AI4RDM: Using Large Language Models (LLMs) for Medical Data Analysis and Research Data Management

Led by: Hajira Jabeen

Research Focus

This focus area explores the application of Large Language Models (LLMs) in analyzing and managing medical and clinical research data. LLMs, with their capacity to process and interpret large volumes of unstructured and semi-structured text, are positioned to address key challenges in the domain.

Key Objectives

Medical Data Analysis

Utilizing LLMs to extract, synthesize, and contextualize information from diverse data sources such as clinical notes, scientific publications, and patient records. The aim is to enhance insights, automate information retrieval, and support decision-making processes in research and clinical settings.

RDM Automation

Leveraging LLMs to streamline tasks in RDM, such as metadata generation, data annotation, and quality assurance, while ensuring compliance with FAIR data principles (Findability, Accessibility, Interoperability, and Reusability).

Data Interoperability and Integration

Employing LLMs to facilitate data harmonization and semantic integration across heterogeneous datasets, thereby enabling more effective cross-study and cross-institutional research.

Ethical and Practical Considerations

This focus area emphasizes rigorous evaluation of LLM capabilities, integration with existing medical infrastructures, and the development of ethical frameworks to address concerns related to data privacy, bias, and transparency in AI-driven processes.