Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL

Yifei Shen∗, Yilun Zhao∗, Justice Ou, Tinglin Huang, Arman Cohan

EACL 2026 Main (Oral)

Overview of the ClinSQL construction pipeline, from scenario design and patient selection through query annotation, gold SQL, and data validation

ClinSQL evaluates models on clinically grounded text-to-SQL tasks that require temporal reasoning and patient-similarity cohort construction.