CogStack Natural Language Processing offers tools to process and extract information from clinical text and documents in Electronic Health Records (EHRs).

The primary NLP focus is the Medical Concept Annotation Tool (MedCAT), a self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT. See the paper on arXiv.

Official Docs here

Discussion Forum discourse

• Medical Concept Annotation Tool: MedCAT can be used to extract information from Electronic Health Records (EHRs) and link it to biomedical ontologies like SNOMED-CT, UMLS, or HPO (and potentially other ontologies).
• Medical Concept Annotation Tool Trainer: MedCATTrainer is an interface for building, improving and customising a given Named Entity Recognition and Linking (NER+L) model (MedCAT) for biomedical domain text.
• MedCAT Service: A REST API wrapper for MedCAT, allowing you to send text for processing and receive structured annotations in response.

• Deidentify app: Demo for AnonCAT. It uses MedCAT, an advanced natural language processing tool, to identify and classify sensitive information, such as names, addresses, and medical terms.
• MedCAT Demo App: A simple web application showcasing how to use MedCAT for clinical text annotation.
• MedCAT Tutorials: The MedCAT Tutorials privde an interactive learning path for using MedCAT