TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

The Forecast Had to Cite Evidence for a Future Code

A bounded research workflow combined an EHR prior, medical search and code dictionaries before ranking next-encounter diagnoses.

Published Updated Story ID: mp-2026-08-19-007
Read the complete editionStory JSON

Summary

A bounded research workflow combined an EHR prior, medical search and code dictionaries before ranking next-encounter diagnoses.

ICD-Deepresearch predicts diagnosis codes that may appear at a future visit, where no source can reveal the answer in advance. It expands candidates from an EHR foundation model, adds a separate direct forecast, validates exact code semantics and writes rationales only after selection. Patient-averaged precision remained about 25 percent, while recall reached 35.09 percent on MIMIC-III and 48.32 percent on MIMIC-IV; physicians nevertheless rated its retrieved documents more useful than the standalone research comparisons.

Why it matters

A bounded research workflow combined an EHR prior, medical search and code dictionaries before ranking next-encounter diagnoses.

Limits and context

  • It expands candidates from an EHR foundation model, adds a separate direct forecast, validates exact code semantics and writes rationales only after selection.

Key claims

  1. A bounded research workflow combined an EHR prior, medical search and code dictionaries before ranking next-encounter diagnoses.

    Qualification: It expands candidates from an EHR foundation model, adds a separate direct forecast, validates exact code semantics and writes rationales only after selection.

    Evidence: source-2026-08-19-007

Sources

  1. arXiv preprint 2608.17075arXiv · primary research

Corrections

No corrections have been recorded for this story.