Phenotype Algorithm Validation PheValuator on the

Phenotype Algorithm Validation PheValuator on the
1 / 1
Phenotype Algorithm Validation PheValuator on the - slide 1 of 2 Phenotype Algorithm Validation PheValuator on the - slide 2 of 2
Phenotype Algorithm Validation PheValuator on the OHDSI Github Have used it to validate about 30 health outcomes Working on validation for journal article: Testing with non-condition code algorithms Procedures Measurements Comparing to

Related Topics

Download this presentation From Below

"Phenotype Algorithm Validation PheValuator on the" is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Presentation Transcript

01
Phenotype Algorithm Validation PheValuator on the OHDSI Github
Have used it to validate about 30 health outcomes
Working on validation for journal article:
Testing with non-condition code algorithms
Procedures
Measurements
Comparing to published validation results
Considering differences in performance characteristics between:
Databases
Exposure groups (e.g., two different drug exposures)
Age groups, e.g.; < 18YO v. 18-65YO v. > 65YO 1<br>
02
Thoughts for Phenotype Library Do we want to have a phenotype library or a concept set library (or both)?
Phenotypes are fit-to-purpose – sensitive (want to find all possible outcomes) v. specific (want to use only definite outcomes)
Validation of the phenotypes may turn out to be DB specific
What do phenotype validation results mean? 2<br>