PatientLevelPrediction
PatientLevelPrediction copied to clipboard
OHDSI
An R package for performing patient level prediction in an observational database in the OMOP Common Data Model.
To get the latest arrow with 64 bit fields running we had to make some changes throughout the PLP package. I will keep track of all changes required here in...
**Is your feature request related to a problem? Please describe** Yes, there is a problem I'm facing. When utilizing the PatientLevelPrediction package, I'm encountering difficulties in creating the `plpData` for...
The PLP Results Model currently defined the column `execution_date_time` as a `DATETIME2` which is generally translated to a `TIMESTAMP` data type for most RDBMs (I'm mainly focused on PostgreSQL for...
Some of our tests, such as some in [test-UploadToDatabase.R](https://github.com/OHDSI/PatientLevelPrediction/blob/main/tests/testthat/test-UploadToDatabase.R) rely on gh secrets to connect to test databases. These tests will fail in a fork. I think it would be...
**Is your feature request related to a problem? Please describe.** Univariate and Random Forest feature selection both rely on python. **Describe the solution you'd like** It would be good to...
Because we usually use categorical features for prediction, it would be great if we can implement CatBoost in our PLP frameworks. https://catboost.ai/ https://github.com/catboost/catboost you can see a cheatsheet in #376...
**Describe the bug** Hello, I'm encountering an issue with our PLP package when used in R Markdown (Rmd). Occasionally, an error is raised stating "Error in globalCallingHandlers (condition=conditionHandler): should not...
**Describe the bug** [diagnosisPlp.txt](https://github.com/OHDSI/PatientLevelPrediction/files/11821706/diagnosisPlp.txt) [viewPlpError.txt](https://github.com/OHDSI/PatientLevelPrediction/files/11821708/viewPlpError.txt) [plpError.txt](https://github.com/OHDSI/PatientLevelPrediction/files/11821710/plpError.txt) I am running through a very typical single PLP model workflow. When I get to the end of the workflow, I run `viewPlp`, which...
According to [this](https://www.sciencedirect.com/science/article/pii/S1386505622000764) paper, over a certain number of outcome events the discriminative model performance stops improving for L1 logistic regression at least. This could be taken advantage of when...
It's an L0 approximated logistic regression model. Resulting in very sparse models. This would add one more dependency in suggests. There is a package [here](https://github.com/OHDSI/BrokenAdaptiveRidge) built on top of Cyclops....