Smoking Related Lung Cancers

This is a subset of data available from the US National Lung Screening Trial (NLST). The data contains information about current and former smokers who were observed for 7 years and were tested for lung cancer each year. No non-smokers were involved in the trial.

Data contains:

• pid - anonymous identifier of a person
• age - age of a person at the start of the trial
• gender - Male/Female
• race - the race of a person
• smoker - Former/Current (Former is defined as quit smoking in last 15 years)
• days_to_cancer - number of days passed since the trial when the cancer was first observed
• stage_of_cancer - the stage of cancer when the cancer was first observed

Full trial metadata is available at https://wiki.cancerimagingarchive.net/download/attachments/5800702/package-nlst-780.2021-05-28.zip?version=1&modificationDate=1633562878492&api=v2