Auditable Emergency Triage for Maternal and Newborn Care in India

Not provided in the abstract

emergency triagelarge language modelrule-based systemauditability

2609.09356

Builder Relevance

80%

1h ago

Abstract

A system was built to improve emergency triage for maternal and newborn care by using a large language model and a deterministic rule engine.

Reality Card

Core Claim

The new triage system improved recall from 0.565 to 0.810 and F1 from 0.606 to 0.702 while allowing clinical experts to independently add rules without causing regressions.

Method / Result

The system triaged 152,421 patient queries and flagged 28,535 (18.7%) as emergencies.

Limitations

The initial system was opaque, making it difficult to analyze mistakes and requiring costly evaluations for prompt changes.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers