Dataset Information

A LASSO-derived risk model for long-term mortality in Chinese patients with acute coronary syndrome.

ABSTRACT: BACKGROUND:The formal risk assessment is essential in the management of acute coronary syndrome (ACS). In this study, we develop a risk model for the prediction of 3-year mortality for Chinese ACS patients with machine learning algorithms. METHODS:A total of 2174 consecutive patients who underwent angiography with ACS were enrolled. The missing data among baseline characteristics were imputed using the MissForest algorithm based on random forest method. In model development, a least absolute shrinkage and selection operator (LASSO) derived Cox regression with internal tenfold cross-validation was used to identify the predictors for 3-year mortality. The clinical performance was assessed with decision curve analysis. RESULTS:The average follow-up period was 27.82?±?13.73 months; during the 3 years of follow up, 193 patients died (mortality rate 8.88%). The Kaplan-Meier estimate of 3-year mortality was 0.91 (95% confidence interval (CI): 0.890.92). After feature selection, 6 predictors were identified: Age," "Creatinine," "Hemoglobin," "Platelets," "aspartate transaminase (AST)" and "left ventricular ejection fraction (LVEF)". At tenfold internal validation, our risk model performed well in both discrimination (area under curve (AUC) of receiver operating characteristic (ROC) analysis was 0.768) and calibration (calibration slope was approximately 0.711). As a comparison, the AUC and calibration slope were 0.701 and 0.203 in Global Registry of Acute Coronary Events (GRACE) risk score, respectively. Additionally, the highest net benefit of our model within the entire range of threshold probability for clinical intervention by decision curve analysis demonstrated the superiority of it in daily practice. CONCLUSION:Our study developed a prediction model for 3-year morality in Chinese ACS patients. The methods of missing data imputation and model derivation base on machine learning algorithms improved the ability of prediction. . Trial registration ChiCTR, ChiCTR-OOC-17010433. Registered 17 February 2017-Retrospectively registered.

SUBMITTER: Li YM

PROVIDER: S-EPMC7137217 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A LASSO-derived risk model for long-term mortality in Chinese patients with acute coronary syndrome.

Li Yi-Ming YM Li Zhuo-Lun ZL Chen Fei F Liu Qi Q Peng Yong Y Chen Mao M

Journal of translational medicine 20200406 1

<h4>Background</h4>The formal risk assessment is essential in the management of acute coronary syndrome (ACS). In this study, we develop a risk model for the prediction of 3-year mortality for Chinese ACS patients with machine learning algorithms.<h4>Methods</h4>A total of 2174 consecutive patients who underwent angiography with ACS were enrolled. The missing data among baseline characteristics were imputed using the MissForest algorithm based on random forest method. In model development, a lea ...[more]

PMID: 32252780

Similar Datasets

Project description:BACKGROUND:Prior studies of healthy populations have found religious practices to be associated with survival. However, no contemporary studies have examined whether religiosity influences survival among patients discharged from the hospital after an acute coronary syndrome (ACS). The present study examined the relationship between religious practices and 2-year all-cause mortality among hospital survivors of an ACS. METHODS:Patients hospitalized for an ACS were recruited from 6 medical centers in Massachusetts and Georgia between 2011 and 2013. Study participants self-reported three items assessing religiosity: strength/comfort from religion, petition prayers for health, and awareness of intercessory prayers by others. All cause-mortality within 2-years of hospital discharge was ascertained by review of medical records at participating study hospitals and from death certificates. Cox proportional hazards models were used to estimate the multivariable adjusted risk of 2-year all-cause mortality. RESULTS:Participants (n = 2,068) were on average 61 years old, 34% were women, and 81% were non-Hispanic White. Approximately 85% derived strength/comfort from religion, 61% prayed for their health, and 89% were aware of intercessions. Overall, 6% died within 2 years post-discharge. After adjusting for sociodemographic variables (age, sex, and race/ethnicity), petition prayers were associated with an increased risk of 2-year all-cause mortality (HR: 1.64; 95% CI: 1.01-2.66). With further adjustment for several clinical and psychosocial measures, this association was no longer statistically significant. Strength and comfort from religion and intercessory prayers were not significantly associated with mortality. CONCLUSIONS:Most ACS survivors acknowledge deriving strength and comfort from religion, praying for their health, and intercessions made by others for their health. Although the reported religious practices were not associated with post-discharge survival after multivariable adjustment, acknowledging that patients utilize their religious beliefs and practices as strategies to improve their health would ensure a more holistic approach to patient management and promote cultural competence in healthcare.

Dataset Information

A LASSO-derived risk model for long-term mortality in Chinese patients with acute coronary syndrome.

Publications

A LASSO-derived risk model for long-term mortality in Chinese patients with acute coronary syndrome.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets