards, is still associated with higher odds of AMI deaths at home. Future studies are warranted to understand the biological mechanisms behind the triggering of AMI deaths by air pollution exposure, to develop intervention strategies to reduce AMI deaths triggered by air pollution exposure, and to evaluate the cost-effectiveness, accessibility, and sustainability of these intervention strategies.

Project description:ImportanceAccurate prediction of adverse outcomes after acute myocardial infarction (AMI) can guide the triage of care services and shared decision-making, and novel methods hold promise for using existing data to generate additional insights.ObjectiveTo evaluate whether contemporary machine learning methods can facilitate risk prediction by including a larger number of variables and identifying complex relationships between predictors and outcomes.Design, setting, and participantsThis cohort study used the American College of Cardiology Chest Pain-MI Registry to identify all AMI hospitalizations between January 1, 2011, and December 31, 2016. Data analysis was performed from February 1, 2018, to October 22, 2020.Main outcomes and measuresThree machine learning models were developed and validated to predict in-hospital mortality based on patient comorbidities, medical history, presentation characteristics, and initial laboratory values. Models were developed based on extreme gradient descent boosting (XGBoost, an interpretable model), a neural network, and a meta-classifier model. Their accuracy was compared against the current standard developed using a logistic regression model in a validation sample.ResultsA total of 755 402 patients (mean [SD] age, 65 [13] years; 495 202 [65.5%] male) were identified during the study period. In independent validation, 2 machine learning models, gradient descent boosting and meta-classifier (combination including inputs from gradient descent boosting and a neural network), marginally improved discrimination compared with logistic regression (C statistic, 0.90 for best performing machine learning model vs 0.89 for logistic regression). Nearly perfect calibration in independent validation data was found in the XGBoost (slope of predicted to observed events, 1.01; 95% CI, 0.99-1.04) and the meta-classifier model (slope of predicted-to-observed events, 1.01; 95% CI, 0.99-1.02), with more precise classification across the risk spectrum. The XGBoost model reclassified 32 393 of 121 839 individuals (27%) and the meta-classifier model reclassified 30 836 of 121 839 individuals (25%) deemed at moderate to high risk for death in logistic regression as low risk, which were more consistent with the observed event rates.Conclusions and relevanceIn this cohort study using a large national registry, none of the tested machine learning models were associated with substantive improvement in the discrimination of in-hospital mortality after AMI, limiting their clinical utility. However, compared with logistic regression, XGBoost and meta-classifier models, but not the neural network, offered improved resolution of risk for high-risk individuals.

Project description:BackgroundClimate change is increasing global average temperatures, as well as the frequency of extreme weather events. Both low and high ambient temperatures have been associated with elevated mortality; however, little is known about the cardiovascular impacts of hourly temperature.MethodsWe assessed the association between hourly ambient temperature and risk of myocardial infarction (MI) across adult residents of New York State (NYS). We identified cases across NYS hospitals from 2000 to 2015 in the New York Department of Health Statewide Planning and Research Cooperative System dataset, using ICD codes. Hourly ambient temperature was assessed at each patient's residential ZIP code, up to 48 hours prior to MI. We employed a time-stratified case-crossover study design matching case to control periods on hour of day, day of week, month and year.ResultsOf the 791,695 primary MI hospital admissions, 45% were female, the mean (standard deviation; SD) age was 70 (15) years, and 49% of cases occurred among New York City residents. The observed temperature range was -29 °C to 39 °C, with a mean of 10.8 °C (10.5 °C). Temperature in the 6 h preceding the MI was positively associated with risk of MI, across the range of observed temperatures, with null or nearly null associations for earlier hours. We estimated a cumulative percent increase in hourly myocardial infarction rate of 7.9% (95% confidence interval [CI]: 5.2%, 10.6%) for an 11 °C (median) to 27 °C (95th percentile) temperature increase for lag hours 0-5. Men, Medicare-ineligible individuals (age < 65), and those experiencing their first MI were most sensitive.ConclusionOur study provides evidence that increases in hourly ambient temperature can trigger myocardial infarction. Health-based definitions of extreme heat events may better capture the deleterious effects of heat by accounting for hourly temperature. Our findings can inform the design of more effective preparedness strategies for the increasingly frequent extreme heat events.

Dataset Information

Development of an optimized risk score to predict short-term death among acute myocardial infarction patients in rural China.

Background

Hypothesis

Methods

Results

Conclusion

Publications

Development of an optimized risk score to predict short-term death among acute myocardial infarction patients in rural China.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets