CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain

Researchers introduce CBR-to-SQL, a new framework using Case-Based Reasoning to improve natural language-to-SQL translation for healthcare databases. The system addresses limitations of standard RAG approaches by using two-stage retrieval and abstract case templates, achieving state-of-the-art results on medical datasets.

• →CBR-to-SQL framework improves upon standard RAG approaches for converting natural language questions to SQL queries in healthcare.
• →The system uses Case-Based Reasoning with two-stage retrieval to handle medical terminology variability and noise.
• →Achieves state-of-the-art logical form accuracy and competitive execution accuracy on MIMICSQL dataset.
• →Demonstrates higher sample efficiency and robustness compared to traditional RAG methods.
• →Addresses the barrier of SQL expertise requirement for healthcare professionals analyzing EHR databases.