Dataset Information

The CAMI-score: A Novel Tool derived From CAMI Registry to Predict In-hospital Death among Acute Myocardial Infarction Patients.

ABSTRACT: Risk stratification of patients with acute myocardial infarction (AMI) is of clinical significance. Although there are many existing risk scores, periodic update is required to reflect contemporary patient profile and management. The present study aims to develop a risk model to predict in-hospital death among contemporary AMI patients as soon as possible after admission. We included 23417 AMI patients from China Acute Myocardial Infarction (CAMI) registry from January 2013 to September 2014 and extracted relevant data. Patients were divided chronologically into a derivation cohort (n?=?17563) to establish the multivariable logistic regression model and a validation cohort (n?=?5854) to validate the risk score. Sixteen variables were identified as independent predictors of in-hospital death and were used to establish CAMI risk model and score: age, gender, body mass index, systolic blood pressure, heart rate, creatinine level, white blood cell count, serum potassium, serum sodium, ST-segment elevation on ECG, anterior wall involvement, cardiac arrest, Killip classification, medical history of hypertension, medical history of hyperlipidemia and smoking status. Area under curve value of CAMI risk model was 0.83 within the derivation cohort and 0.84 within the validation cohort. We developed and validated a risk score to predict in-hospital death risk among contemporary AMI patients.

SUBMITTER: Song C

PROVIDER: S-EPMC5998057 | biostudies-literature | 2018 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The CAMI-score: A Novel Tool derived From CAMI Registry to Predict In-hospital Death among Acute Myocardial Infarction Patients.

Song Chenxi C Fu Rui R Dou Kefei K Yang Jingang J Xu Haiyan H Gao Xiaojin X Li Wei W Gao Guofeng G Zhao Zhiyong Z Liu Jia J Yang Yuejin Y

Scientific reports 20180613 1

Risk stratification of patients with acute myocardial infarction (AMI) is of clinical significance. Although there are many existing risk scores, periodic update is required to reflect contemporary patient profile and management. The present study aims to develop a risk model to predict in-hospital death among contemporary AMI patients as soon as possible after admission. We included 23417 AMI patients from China Acute Myocardial Infarction (CAMI) registry from January 2013 to September 2014 and ...[more]

PMID: 29899463

Similar Datasets

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:ObjectivesThe aim of this study was to develop and validate a novel risk score to predict in-hospital mortality in patients with acute myocardial infarction (AMI) using the Heart Failure after Acute Myocardial Infarction with Optimal Treatment (HAMIOT) cohort in China.MethodsThe HAMIOT cohort was a multicenter, prospective, observational cohort of consecutive patients with AMI in China. All participants were enrolled between December 2017 and December 2019. The cohort was randomly assigned (at a proportion of 7:3) to the training and validation cohorts. Logistic regression model was used to develop and validate a predictive model of in-hospital mortality. The performance of discrimination and calibration was evaluated using the Harrell's c-statistic and the Hosmer-Lemeshow goodness-of-fit test, respectively. The new simplified risk score was validated in an external cohort that included independent patients with AMI between October 2019 and March 2021.ResultsA total of 12,179 patients with AMI participated in the HAMIOT cohort, and 136 patients were excluded. In-hospital mortality was 166 (1.38%). Ten predictors were found to be independently associated with in-hospital mortality: age, sex, history of percutaneous coronary intervention (PCI), history of stroke, presentation with ST-segment elevation, heart rate, systolic blood pressure, initial serum creatinine level, initial N-terminal pro-B-type natriuretic peptide level, and PCI treatment. The c-statistic of the novel simplified HAMIOT risk score was 0.88, with good calibration (Hosmer-Lemeshow test: P = 0.35). Compared with the Global Registry of Acute Coronary Events risk score, the HAMIOT score had better discrimination ability in the training (0.88 vs. 0.81) and validation (0.82 vs. 0.72) cohorts. The total simplified HAMIOT risk score ranged from 0 to 121. The observed mortality in the HAMIOT cohort increased across different risk groups, with 0.35% in the low risk group (score ≤ 50), 3.09% in the intermediate risk group (50 < score ≤ 74), and 14.29% in the high risk group (score > 74).ConclusionThe novel HAMIOT risk score could predict in-hospital mortality and be a valid tool for prospective risk stratification of patients with AMI.Clinical trial registration[https://clinicaltrials.gov], Identifier: [NCT03297164].

Dataset Information

The CAMI-score: A Novel Tool derived From CAMI Registry to Predict In-hospital Death among Acute Myocardial Infarction Patients.

Publications

The CAMI-score: A Novel Tool derived From CAMI Registry to Predict In-hospital Death among Acute Myocardial Infarction Patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets