DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries

Abstract

This paper develops the first question answering dataset (DrugEHRQA) containing question-answer pairs from both structured tables and unstructured notes from a publicly available Electronic Health Record (EHR). EHRs contain patient records, stored in structured tables and unstructured clinical notes. The information in structured and unstructured EHRs is not strictly disjoint: information may be duplicated, contradictory, or provide additional context between these sources. Our dataset has medication-related queries, containing over 70,000 question-answer pairs. To provide a baseline model and help analyze the dataset, we have used a simple model (MultimodalEHRQA) which uses the predictions of a modality selection network to choose between EHR tables and clinical notes to answer the questions. This is used to direct the questions to the table-based or text-based state-of-the-art QA model. In order to address the problem arising from complex, nested queries, this is the first time Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (RAT-SQL) has been used to test the structure of query templates in EHR data. Our goal is to provide a benchmark dataset for multi-modal QA systems, and to open up new avenues of research in improving question answering over EHR structured data by using context from unstructured clinical data.

Evaluation of Search Methods on Community Documents

“…Therefore, there is a need for evaluating the quality of the user search experience when searching for information. And this is especially necessary because of the emergence and popularity of new search techniques such as Elastic search [16] [26], Question Answering over free text [3] [6] [4] [2], and Question Answering over knowledge graphs [8] [9] [27] [30]. The search techniques are one-field one-shot search i.e users retrieve information by building a question/query through only a text field and receive the answer in response.…”

EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records

“…The records cover a wide range of clinical knowledge, from individual-level information to group-level insight, in various forms, including tables, text, and images [16,17,11,15]. As a vast and comprehensive knowledge base, hospital staff, including physicians, nurses, and administrators, constantly interact with EHRs to store and retrieve patient information to make better clinical decisions [32,3].…”