NeurIPS paper: Discrete Neural Interlingua enables ontology-agnostic EHR modeling across hospitals
AI4Pathology · x · 2026-10-29
A NeurIPS 2026-accepted paper, "Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling," tackles cross-hospital EHR generalization.
- Problem: the same clinical concept may appear as an ICD code, SNOMED term, local identifier, or free text, and standard EHR tokenizers treat each as unrelated symbols — a model trained on MIMIC-III with a closed vocabulary can use only 13% of eICU events. Even within one hospital, "acute kidney injury" appears as a billing code, a flowsheet identifier, and note text.
- Approach: learn a discrete neural interlingua mapping clinical concepts across ontologies into a shared representation.
- Paper, code and model are released; from the AI4Pathology team.
More from Research
- Study: ~24% of crawlable web pages now contain AI-generated or edited text — omarsar0 · 2026-10-29
- Machenta teaches a three-robot assembly line in 2 minutes with sim-trained model — Ed__Johns · 2026-10-29
- 100% in sim, 0/11 real robot inserts: joint team exposes benchmark inflation in GPT-6-Astra eval — jiqizhixin · 2026-10-29
- GPT re-analysis shows DeepSeek's agent training gains were understated: +9.7 normalized, +172 human pref — teortaxesTex · 2026-10-29
- "Knowledge cartridges" for a frozen 72B model: pull the cartridge and the AI honestly says "I don't know" — Nearby_Indication474 · 2026-10-29
- Reverse Turing test for speech: humans score 0.71 vs Gemini 0.54 in cocktail-party transcription — cloud_kj · 2026-10-29