https://github.com/genentech/conmedclassify
Process clinical ADaM-format data and classify subjects into profiles based on their concomitant medication usage within a clinical trial.
https://github.com/genentech/conmedclassify
Last synced: 8 months ago
JSON representation
Process clinical ADaM-format data and classify subjects into profiles based on their concomitant medication usage within a clinical trial.
- Host: GitHub
- URL: https://github.com/genentech/conmedclassify
- Owner: Genentech
- License: mit
- Created: 2022-04-06T19:29:29.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2022-04-14T05:25:15.000Z (about 4 years ago)
- Last Synced: 2025-07-21T16:46:07.747Z (11 months ago)
- Language: R
- Homepage:
- Size: 28.3 KB
- Stars: 1
- Watchers: 8
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.Rmd
- License: LICENSE
Awesome Lists containing this project
README
---
output: github_document
---
```{r, include = FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>",
fig.path = "man/figures/README-",
out.width = "100%"
)
```
# ConMedClassify
This package stores sufficient demonstration data to perform a classification.
```{r}
library(ConMedClassify)
# load demo drug basket information
data(drug_baskets)
drug_baskets
# load demo clinical data
data(demo_clinical_data)
dplyr::glimpse(demo_clinical_data)
as.data.frame(unnest_domain(demo_clinical_data[, c("STUDYID", "USUBJID", "nested.CM")], nested.CM))
as.data.frame(unnest_domain(demo_clinical_data[, c("STUDYID", "USUBJID", "nested.EX")], nested.EX))
as.data.frame(unnest_domain(demo_clinical_data[, c("STUDYID", "USUBJID", "nested.TTE")], nested.TTE))
```
Performing the classification results in a file of profiles
```{r, eval = FALSE}
# profile subjects into conmed profiles
extract_conmed_profiles_to_tsv(demo_clinical_data, drug_baskets = drug_baskets, drug_basket_data_objects = NULL, treatments = "trt1")
```
```{r}
res <- readr::read_tsv("inst/outputs/ConMedProfiles_trial1_basket_demo.tsv", col_types = "c")
dplyr::glimpse(res)
```
When many of these are constructed they can be aggregated together into a single file per drug basket
```{r, eval = FALSE}
# merge all individual TSV files across studies into a single one for a given drug basket
aggregate_conmed_profile_tsv(input_tsv_path = "outputs/",
tsv_pattern = '_basket_demo\\.tsv',
basket_name = "DEMO",
output_filename_prefix = "outputs/CITDataMart_ConMedProfiles_")
```