DeepPatientLevelPrediction 2.0.3 has been released. This bugfix release only includes one change which was necessary because one of my dependencies introduced a breaking change (polars) which broke some functionality in the package.
PheValuator 2.2.11 has been released. It adds the capability to include multiple visits per subject in the evaluation cohort.
SelfControlledCaseSeries 5.1.1 has been released. This contains a fix of a minor bug introduced in 5.1.0.
CohortMethod 5.2.1 has been released. Most important changes are updating the Capr function calls in the vignettes (the old code was no longer working), and CohortMethod now asks if you want to delete old files when you call runCmAnalyses() using an existing folder but different analysis settings than before.
FeatureExtraction 3.4.0 has been released. It contains mainly bugfixes and furthermore the ‘cohortId’ argument in exported functions has been deprecated, one should use ‘cohortIds’ instead.
DataQualityDashboard 2.6.0 has been released. This is a big release with 4 new data quality checks and the first half of our documentation overhaul.
- @MaximMoinat added 3 new temporal plausibility checks which make DQD’s approach to checking temporality clearer and more comprehensive
- @Dymshyts added a reformatted gender plausibility check which makes DQD’s approach to checking plausible genders simpler and more performant
- @Dymshyts refined the plausible measurement unit check to include a smaller number of measurements and a better-curated list of plausible units for each of those measurements. This change will greatly improve the performance and reliability of this check’s results
-
@MaximMoinat and @Dymshyts fixed some
plausibleValueLowthresholds which were causing false positive failures to be returned - Several members of the extended DQD family (@clairblacketer , @greshje , @Heidi_Schmidt , @MaximMoinat , @Dymshyts ) all contributed to our revamped check-level documentation! We started work on this initiative in last year’s DQD Hackathon and it’s actually still ongoing as we work to complete comprehensive user guidance for each of our data quality check types. Our goal is to provide more detailed information for both ETL developers and data users on how check results are calculated and what to do when checks fail
See our Changelog for more information and check out the new docs here 
Thanks a million to all who contributed to this release!
1 Like
Andromeda 0.6.6 has been released. This contains.a fix for the error in groupApply() introduced by dbplyr 2.5.0 (released two days ago)
HADES-wide release 2024Q1 has been released. This is a snapshot of the HADES packages and their dependencies, thoroughly tested and confirmed to be mutually compatible. It is intended to be a stable environment for studies and execution engines. Currently, the release is only available as an renv lock file, but folks are working on containers as well.
PatientLevelPrediction v6.3.7 has been released. This is mostly a bugfix release. Includes as well some performance improvements and an overhaul of the unit tests to make them more reliable and faster
FeatureExtraction 3.5.0 has been released. It adds the option to filter covariates by setting a minimum threshold for the covariate mean.
FeatureExtraction v3.5.1 has been released which fixes a bug for the minimum threshold for binary covariate mean.
ResultModelManager v0.5.7 has been released.
This is a hotfix for a bug where numerical only values attempted to be inserted into character fields caused a type error due to the csv value being interpreted incorrectly.
SqlRender 1.18.0 has been released. This contains some bugfixes, increases the allowed temp table field names to 63 - 8 = 55 characters (since Oracle now supports longer names), and adds translation of the bitwise & operator.
CohortMethod 5.3.0 has been released. Contains several bug fixes for specific edge cases, and a minor change to the results data model.