OpenLong harmonizes commonly used longitudinal data sets on aging. Its purpose is to facilitate machine learning benchmark studies, prediction modeling, and meta-analyses, enabling researchers to perform more efficient and accurate analyses.
The cohorts currently available for harmonization are:
-
Health ABC: The Health, Aging and Body Composition Study ABC
-
CHS: The Cardiovascular Health Study
-
MESA: The Multi-Ethnic Study of Atheroscelerosis
- ARIC: Atherosclerosis Risk in Communities Study
Any combination of these data sets can be harmonized and output in a standardized format which consists of two data sets:
-
baseline.csv: A cross-sectional data set with information on each patient at the baseline of the study.
-
long.csv: A longitudinal data set with information on each patient collected as a sequence of time points.
You can install the development version of OpenLong like so:
remotes::install_github("briannathanwhite/OpenLong")TBA
library(OpenLong)
## basic example code