Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets

Abstract: Electronic medical records (EMRs) are stored in relational databases. It can be challenging to access the required information if the user is unfamiliar with the database schema or general database fundamentals. Hence, researchers have explored text-to-SQL generation methods that provide healthcare professionals direct access to EMR data without needing a database expert. However, currently available datasets have been essentially "solved" with state-of-the-art models achieving accuracy greater than or near 90%. In this paper, we show that there is still a long way to go before solving text-to-SQL generation in the medical domain. To show this, we create new splits of the existing medical text-to-SQL dataset MIMICSQL that better measure the generalizability of the resulting models. We evaluate state-of-the-art LLMs on our new split showing substantial drops in performance with accuracy dropping from up to 92% to 28%, thus showing substantial room for improvement. Moreover, we introduce a novel data augmentation approach to improve the generalizability of the LLMs. Overall, this paper is the first step towards developing more robust text-to-SQL models in the medical domain.\footnote{The dataset and code will be released upon acceptance.