CohortMethod
CohortMethod copied to clipboard
OHDSI
An R package for performing new-user cohort studies in an observational database in the OMOP Common Data Model.
Right now it seems that if the user selects no covariates, the cohort will always be assumed to be empty.
It might be beneficial to add PS overlap weight (an alternative to the IPTW), which was suggested by Li et al. (Li, Fan, Laine E. Thomas, and Fan Li. “Addressing...
The upcoming version of CohortMethod (v5.0.0) automatically performs empirical calibration, but it assumes the negative controls are outcomes. In theory, one could also use negative control exposures, target and comparators...
Dear developers, I am running a PLE package and encounter the issue: createPs(stopOnError = TRUE, excludeCovariateIds = list(), prior = list( : ILLCONDITIONED Calls I put error message bellow, could...
When the outcome for example is a lab value. We could implement linear regression to start with. This would probably require using the cohort_attribute table.
The [computeMdrr function](https://github.com/OHDSI/CohortMethod/blob/master/R/Power.R#L43) currently only implements power calculations for Cox models. We should add implementations for logistic regression and Poisson models.
In trying to run [this study](https://github.com/oxford-pharmacoepi/ROC22_CovVaxComparativeSafety/tree/main/CovVaxComparativeSafety) from @Xintong-Li-ZnCu the repeated calls to connect and disconnect to the database here https://github.com/OHDSI/CohortMethod/blob/79b86e4435f66825cecfc8e518d0d1d034d3d4ef/R/DataLoadingSaving.R#L158 causes problems running on sidiap´s postgres database (at some point...
I was running the `createPs` function, and the process stopped with "Error: Invalid result set" I have attached the results from traceback() below. The CmData file was part of the...
The `priorOutcomeLookback` argument of the `createStudyPopulation()` function currently takes a single value, used across outcomes when performing multiple analyses. We should add the ability to specify this per outcome, in...
Probably using the `checkmate` package.