days between lab visits

days_between_visits.R

library("readr")
library("dplyr")
library("tidyr")
library("lubridate")

# Load the visit history, parse the timestamp as a Date
mdr <- read_csv("C:/Users/trist/Downloads/longitudinal_missing.csv") %>%
  mutate(Date = mdy_hm(DateTime) %>% as.Date)

# for each study/subject, find difference between latest and earliest date
diffs <- mdr %>%
  select(Study, Subj, Date) %>%
  distinct %>%
  group_by(Study, Subj) %>%
  summarise(Diff = max(Date) - min(Date))


# Save the ones with more than 30 days between visits
diffs %>%
  arrange(desc(Diff)) %>%
  mutate(MoreThan30 = 30 < Diff) %>%
  filter(MoreThan30) %>%
  arrange(Study, Subj) %>%
  select(Study, Subj, Diff) %>%
  write_csv("C:/Users/trist/Downloads/days_betwen_visits.csv")