Evaluates phenotype algorithms by developing a diagnostic
prediction model using a set of noisy positives and noisy negatives.
It can then apply the model to a large cohort
to create a set of subjects each with a predicted probability for the
health outcome of interest. This cohort can then be used to evaluate
phenotype algorithms through the calculation of the necessary performance
characteristics - sensitivity, specificity, and positive and negative
predictive value. Based on work by Swerdel (2022) <doi:10.1016/j.jbi.2022.104177>
and Swerdel (2019) <doi:10.1016/j.jbi.2019.103258>.
| Version: |
2.2.18 |
| Depends: |
R (≥ 4.1.1) |
| Imports: |
DatabaseConnector, PatientLevelPrediction (≥ 6.0.4), FeatureExtraction (≥ 2.1.5), SqlRender (≥ 1.5.2), dplyr (≥
0.7.8), methods, ParallelLogger, tibble |
| Suggests: |
knitr, rmarkdown, shiny, shinydashboard, DT, htmltools, qpdf, testthat, Eunomia, withr, CohortGenerator |
| Published: |
2026-10-24 |
| DOI: |
10.32614/CRAN.package.PheValuator (may not be active yet) |
| Author: |
William J. O'Brien [aut, cre],
Joel Swerdel [aut],
Martijn Schuemie [aut] |
| Maintainer: |
William J. O'Brien <wobrien8 at its.jnj.com> |
| BugReports: |
https://github.com/OHDSI/PheValuator/issues |
| License: |
Apache License 2.0 |
| URL: |
https://ohdsi.github.io/PheValuator/,
https://github.com/OHDSI/PheValuator |
| NeedsCompilation: |
no |
| Materials: |
README, NEWS |
| CRAN checks: |
PheValuator results |