Publications by authors named "Sarah Prezek"
Accurately calling indels with next-generation sequencing (NGS) data is critical for clinical application. The precisionFDA team collaborated with the U.S.
View Article and Find Full Text PDFArticle Synopsis
- - The COVID-19 pandemic had a significant impact on Veterans, who often have higher health risks, prompting a need for targeted predictive models using synthetic electronic health record (EHR) data to overcome access restrictions in traditional datasets.
- - The precisionFDA COVID-19 Risk Factor Modeling Challenge was initiated by the FDA and VHA to create diagnostic models specific to Veterans, using synthetic data to increase participation and replace the limited access to real data.
- - Results indicated that models trained on synthetic data yielded similar, albeit slightly inflated, performance metrics compared to those using real data, with major risk factors from both sources largely overlapping and validated by existing research.