aceLarge Language Model-Generated Synthetic Data for Parole and Probation Detection in Clinical Notes: Development and Evaluation Study
Background Identifying individuals on parole or probation can help inform care pathways and ensure continuity of care in health care systems. However, this sensitive justice-related information is often absent from structured electronic health record fields and is instead documented in narrative clinical notes. Developing automated parole and probation detection (PPD) systems typically requires expert-annotated clinical data, but manual annotation is costly, time-consuming, and constrained by data sparsity and p…
Training only on LLM-generated synthetic notes let models detect parole or probation status in real Veterans Affairs notes, beating rule-based baselines without expert-annotated training data.
Real-world performance was assessed on only 293 expert-annotated notes from a single source, the US Department of Veterans Affairs, so generalization beyond that setting is not established.
Evidence
- Peer-reviewedJMIR AI2026-10-19
How should this claim be treated?
Truvace Impact Record TRV-2026-2081, v1: “Large Language Model-Generated Synthetic Data for Parole and Probation Detection in Clinical Notes: Development and Evaluation Study.” Truvace, 2026-10-21. /record/TRV-2026-2081 (accessed at citation time). sha256 2561db4aacf6015f…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-2081 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.