Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks

Research data management in biomedical and machine learning applications

A Python package for standardizing medical data

watchlib is a Python module providing tools for loading, analyzing and visualizing Apple Watch health data.

HL7 FHIR client library. Sync and async crud operations against R4 FHIR servers. Resource validation & serialization

This repository includes API to get ICD-10 codes from descriptions. The Model is a transformer based on BERT. The embeddings are being finetuned based on the following paper: https://arxiv.org/abs/1904.03323 .

Extractive summarizationof medical transcriptions

ScrapeMed: Data scraping for PubMed Central.

Risk Factor Analysis for Medical Data, Open-source Machine Learning Platform

The code used to collect data about medical journal papers with at least 1 student author since 2012

Get started building safe, reliable, and production-grade multi-agent systems for medical applications!

https://arxiv.org/abs/2201.06499

Approach for the MEDDOPROF (Medical Documents Profession Recognition) competition on spanish data.

CANINE for Medical Natural Language Inference on MedNLI data, as part of the Algorithms for Speech and NLP course of the MVA master program.

In this project, we propose to deal with the data scarcity problem in a specific NLP task by harnessing existing annotated datasets from related tasks. Our approach involves training a multi-head architecture concurrently on both the main task and these “supporting” tasks. We experimented this approach on medical NLP tasks and on three GLUE tasks.

Question-Answering Model for Schizophrenia Symptoms and Their Impact on Daily Life using Mental Health Forums Data (https://arxiv.org/abs/2310.00448)

This project implements a machine learning-based triage system for emergency rooms, which classifies patients based on their symptoms and vitals using a Random Forest Classifier. The system features real-time patient data integration, a user-friendly GUI built with Tkinter, and secure patient data encryption using Fernet from the cryptography lib

This is a fast API requester for fetching data from the cancer imaging archive