Sam Schifman - RAG on FHIR with Knowledge Graphs: Using FHIR with Generative AI | DevDays 2024 скачать в хорошем качестве

Sam Schifman - RAG on FHIR with Knowledge Graphs: Using FHIR with Generative AI | DevDays 2024

Generative AI / LLMs have amazing potential to revolutionize many aspects of life. However, they have many flaws, including the limitations imposed by the data they are trained on. These limitations are especially important in healthcare; people are understandably reluctant to allow their health data to be used in Machine Learning (ML). Retrieval-augmented Generation (RAG) offers a possible solution, by providing the data with the question instead of during training. However, to do this, health data needs to be in a form that can be consumed by RAG. FHIR is already a great start, because it breaks the data into consumable chunks (resources), but those chunks are not easily consumable by RAG. This talk outlines some ways that FHIR could be transformed to make it more accessible for RAG. Additionally, it covers how Knowledge Graphs and NLP can enhance the process and lead to better results.