Assessment of the Suitability of the Estonian Health Record Data for the Prediction of Ischemic Stroke
Name
Ainika Adamson
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.
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.
Graduation Thesis language
English
Graduation Thesis type
Master - Computer Science
Supervisor(s)
Toomas Haller, Kaur Alasoo
Defence year
2021