LLM
NYUTron
NYU Langone clinical language model for EHR prediction. Readmission AUC 79.87% (temporal test) and 78.70% (prospective); in-hospital mortality AUC 94.9%. Deployed through the EHR over HL7 FHIR from January to April 2022.
Levelmodel
ClassLLM
Parameters109M
Contextnot in the notes
Released7 Jun 2023
Opennessproprietary
Runs onnot in the notes
Statusnot in the notes
Industry Use Cases
Healthcare
EHR predictionR&D Topics
Deployments
NYU LangoneresearchUSAJan 2022
Prospective trial over 29,286 discharges via EHR (HL7 FHIR), Jan to Apr 2022; prospective readmission AUC 78.70%
EHR predictionacademic papernature.comWhere this comes from
From G13, the deployment rows of T08 to T10, and the Indonesian-language search of 11 October 2026. An outcome claim is the organisation's own unless the evidence type says independent report.
Identity
- Developer
- NYU Langone
- Family
- not in the notes
- Released
- 7 Jun 2023 sourcesnotes
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer BERT-style clinical encoder trained on 4.1B words of clinical notes
- Total parameters
- 109M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- proprietary
- Licence
- not in the notes sources
- Access routes
- internal only
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Links
DeveloperNYU Langoneuniversity, USA
NYU Langoneuniversity, USAModelNYUTronNYU Langone, LLM
NYUTronNYU Langone, LLMR&D TopicsDomain Adaptation (Vertical Models)
Use CasesEHR PredictionHealthcare
Who Runs ItNYU LangoneResearch, Jan 2022
NYU LangoneResearch, Jan 2022Use cases 1
Organisations 1
Deployments 1
Sources
- Client Challenge nature.com https://www.nature.com/articles/s41586-023-06160-y
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "NYUTron", https://aurion.semai.id/models/nyu-langone-nyutron/, records of October 2026.