Case Study - Named Entity Recognition for Medical Texts

In one project, our employees managed to improve the performance of Named Entity Recognition for Swedish medical texts.

Client
Sahlgrenska Universitetssjukhuset
Year
Service
Machine Learning

Overview

In that digital age, data has become an important asset, but in our Swedish healthcare system, there is an enormous amount of invaluable information locked in text form, in patient records. Transforming this unstructured information into useful data poses a major challenge.

But that's where a project comes in, carried out by two of our current employees, with the goal of efficiently extracting valuable data from Swedish patient records using Named Entity Recognition (NER).

In the work, several different BERT models and techniques for data augmentation (data augmentation) were investigated, which have the potential to significantly improve the results of NER on Swedish patient records.

The result showed that the data augmentation could significantly improve the performance of the system, especially when handling smaller data sets. Interestingly, we were also able to achieve comparable results by boosting 50% of the training data as using the entire original data set without boosting.

This project shows how the right technology and methods can help us extract valuable information from Swedish patient records, which can contribute to a more enlightened and data-driven healthcare.

What we did

  • Machine Learning
  • Data Augmentation
  • Pytorch
  • Python

It was incredibly rewarding to work on this project with Sahlgrenska. Not only it gave us the chance to contribute to better healthcare, but we could also explore and apply new techniques to improve performance within text extraction.

Lucas Rosvall
Software Engineer

Fler kundcase

ChainSec: Cybersecurity for supply chains

In this project, we developed a SaaS solution designed to automate and improve cybersecurity in corporate supply chains by offering tools for continu...

Fortsätt läsa

Chatbot for Dialogue with Technical Manuals

In this project, we acted as an external party and developed an AI-driven chatbot as a Proof of Concept, specifically designed to facilitate service ...

Fortsätt läsa

Vill du se din idé bli verklighet?

Är du redo att börja ett långsiktigt samarbete? Hör av dig så pratar vi om hur vi kan stödja din resa.

Kontor


  • Kungsgatan 4
    411 19 Göteborg