P230: Leveraging Generative AI and FHIR Standards for Seamless Data Integration and Real-Time Analytics in Clinical Trials
Poster Presenter
Saurabh Das
Senior Consultant
Tata Consultancy Services Ltd United States
Objectives
A system was developed using Generative AI and FHIR-compliant healthcare data to enable real-time data retrieval, automated dashboards, and AI-driven insights for clinical trial analytics and training scenarios.
Method
A proof-of-concept system was developed using Generative AI and FHIR-compliant healthcare data to enable real-time data retrieval, automated dashboards, and AI-driven insights for clinical trial analytics and training scenarios.
Results
The proposed Generative AI–FHIR framework demonstrated the ability to improve accessibility and utilization of clinical trial data through real-time, AI-powered querying of FHIR repositories. Automated dashboards enabled near real-time visualization of clinical and operational metrics, reducing manual data handling. AI-driven insights generated contextual summaries and recommendations, supporting exploratory analysis and clinical decision-making in training scenarios. The use of FHIR standards ensured interoperability across heterogeneous healthcare systems, allowing scalable integration without custom data mappings. Overall, the proof-of-concept indicated that combining Generative AI with standardized FHIR data can enhance data accessibility, analytical efficiency, and decision support in clinical trial environments.
Conclusion
This study demonstrates that integrating Generative AI with FHIR standards offers a scalable and interoperable approach for real-time clinical trial analytics and intelligent decision support. By enabling seamless data exchange, automated visualization, and AI-driven insights, the proposed framework addresses key challenges related to fragmented healthcare data and limited interoperability. The approach has strong potential to enhance clinical training and trial operations by improving efficiency, data accessibility, and analytical depth. Future work should focus on expanding real-world trial use cases, improving AI interpretability, and incorporating privacy-preserving techniques to support secure and compliant data utilization.
