A.1 Motivation For what purpose was the dataset created?

This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant (No.2019-0-00075, Artificial Intelligence Graduate School Program(KAIST)), National Research Foundation of Korea (NRF) grant (NRF2020H1D3A2A03100945) andDataVoucher grant(2021-DV-I-P-00114), funded bythe Koreagovernment(MSIT). The dataset contains question-SQL pairs if the question is answerable. Are relationships between individual instances made explicit (e.g., users' movie ratings, socialnetworklinks)? N/A. Arethereanyerrors,sourcesofnoise,orredundanciesinthedataset? Question templates are created to have slots that are later filled with pre-defined values and records from the database. EHRSQL is based on patients in MIMIC-III and eICU.

A.1 Motivation For what purpose was the dataset created?

The following section is answers to questions listed in datasheets for datasets. A.1 Motivation For what purpose was the dataset created? Who created the dataset (e.g., which team, research group) and on behalf of which entity Who funded the creation of the dataset? This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant (No.2019-0-00075, Artificial Intelligence Graduate School Program(KAIST)), National Research Foundation of Korea (NRF) grant (NRF-2020H1D3A2A03100945) and Data V oucher grant (2021-DV -I-P-00114), funded by the A.2 Composition What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)? EHRSQL contains natural questions and their corresponding SQL queries (text). How many instances are there in total (of each type, if appropriate)? There are about 24.4K instances (22.5K answerable; 1.9K unanswerable). We conducted a poll at a university hospital and collected a wide range of questions frequently asked on the structured EHR data. What data does each instance consist of? The dataset contains question-SQL pairs if the question is answerable.

We present a new text-to-SQL dataset for electronic health records (EHRs). The utterances were collected from 222 hospital staff members, including physicians, nurses, and insurance review and health records teams. To construct the QA dataset on structured EHR data, we conducted a poll at a university hospital and used the responses to create seed questions. We then manually linked these questions to two open-source EHR databases, MIMIC-III and eICU, and included various time expressions and held-out unanswerable questions in the dataset, which were also collected from the poll. Our dataset poses a unique set of challenges: the model needs to 1) generate SQL queries that reflect a wide range of needs in the hospital, including simple retrieval and complex operations such as calculating survival rate, 2) understand various time expressions to answer time-sensitive questions in healthcare, and 3) distinguish whether a given question is answerable or unanswerable. We believe our dataset, EHRSQL, can serve as a practical benchmark for developing and assessing QA models on structured EHR data and take a step further towards bridging the gap between text-to-SQL research and its real-life deployment in healthcare. EHRSQL is available at https://github.