Methods Core

Methods Core

DATA-DRIVEN CLINICAL TRIAL DESIGN AND GENERALIZABILITY ASSESSMENT

  • Principal Investigator: Zhe He, Ph.D

  • Specific Aims: Clinical studies are essential in evidence-based medicine. However, participant recruitment has long been a major concern. Although ~60% of new all cancer cases occur among older adults, they comprise merely 25% of participants in cancer clinical studies. Unjustified or overly-restrictive eligibility criteria are the most important modifiable barriers causing low accrual, early termination, and low generalizability.

    This in turn can cause the studies to be underpowered and increase the likelihood of adverse drug reactions and toxicity when moved into clinical practice. We are developing data-driven methods and tools to assess the generalizability of clinical studies using the electronic data in clinical trial registries, public patient databases, and clinical data warehouses. This project aims to improve the representation of underserved population subgroups in clinical studies such as older adults with multiple chronic conditions.

  • Funding Source:

    National Institute on Aging (R21 AG061431), Amazon, Eli Lilly and Company, FSU Council on Research and Creativity

SEMANTICS-POWERED DATA ANALYTICS AND MACHINE LEARNING

  • Principal Investigator: Zhe He, Ph.D

  • Specific Aims: Various healthcare information systems such as EHRs have integrated well-curated biomedical controlled vocabularies, e.g., the International Classification of Diseases (ICD) and RxNORM, as their vocabulary foundation. With rich medical concepts linked by hierarchical and associative relationships, these vocabularies and ontologies can also be utilized in health data analytics tasks such as natural language processing, data integration, and decision support. Opportunities exist for leveraging semantic methods to enhance these data science efforts.

    Our research and development effectively use biomedical ontologies and/or semantics methods to address important problems in biomedicine and fundamental problems in natural language processing such as word sense disambiguation, relation extraction, and temporal information extraction. In addition, we also seek to build effective machine learning models to predict health outcomes for patients such as mortality and readmission.

COHORT DISCOVERY OVER ONEFLORIDA DATA TRUST

  • Principal Investigator: Zhe He, Ph.D

  • Specific Aims: The OneFlorida Clinical Data Research Network (CDRN) is a collaborative statewide network that seeks to improve health research capacity and opportunities in the State of Florida through the facilitation of clinical and translation research in communities and health care settings.  Its core resource - OneFlorida Data Trust, contains longitudinal and linked patient records of ~15 million Floridians from various sources, including Medicaid/Medicare, cancer registry, vital statistics, and electronic health records (EHR) from its clinical partners.

    The Data Trust follows the PCORnet Common Data Model (CDM), and contains detailed patient characteristics and clinical variables, including demographics, encounters, diagnoses, procedures, vitals, medications, and labs. We will help FSU investigators define cohort discovery queries over this rich clinical data warehouse to answer critical research questions

METHODS FOR TRANSLATIONAL BEHAVIORAL RESEARCH (2014 NIH WORKSHOP)

  • Specific Aims: The National Institutes of Health sponsored a cross-institute, two-day "Workshop on Innovative Study Designs and Methods for Developing, Testing and Implementing Behavioral Interventions to Improve Health" to review, evaluate, and disseminate a selection of innovative designs and analytic strategies for use in behavioral intervention studies. Experts from the behavioral, biostatistical and clinical communities reviewed the utility of new, innovative and potentially more efficient study designs and methods to develop, optimize, test and implement behavioral interventions across the translational targeting multiple behavioral risk factors (e.g., adherence, diet, physical activity, smoking). Presentations and discussions focused mainly on the development and preliminary testing of behavioral interventions on Day 1, with an emphasis on later-stages of development, including testing and implementation of interventions within clinical and community contexts, on Day 2.

    Access agenda and resources here.

title-inside title-centered
2