Discovering Related Clinical Concepts using Large Amounts of Clinical Notes. An unsupervised graphical approach to mine related concepts by leveraging the volume within large amounts of clinical notes.

SpaCy component for modifying the string of a doc before tokenizing.

A spaCy component for executing custom logic at the end of a pipeline.

A Python implementation of the ConText algorithm for clinical text concept assertion using the spaCy framework

A rule-based Python module for spitting documents into sections.

Multitask Learning with Pretrained Transformers

MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain (ACL-IJCNLP '21)

Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation

Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text, ClinicalNLP workshop at EMNLP 2020

Application to analyze clinical texts input by users to extract symptoms and treatments. Created with React, Java and Python.

Detecting the functioning level of a patient from a free-text clinical note in Dutch.

AskDocs: A medical QA dataset

Off-the-Shelf Ensemble Systems

CLIFT : Analysing Natural Distribution Shift on Question Answering Models in Clinical Domain

Extract context modifiers targeting clinical terms

Instructions and code to create for a table of UMLS, SNOMED or HPO concepts containing Dutch medical names, usable in named entity recognition and linking methods such MedCAT.

The project is in the incubation stage and still under development. ForteHealth is a flexible and powerful ML workflow builder for biomedical and clinical scenarios. This is part of the CASL project: http://casl-project.ai/

Estimate sentiment in clinical notes via keywords or deep learning models

[NLPMC 2023] "Dr LLM, what do I have?": The Impact of User Beliefs and Prompt Formulation on Health Diagnoses