Aims to facilitate the learning of issues in cardiovascular risk scoring. cvdRiskData consists of a synthetic dataset and curricular materials modeled on a real patient cohort that includes clinical and genetic covariates. The script, Bayesian network, and conditional probability tables (CPTs) used to generate the dataset are also included. The dataset can be used for (1) teaching math, statistics, (2) teaching machine learning techniques to biologists and clinicians, and (3) assessing the performance of machine learning techniques on a tunable dataset.
Department of Medical Informatics and Clinical Epidemiology, Oregon Health and Science University, Portland, OR, USA; Knight Cancer Institute, Oregon Health and Science University, Portland, OR, USA; OHSU Library, Oregon Health and Science University, Portland, OR, USA
cvdRiskData funding source(s)
Supported by a BD2K Training grant: 1R25EB020379-01.