Analysis Results Datasets Onboarding

Background on {cards}, {cardx}, {gtsummary}

Overview

The CDISC Analysis Results Data (ARD) Model is an emerging standard for encoding statistical analysis outcomes in a machine-readable format. Its primary objective is to streamline the processes of automation, ensuring reproducibility, promoting reusability, and enhancing traceability.

The {cards} R package offers a range of functions for ARD generation, from basic univariate summaries like means and tabulations to complex multivariable summaries encompassing regression models and statistical tests.

The package includes functionalities to represent results in various formats, including JSON and YAML. Thanks to its flexible structures, the {cards} package can be harnessed in diverse applications, such as generating tables for regulatory submissions and conducting quality control checks on existing tables. Furthermore, the {cards} ARD object can be accessed through a REST API, allowing writers to dynamically incorporate table results into reports.

The {cardx} package (extra cards) is a companion to {cards}, exporting more complex functions to generate ARD objects. While the {cards} package has minimal dependencies, the {cardx} package will include additional suggested package dependencies for implementing complex statistical methods.

While {cards} calculates statistics and stores them in a structured object, it cannot present those results; this, however, is where the {gtsummary} package shines. The {gtsummary} package offers a modular framework to construct summary tables. It is the most widely used package for summary tables in the healthcare/pharmaceutical/research space. The package won the American Statistical Association’s 2021 award for Innovation in Statistical Programming and Analytics, the Posit 2024 Table Contest’s pharmacuetical track, and has over 1 million installations from CRAN. The {gtsummary} package was recently refactored to utilize {cards} and {cardx} as its backend, which will allow users to both extract an ARD object from a {gtsummary} table and use an ARD object to construct a new {gtsummary} table. The {cards}, {cardx}, and {gtsummary} packages stand as robust and versatile tools, poised to assist in a multitude of analytical endeavors.

{cards} {cardx} {gtsummary}

Pre-work

Before we meet to review the details, please complete the following:

Install the development versions of {cards}, {cardx}, and {gtsummary} packages.

pak::pak(c("insightsengineering/cards", "insightsengineering/cardx", "ddsjoberg/gtsummary"))

Review the full Analysis Results Standard, paying particular attention to the section on Analysis Results Data.
- CDISC webinar on the model: https://www.cdisc.org/events/webinar/analysis-results-standard-public-review
Review the {gtsummary} package.
- Cornell Seminar (this recording was made long before ARDs were used in gtsummary, and gives an overview of how, generally, one uses the package): https://www.youtube.com/watch?v=tANo9E1SYJE&t=5s
Using the {cards} package, create a single ARD object that contains all the statistics needed to construct the table below (including the statistics in the header).
- Use the cards::ADSL data set.
- Use the cards::ard_continuous(), cards::ard_cateogrical(), and cards::ard_dichotomous() functions to calculate the statistics.
- Use cards::bind_ard() to combine the results into a single ARD object.

Characteristic	Placebo N = 86	Xanomeline Low Dose N = 84	Xanomeline High Dose N = 84
Age
Median (Q1, Q3)	76 (69, 82)	78 (71, 82)	76 (71, 80)
Mean (SD)	75 (9)	76 (8)	74 (8)
Min - Max	52 - 89	51 - 88	56 - 88
Age Group, n (%)
<65	14 (16%)	8 (10%)	11 (13%)
65-80	42 (49%)	47 (56%)	55 (65%)
>80	30 (35%)	29 (35%)	18 (21%)
Female, n (%)	53 (62%)	50 (60%)	40 (48%)