From d0ffa499e85a8b84d8d54152e4dae275f60d91ab Mon Sep 17 00:00:00 2001 From: mart-r Date: Tue, 7 Oct 2025 11:16:22 +0100 Subject: [PATCH 1/6] CU-869ar9dcf: Update README to include available models. Now including v2 models on the v2 demo as well as list of v1 models and guidance on model conversion --- medcat-v2/README.md | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/medcat-v2/README.md b/medcat-v2/README.md index b0465b36..8c6fe44b 100644 --- a/medcat-v2/README.md +++ b/medcat-v2/README.md @@ -18,10 +18,23 @@ Details on breaking are outlined [here](docs/breaking_changes.md). ## Available Models -As MedCAT v2 is still in early release, we do not currently have any models publically available. -You can still use models for v1, however (see the [README](https://github.com/CogStack/cogstack-nlp/blob/main/medcat-v2/README.md) there). +We have 2 public v2 models available: +1) SnomedCT UK Clinical edition 39.0 (Oct 2024) and UK Drug Extension 39.0 (July 2024) based model enriched with UMLS 2024AA; trained only on MIMIC-IV +2) SnomedCT UK Clinical edition 40.2 (June 2025) and UK Drug Extension 40.3 (July 2024) based model enriched with UMLS 2024AA; trained only on MIMIC-IV -If you wish you can also convert the v1 models into the v2 format (see [tutorial](https://github.com/CogStack/cogstack-nlp/blob/main/medcat-v2-tutorials/notebooks/introductory/migration/1._Migrate_v1_model_to_v2.ipynb)). +We also have a number of MedCAT v1 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](https://github.com/umcu/dutch-umls) trained on Dutch medical wikipedia articles and a negation detection model [repository](https://github.com/umcu/negation-detection/)/[paper](https://doi.org/10.48550/arxiv.2209.00470) trained on EMC Dutch Clinical Corpus). +4) UMLS Full. >4MM concepts trained self-supervised on MIMIC-III. v2022AA of UMLS. +5) The same 2024 based model as above in v1 format +6) The same 2025 based model as above in v1 format + +To download any of these models, please [follow this link](https://uts.nlm.nih.gov/uts/login?service=https://medcat.sites.er.kcl.ac.uk/auth-callback) (or [this link for API key based download](https://medcat.sites.er.kcl.ac.uk/auth-callback-api)) 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. + +While we encourage you use MedCAT v2 and the models in that native format, if you download an older version MedCAT v2 will be able to load it and covnert it to the format it knows. However, the loading process will be considerably longerin those cases. + +If you wish you can also convert the v1 models into the v2 format (see [tutorial](medcat-v2-tutorials/notebooks/introductory/migration/1._Migrate_v1_model_to_v2.ipynb)). ```python from medcat.utils.legacy import legacy_converter From 28a319313886f0d7980223260acf5713a319569a Mon Sep 17 00:00:00 2001 From: mart-r Date: Tue, 7 Oct 2025 11:16:54 +0100 Subject: [PATCH 2/6] CU-869ar9dcf: Update demo link in README --- medcat-v2/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/medcat-v2/README.md b/medcat-v2/README.md index 8c6fe44b..48c86017 100644 --- a/medcat-v2/README.md +++ b/medcat-v2/README.md @@ -87,7 +87,7 @@ pip install "medcat[spacy,meta-cat,deid,rel-cat,dict-ner]~=2.0.0" # for all of ## Demo -The MedCAT v2 demo web app is available [here](https://medcatv2.sites.er.kcl.ac.uk/). +The MedCAT v2 demo web app is available [here](https://medcat.sites.er.kcl.ac.uk/). ## Tutorials A guide on how to use MedCAT v2 is available at [MedCATv2 Tutorials](https://github.com/CogStack/cogstack-nlp/tree/main/medcat-v2-tutorials). From 0578a9584e1b061a397cc533fdcb5b92bebd39e7 Mon Sep 17 00:00:00 2001 From: mart-r Date: Tue, 7 Oct 2025 11:17:58 +0100 Subject: [PATCH 3/6] CU-869ar9dcf: Update tutorials link to relative link --- medcat-v2/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/medcat-v2/README.md b/medcat-v2/README.md index 48c86017..fb83c95f 100644 --- a/medcat-v2/README.md +++ b/medcat-v2/README.md @@ -90,7 +90,7 @@ pip install "medcat[spacy,meta-cat,deid,rel-cat,dict-ner]~=2.0.0" # for all of The MedCAT v2 demo web app is available [here](https://medcat.sites.er.kcl.ac.uk/). ## Tutorials -A guide on how to use MedCAT v2 is available at [MedCATv2 Tutorials](https://github.com/CogStack/cogstack-nlp/tree/main/medcat-v2-tutorials). +A guide on how to use MedCAT v2 is available at [MedCATv2 Tutorials](medcat-v2-tutorials). However, the tutorials are a bit of a work in progress at this point in time. From 14705fadf9356aa92d43625777729c4d9f7a58c2 Mon Sep 17 00:00:00 2001 From: mart-r Date: Tue, 7 Oct 2025 11:20:07 +0100 Subject: [PATCH 4/6] CU-869ar9dcf: Update README with note/news of new models --- medcat-v2/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/medcat-v2/README.md b/medcat-v2/README.md index fb83c95f..21e50caf 100644 --- a/medcat-v2/README.md +++ b/medcat-v2/README.md @@ -51,6 +51,7 @@ new_model_folder = "models" # file in this folder ``` ## News +- **New public 2024 and 2025** Snomed models were uploaded and made available 7. October 2025. - **MedCAT 2.0.0** was released 18. August 2025.