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

arXiv: https://arxiv.org/abs/2505.21801 · HTML: https://mlsanity.com/paper/2505.21801/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2025.

## Built on by (most cited first, 5 of 5)

- [Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning](https://mlsanity.com/paper/2509.02401/) (2025)
- [STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing](https://mlsanity.com/paper/2506.21575/) (2025)
- [Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents](https://mlsanity.com/paper/2605.09698/) (2026)
- [Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization](https://mlsanity.com/paper/2605.06308/) (2026)
- [Concordia: Self-Improving Synthetic Tables for Federated LLMs](https://mlsanity.com/paper/2605.09855/) (2026)

## Abstract (arXiv)

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 Query, Don't Train (QDT): a structured-data foundation-model interface enabling 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.