The dataset contains information about patients, specifically
their CD4 T cell counts (cd_2018, cd_2019, cd_2021, cd_2022, cd_2023) and
viral loads (vl_2019, vl_2021, vl_2022, vl_2023). For modeling patient
recovery and viral load persistence or suppression, column cd_2023 is
identified as the outcome variable for CD4 cell counts, and column vl_2023
is identified as the outcome variable for viral load.