Teaching data science fundamentals through realistic synthetic clinical cardiovascular data
Preprint
Abstract
Objective: Our goal was to create a synthetic dataset and curricular materials to assist in teaching fundamentals of translational data science. Materials and Methods: A literature review was conducted to extract current cardiovascular risk score logic, data elements, and population characteristics. Then, clinical data elements in the models were pulled from clinical data and transformed to the Observational Medical Outcomes Partnership (OMOP) common data model; genetic data elements were added based on population rates. A hybrid Bayesian network was used to create synthetic data from the logical elements of the risk scores and the underlying population frequencies of the clinical data. Results: A synthetic dataset of 446,000 patients was created. A two-day curriculum was created based on this synthetic data with exploratory data analysis and machine learning components. The curriculum was offered on two separate occasions; the two groups of learners were given the curriculum and data, and results were tallied, summarized, and compared. Students’ ability to complete the challenge was mixed; more experienced students achieved a range of 70%-85% in balanced accuracy, but many others did not perform better than the baseline model. Discussion: Overall, students enjoyed the course and dataset, but some struggled to consistently apply machine learning techniques. The curriculum, data set, techniques for generation, and results are available for others to use for their own training. Conclusion: A realistic synthetic data with clinical and genetic components helps students learn issues in cardiovascular risk scoring, practice data science skills, and compete in a challenge to improve identification of risk.Keywords
This publication has 16 references indexed in Scilit:
- Assessment-based health informatics curriculum improvementJournal of the American Medical Informatics Association, 2016
- 10-Year Coronary Heart Disease Risk Prediction Using Coronary Artery Calcium and Traditional Risk FactorsJACC, 2015
- 2013 ACC/AHA Guideline on the Assessment of Cardiovascular RiskCirculation, 2014
- Validation of the Atherosclerotic Cardiovascular Disease Pooled Cohort Risk EquationsJAMA, 2014
- Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical researchJournal of the American Medical Informatics Association, 2013
- SNPedia: a wiki supporting personal genome annotation, interpretation and analysisNucleic Acids Research, 2011
- Data-driven approach for creating synthetic electronic medical recordsBMC Medical Informatics and Decision Making, 2010
- Program Requirements for Fellowship Education in the Subspecialty of Clinical InformaticsJournal of the American Medical Informatics Association, 2009
- General Cardiovascular Risk Profile for Use in Primary CareCirculation, 2008
- How Students Learn Statistics Revisited: A Current Review of Research on Teaching and Learning StatisticsInternational Statistical Review, 2007