Simulated Breast Cancer Screening Cohort

Description

A synthetic dataset of 100 participants illustrating the data structure required by clone_censor(). Values are entirely simulated and do not represent real patients.

Usage

cohort

Format

A data frame with 100 rows and 7 columns:

id
Integer participant identifier (1–100).
age
Age at study entry (70–84 years).
start_month
Month of trial entry (1–60).
end_month
Last follow-up month, equal to the minimum of the death month and the administrative end of study (month 108).
death_month
Month of all-cause death; NA if alive at last follow-up.
bc_death
Breast cancer death indicator (0/1).
bc_month
Month of breast cancer diagnosis; NA if no diagnosis during follow-up.

Details

Months are numbered consecutively from 1 (January 2000) to 108 (December 2008), matching the convention used in the original SAS implementation of García-Albéniz et al. (2020). Participants enter the study between months 1 and 60 (January 2000 – December 2004) to allow adequate follow-up.

Approximately 15 % of participants die during follow-up; roughly 2 % die from breast cancer. Administrative censoring occurs at month 108.

References

García-Albéniz X, Uno H, Bhatt DL, McArdle PH, Joffe MM, Hernán MA. Continuation of Annual Screening Mammography and Breast Cancer Mortality in Women Older Than 70 Years: A Prospective Observational Study. Ann Intern Med. 2020;172(6):381–389. doi:10.7326/M18-1199

See Also

clone_censor(), screening_mammograms, diagnostic_mammograms

Examples

Code
  id age start_month end_month death_month bc_death bc_month
1  1  81          26       108          NA        0       NA
2  2  81          33       108          NA        0       NA
3  3  76          28       108          NA        0       NA
4  4  75           1       108          NA        0       NA
5  5  77          17       108          NA        0       NA
6  6  70          40       108          NA        0       NA