We have the longest experience and widest knowledge base on health data, especially about Estonian electronic health records stored in several national databases. The existence of large-scaled databases of real-world data enable to conduct various health studies and participate in international collaboration projects.
To ease the health data analysis we have developed several tools and methods that come handy during the analysis process, such as
text anonymization tool
tool to calculate the average cost of treatment case
methods for facts extraction
We have analyzed health data from various areas such as COVID-19, human papillomavirus (HPV), drug side effects, drug interactions, prevention of cervical cancer, chronic kidney disease, and others. We have also participated in several study-a-thlons. Many of these topics have already been published as scientific papers.
Health and treatment patterns
One special focus in analyzing health data is finding health and treatment patterns. How treatment guidelines are followed or what events are following the initial diagnoses are some examples of our research questions. To get better insight of the trajectories present in our data we have developed several R packages .
Our team has extensive experience in developing practical software solutions for personalized medicine. Specifically, we have created a pipeline for pharmacogenetic testing and a national infrastructure for delivering personalized healthcare services. This infrastructure includes a database of genetic information, a database of computational models, and an environment for computations, all of which are seamlessly integrated with national healthcare systems.
We have the best OMOP expertise in the region. We have developed a reusable data transformation process which transforms claims, electronic health records and prescriptions data from three Estonian health databases into OMOP. Read more about this from our paper! Thanks to this development process, we have acquired enormous experience in mapping health vocabularies, standardising health data and transferring them to the common data model.
Of course, the data storage and analysis infrastructure is secure and can be used conveniently. In our work, we use several tools provided by OHDSI, for example, ATLAS for creating study cohorts.