Is there some guides or examples to help implement MedCAT in other language other than English?

MedCAT
1

My aim is to implement MedCAT to applied to Thai language (in fact, multi-language of Thai and English).
I have search through the forum and someone mentioned that there are some users had implemented in Dutch, french, spanish, korean and chinese (Why use medcat over ctakes?). I tried to search for Github or some sources, but cannot find any examples.

2

That is correct, in terms if the wide variety of languages used.
It is just that people do not generally share models that they have created and trained.

If anyone does want to share models please contact contact@cogstack.org and an official hub or something can be created if there is enough demand. :smiley:

We currently only have 4 public models available:

  1. UMLS Small (A modelpack containing a subset of UMLS (disorders, symptoms, medications…). Trained on MIMIC-III)
  2. SNOMED International (Full SNOMED modelpack trained on MIMIC-III)
  3. UMLS Dutch v1.10 (a modelpack provided by UMC Utrecht containing UMLS entities with Dutch names trained on Dutch medical wikipedia articles and a negation detection model repository/paper trained on EMC Dutch Clinical Corpus).
  4. UMLS Full. >4MM concepts trained self-supervsied on MIMIC-III. v2022AA of UMLS.

To download any of these models, please follow this link and sign into your NIH profile / UMLS license. You will then be redirected to the MedCAT model download form. Please complete this form and you will be provided a download link.

The rest of the models are propriety owed by the organisation/s that train them on their data.

Are you a seeking to creating a Thai MedCAT model? Im sure one of us from the team will be willing to help!

2 Likes
3

If you are attending the meet up at the Thai embassy in London this weekend, do connect up with me then and we can explore how to help you.

4

Hello, Prof. James Teo. Dr. Jo (also known as s2p2) is a fellow doctor at Siriraj Hospital. Unfortunately, he is based in Thailand so he cannot join with us this Saturday, and we are currently working on developing Thai Medical NLP for our country. Dr. Jo is in the process of implementing MedCAT in the Thai language. In fact, we also have a few doctors and medical students who working on this project such as Dr. Kanyakorn Veerakanjana, a PhD student of Prof. Richard Dobson. However, she is primarily focusing on wearable device development at the moment.

We are newcomers in this field, and we are all learning from Dr. Anthony’s teachings. Thank you for recommending that I meet with Dr. Anthony.

In conclusion, I will discuss further with Dr. Jo and provide more details to you this coming weekend. Thank you once again, Prof. James and Dr. Anthony.

3 Likes