Develop Clinical Prediction Models Using the Common Data Model R package PatientLevelPrediction version 6.6.0 A user friendly way to create patient level prediction models using the Observational Medical Outcomes Partnership Common Data Model. Given a cohort of interest and an outcome of interest, the package can use data in the Common Data Model to build a large set of features. These features can then be used to fit a predictive model with a number of machine learning algorithms. This is further described in Reps (2017) <doi:10.1093/jamia/ocy032>. Software Depends: R (>= 4.0.0) Imports: Andromeda, Cyclops (>= 3.0.0), DatabaseConnector (>= 6.0.0), digest, dplyr, FeatureExtraction (>= 3.0.0), Matrix, memuse, ParallelLogger (>= 2.0.0), pROC, PRROC, rlang, SqlRender (>= 1.1.3), tidyr, utils Suggests: curl, Eunomia (>= 2.0.0), glmnet, ggplot2, gridExtra, IterativeHardThresholding, knitr, lightgbm, Metrics, mgcv, OhdsiShinyAppBuilder (>= 1.0.0), parallel, pkgload, polspline, readr, ResourceSelection, ResultModelManager (>= 0.6.0), reticulate (>= 1.41), rmarkdown, RSQLite, scoring, survival, survminer, testthat, withr, xgboost (> 1.3.2.1) Egill Fridgeirsson <e.fridgeirsson@erasmusmc.nl> Comprehensive R Archive Network (CRAN) Egill Fridgeirsson [aut, cre], Jenna Reps [aut], Martijn Schuemie [aut], Marc Suchard [aut], Patrick Ryan [aut], Peter Rijnbeek [aut], Observational Health Data Science and Informatics [cph] Apache License 2.0 2026-03-09 application/tgz https://CRAN.R-project.org/package=PatientLevelPrediction doi:10.32614/CRAN.package.PatientLevelPrediction