Large Language Models Blog

High-Accuracy Clinical Term Mapping to Standard Medical Terminologies (ICD-10, RxNorm, SNOMED, and 90+ vocabularies) with John Snow Labs’ Medical Language Models

by

Ozgur Caglayan

High-Accuracy Clinical Term Mapping to Standard Medical Terminologies (ICD-10, RxNorm, SNOMED, and 90+ vocabularies) with...

Generate DICOM de-identification pipelines with the Visual NLP DICOM Skill

by

Nitin Kumar

DICOM de-identification is workflow-specific because PHI can appear in metadata tags, free-text metadata fields, burned-in image pixels, and encapsulated PDF content. A production pipeline may need to inspect tags, apply...

Generative AI Lab Turns Extracted Entities into Standard Medical Codes

by

Aleksei Zakharov

Medical code resolution maps an entity extracted from clinical text to a concept in a standard terminology. For example, "type 2 diabetes mellitus without complications" maps to E11.9 in ICD-10-CM....

Agentic Workflow Design Lets a Small Medical Model Compete with Frontier LLMs

by

Mahmood Bayeshi

Hand a language model a difficult clinical case and it will hand you a diagnosis. Quickly, fluently, with an air of total certainty. Quite often it will also be wrong,...

John Snow Labs and 3Aware Announce Partnership to Deliver Multimodal De-Identification Inside the 3Aware Evidence Vault

by

Gina Devine

John Snow Labs announced a formal partnership with 3Aware to integrate our world-class multimodal de-identification capabilities directly into the 3Aware Evidence Vault. This collaboration enables health systems to unlock governed,...