Data Liberation in a Public Healthcare Setting: Using AI to improve accessibility of data to researchers and clinicians

Today, 30% of the world's data volume is generated by the healthcare industry. This data is collected by care providers to improve patient care and with the intention of secondary use for critical research and development. However, the ability to effectively data mine is limited by the nature of healthcare data itself: disparate systems, volume of unstructured (free-text) data, and human factors. SapienSecure is a data enablement solution that utilizes Natural Language Processing (NLP) and other AI to extract and index this complex data into a usable format to ensure researchers have access to comprehensive and clean datasets. To date, SapienSecure has extracted 400+ million datapoints to facilitate research within VCHRI.