Text2Cohort: Democratizing the NCI Imaging Data Commons with Natural Language Cohort Discovery

The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data and tools for analysis, with the goal of facilitating collaboration in medical imaging research. However, querying the IDC database for cohort discovery and access to imaging data has a significant learning curve for researchers due to its complex and technical nature. We developed Text2Cohort, a large language model (LLM) based toolkit to facilitate natural language cohort discovery by translating user input into IDC database queries through prompt engineering and returning the query's response to the user. Furthermore, autocorrection is implemented to resolve syntax and semantic errors in queries by passing the errors back to the model for interpretation and correction. We evaluate Text2Cohort on 50 natural language user inputs ranging from information extraction to cohort discovery. The resulting queries and outputs were verified by two computer scientists to measure Text2Cohort's accuracy and F1 score. Text2Cohort successfully generated queries and their responses with an 88% accuracy and F1 score of 0.94. However, it failed to generate queries for six user inputs due to syntax and semantic errors. Our results indicate that Text2Cohort succeeded at generating queries with correct responses, but occasionally failed due to a poor understanding of the data schema. Despite these shortcomings, Text2Cohort demonstrates the utility of LLMs to enable researchers to discover and curate cohorts using data hosted on IDC with incredible accuracy using natural language in a more intuitive and user-friendly way, thus democratizing access to the IDC.