Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries

TL;DR

This paper presents QDT, a privacy-preserving method for tabular prediction from EHR data that uses LLM-generated SQL queries to infer from aggregate statistics without accessing individual records.

Contribution

QDT introduces a novel inference-time-only approach that leverages LLMs to generate SQL queries for privacy-compliant, interpretable, and effective prediction from structured health data.

Findings

Achieved F1=0.70 on hospital readmission prediction, outperforming TabPFN.

Enables prediction without supervised training or access to individual data.

Provides interpretable, schema-aware, aggregate-based inference.

Abstract

Electronic health records (EHRs) contain richly structured, longitudinal data essential for predictive modeling, yet stringent privacy regulations (e.g., HIPAA, GDPR) often restrict access to individual-level records. We introduce \textbf{Query, Don't Train} (QDT): a \textbf{structured-data foundation-model interface} enabling \textbf{tabular inference} via LLM-generated SQL over EHRs. Instead of training on or accessing individual-level examples, QDT uses a large language model (LLM) as a schema-aware query planner to generate privacy-compliant SQL queries from a natural language task description and a test-time input. The model then extracts summary-level population statistics through these SQL queries, and the LLM performs chain-of-thought reasoning over the results to make predictions. This inference-time-only approach enables prediction without supervised model training, ensures interpretability through symbolic, auditable queries, naturally handles missing features without imputation or preprocessing, and effectively manages high-dimensional numerical data to enhance analytical capabilities. We validate QDT on the task of 30-day hospital readmission prediction for Type 2 diabetes patients using a MIMIC-style EHR cohort, achieving F1 = 0.70, which outperforms TabPFN (F1 = 0.68). To our knowledge, this is the first demonstration of LLM-driven, privacy-preserving structured prediction using only schema metadata and aggregate statistics -- offering a scalable, interpretable, and regulation-compliant alternative to conventional foundation-model pipelines.