AI-Ready Multimodal Data Pipeline to Enrich Cancer Care
This study reports on the progress in designing and developing a framework for integrating heterogeneous datasets—structured, semi-structured, and unstructured—into an AI-ready multimodal data pipeline aimed at predicting radiation therapy interruptions (RTI) and enhancing patient care navigation. The AI-Ready dataset incorporates a broad set of information, including patient demographics, health data, clinical notes, medical imaging, and data on social determinants of health. Preliminary results indicate that this pipeline effectively integrates diverse distributed data sources, providing a foundation for training AI models capable of generating reliable and actionable predictions.
Authors
- Caroline Brett (ORCID: https://orcid.org/0000-0002-5680-2948)
- Rezaur Rashid (ORCID: https://orcid.org/0000-0003-1343-5364)
- Brianna M White (ORCID: https://orcid.org/0000-0001-7576-5874)
- Janet A. Zink (ORCID: https://orcid.org/0000-0002-0261-4917)
- Arash Shaban‐Nejad (ORCID: https://orcid.org/0000-0003-2047-4759)
- Lokesh K. Chinthala (ORCID: https://orcid.org/0000-0002-1258-8353)
- Fekede Asefa Kumsa (ORCID: https://orcid.org/0000-0002-6700-4810)
- Soheil Hashtarkhani (ORCID: https://orcid.org/0000-0001-7750-6294)
- Robert Lowell Davis (ORCID: https://orcid.org/0000-0001-8807-0019)
- David L. Schwartz (ORCID: https://orcid.org/0000-0002-7235-5586)
Institutions
- University of Tennessee Health Science Center (US)
- University of Tennessee at Knoxville (US)
Publication Details
- Published
- 2024-12-15
- DOI
- https://doi.org/10.1109/bigdata62323.2024.10825353
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- HORIZON EUROPE Health