Skip to content

Final project on 'Healthcare Summarization of Clinical Notes in MIMIC-III' developed as part of the Big Data Engineering course by Prof. Vincenzo Moscato, University of Naples 'Federico II', 2022-23

Notifications You must be signed in to change notification settings

LaErre9/HealthcareSummarizationMIMIC

 
 

Repository files navigation

🩺 Healthcare Summarization in MIMIC-III

The project aims at the extraction of semi-structured textual data (interrelated clinical notes) generated by competent healthcare professionals, within the MIMIC-III database (noteevents). These data will undergo Summarization and Named Entity Recognition + Entity Linking + Relation Extraction processes in order to generate a comprehensive report summarizing the patient's medical history.

  • 📖 Full Documentation in Italian 🇮🇹 Read
  • 📄 Research Papers in English 🇬🇧 for ITADATA2023/calls Read

⚙️ Project Workflow

Mongo DB

🛠️ Tools used

Mongo DB OpenAI Neo4J MedCat Python MedCat

🗊 Extract final demo report of the 'Healthcare Summarization' solution

Demo.Healthcare.Summarization.mp4

⚠️ Warning

It is essential to note that MIMIC-III contains sensitive patient data and, therefore, must be handled with the utmost care and in compliance with privacy regulations and institutional policies. Before using the dataset, carefully review and adhere to the guidelines provided by the MIMIC team and consult your local ethics committee.

✅ Project realised for demonstration and educational purposes only

Copyright © 2023 - Healthcare Summarization project carried out for the Big Data Engineering exam held at the University of Naples, Federico II. Realised for demonstration and teaching purposes only.
Antonio Romano, Giuseppe Riccio, Michele Cirillo, Andriy Korsun

About

Final project on 'Healthcare Summarization of Clinical Notes in MIMIC-III' developed as part of the Big Data Engineering course by Prof. Vincenzo Moscato, University of Naples 'Federico II', 2022-23

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 94.7%
  • Python 5.3%