Research

At PARSE Health, we join forces with researchers and clinicians to craft and implement cutting-edge statistical and computational methodologies for tackling intricate health challenges. Our multidisciplinary team combines expertise in biostatistics, machine learning, and data science to address pressing issues in precision medicine, drug discovery, and public health.

CSRP

The Center for Suicide Risk Prevention and Research (CSRP) is dedicated to enhancing outcomes for individuals at risk of suicide through groundbreaking research and innovative methodologies. The CSRP Methods Core (CSRP-MC) consists of a talented group of biostatisticians, informaticians, and app developers who employ sophisticated statistical and computational techniques. Their research focuses on key areas including:

  • Automated Feature Selection: Optimizing data analysis workflows.

  • Mental Health Knowledge Network: Promoting collaboration and knowledge sharing among researchers.

  • Federated Transfer Learning: Advancing predictive modeling approaches for suicide risk assessment and treatment response prediction.

The center places a strong emphasis on utilizing diverse data sources, particularly electronic health records (EHR), to assess and implement effective interventions.

For comprehensive information, please visit the CSRP website.

GREAD

The GREAD (Scalable and Generalizable Real-world Evidence on Unstructured Efficacy and Adverse Effect Endpoints for Chronic Diseases) initiative strives to deepen our understanding of chronic diseases through pioneering methodologies. The project’s key focus areas include:

  • Creating electronic progression (eProg) models derived from electronic health record (EHR)-linked registries.

  • Estimating disease-modifying therapies (DMTs) using partial prescription (RX) data.

  • Applying federated meta-learning techniques to evaluate adverse event (AE) risks.

Funded by the U.S. Food & Drug Administration (FDA), the GREAD study concentrates on harnessing real-world evidence to enhance patient outcomes.

To learn more, please explore the GREAD website.