Assessment of the suitability of the Estonian Health Record data for the prediction of ischemic stroke
Date
2021
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Tartu Ülikool
Abstract
An increase in the instances of cardiovascular diseases has elevated the need
for better and more efficient prediction models for ischemic stroke as well. Therefore, it
is vitally important to assess the Estonian Health Record laboratory data to find out its
suitability for ischemic stroke prediction models. To that effect five different approaches
and three methods were utilized in three tiers in this Thesis. The potential of binary
statement of measurement facts, as well as the actual analysis results, calculated z-scores
and medical reference values were evaluated as the input for prediction models. It was
found that the binary statement of measurements itself contained enough information for
a competitive prediction model. However, several analytes were identified that had
increased the quality of the prediction outcomes and therefore should be studied further.
Description
Keywords
Data usability assessment, laboratory analyses, ischemic stroke