Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information beyond the database's scope or exceed the system's capabilities. In this paper, we introduce a novel text-to-SQL framework that robustly handles out-of-domain questions and verifies the generated queries with query execution.Our framework begins by standardizing the structure of questions into a templated format. We use a powerful large language model (LLM), fine-tuned GPT-3.5 with detailed prompts involving the table schemas of the EHR database system. Our experimental results demonstrate the effectiveness of our framework on the EHRSQL-2024 benchmark benchmark, a shared task in the ClinicalNLP workshop. Although a straightforward fine-tuning of GPT shows promising results on the development set, it struggled with the out-of-domain questions in the test set. With our framework, we improve our system's adaptability and achieve competitive performances in the official leaderboard of the EHRSQL-2024 challenge.
@article{arxiv.2406.00014,
title = {KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR},
author = {Hajung Kim and Chanhwi Kim and Hoonick Lee and Kyochul Jang and Jiwoo Lee and Kyungjae Lee and Gangwoo Kim and Jaewoo Kang},
journal= {arXiv preprint arXiv:2406.00014},
year = {2024}
}