Swedish Medical Language Data Lab
|Coordinator||Sahlgrenska Science Park AB|
|Funding from Vinnova||SEK 1 913 272|
|Project duration||December 2019 - December 2021|
|Call||Data lab and data factory as national resource 2020|
Purpose and goal
Svenskt Medicinskt Språkdatalabb is to be a national experimental workshop with the aim to make medical language data sets available for use in health care, dental care and data-driven research and innovation in the life science sector. The project has a clear user focus and goal to develop language models as well as technical, legal and ethical processes that enable the sharing of sensitive training data for AI solutions in the life science sector.
Expected results and effects
The project is to create: A national Swedish medical language database with a long-term plan for ownership and operation. A growing knowledge node where need owners, experts and stakeholders meet and share knowledge. Processes and licensing models for access to data sets and models that enable application of medical natural language processing for health care and life science industry.
Planned approach and implementation
The project is to be implemented as follows: In-depth requirements and needs analysis. Inventory and evaluation of existing data and models from a needs perspective. Technical adaptation of data. Modeling of models. Develop trained models for language understanding of Swedish medical text including documented evaluations of method and model choices. Sharing and making data available. Models will be published as open source code in all instances possible. Distribution of results.