BIG DATA DRIVEN CLINICAL INFORMATICS & SURVEILLANCE (BDD_CIS) - A MULTIMODAL DATABASE FOCUSED CLINICAL, COMMUNITY, AND MULTI-OMICS SURVEILLANCE PLAN FOR COVID-19: A STUDY PROTOCOL (Preprint)

Abstract

The Coronavirus Disease 2019 (COVID-19) caused by SARS-CoV-2 remains a serious global pandemic. All age groups are at risk for infection but elderly and persons with underlying health conditions are at higher risk of severe complications. Survivors are also at risk for multiorgan dysfunction. The US is significantly impacted with over 41,915,285 cases and 670,565 deaths reported as of 09/20/2021, including 660,034 cases and 10,099 deaths in SC. The availability of COVID-19 data in SC provides a basis for using data science to leverage multitudinal and multimodal data sources for incremental learning and disease monitoring specific to SC. Doing this requires the acquisition and collation of multiple data sources at the individual level.

This project focuses on the process for creating a large unique linked integrated database for all reported South Carolina COVID-19 patients, namely, SC COVID Cohort (S3C).

The population for the comprehensive database comes from statewide COVID-19 testing surveillance data (March 2020- till present) for all SC COVID-19 patients (N≈700,000). This project will 1) connect multiple partner data sources for prediction and intelligence gathering, 2) build a secure HIPAA compliant database that links de-identified multitudinal and multimodal data sources, 3) provide a brief overview of data science strategies contemplated for use. Data sources will include all statewide COVID-19 data, hospital based COVID-19 patient registries, Health Sciences South Carolina (HSSC) data, data from the office of Revenue and Fiscal Affairs (RFA), Area Health Resource Files (AHRF) etc.

Till present, data on 440,000 of the 660,000 SC cases of COVID-19 have been collated. We have created a secure remote server, accessible to approved researchers with necessary statistical analytic tools. The project plans to use the data to examine and monitor short- and emergent long-term clinical outcomes specific to SC.

The development of such a unique linked and integrated statewide database will allow for the identification of important predictors of short- and long-term clinical outcomes for all SC COVID-19 residents using data science.