Currently submitted to: JMIR Medical Informatics
Date Submitted: Sep 20, 2019
Open Peer Review Period: Sep 19, 2019 - Nov 14, 2019
(currently open for review)
Development and Validation of A Simplified Short-term Prognostic Evaluation Nomogram for Patients with Stable Coronary Heart Disease
Objective To predict the incidence of recurrent cardiovascular events in patients with stable coronary heart disease in one year, a simple and robust nomogram was established and validated. Method The predictive model was developed and validated in two prospective coronary artery disease cohorts. The total population was 3618, with 589 recurrent cardiovascular events. Seven-tenths of the total population were randomly selected for model development, and LASSO regression was used to extract features from the information needed for routine diagnosis and treatment. Multivariate logistic regression analysis was used to establish the prediction model, which was displayed by nomograph. Internal validation was conducted using the remaining three-tenths of the population.The performance of nomograph was evaluated according to its calibration, identification and clinical practicability. Result Prognostic factors consisting of 10 selected features were significantly associated with recurrent cardiovascular events. Predictors of prognostic evaluation model included age, heart rate, diastolic pressure, triglyceride, red blood cell count, grade of Hypertension， history of hyperlipidemia, history of revascularization, use of clopidogrel, use of ACEI or ARB. The model has good discrimination. The C index is 0.722 in the development set and 0.711 in the validation set. Nomograph also has good calibration. Decision curve analysis shows that radiography is useful in clinic. Conclusion This study developed a relatively accurate nomograph to predict the incidence of recurrent cardiovascular events in patients with stable coronary heart disease within one year.
Request queued. Please wait while the file is being generated. It may take some time.
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.