colcancer: Colon Cancer Dataset

colcancerR Documentation

Colon Cancer Dataset

Description

A dataset describing colon cancer patients. The data is based on real data from a hospital-based cancer registry but many values are changed to ensure anonymity. Each row is a single case, while the columns represent patients' health conditions and physical parameters.

Usage

data("colcancer")

Format

A data.frame with 546 observations with colon cancer cases. The 12 columns describe different parameters of patients' conditions.

Details

The columns of the data set are:

  • followup. numeric. Follow-up time since surgery in days. The time the patient was observed.

  • logfollowup. numeric. The follow-up time, but logarithmic.

  • death. integer. Indicates whether the patient died. If death occured it is set to 1, otherwise 0.

  • sex. factor. Level: "f", "m". The sex of the patient. In this case "f" stands for female, and "m" represents male patients.

  • LNE. numeric. The number of examined lymph nodes.

  • LNR. numeric, ranges from 0 to 1. The number of cancerous lymph nodes divided by the total number (LNE).

  • pUICC. factor. Levels: "I", "II", "III", "IV". Pathological cancer stage. The UICC staging system was used.

  • CTX. factor. Levels: "0", "1". Chemotherapy (no / yes)

  • ASA.score. factor. Levels: "mild", "severe". An ASA score smaller than 3 is considered a mild general illness, 3 or greater is considered a severe general illness. The ASA scoring system of patients was originally proposed by the American Society of Anesthesiologists.

  • R.status factor. Level: "0", "12". Residual tumor after surgery. 0 stands for no residual tumor. 12 stands either for microscopic (R1) or macroscopic residues (R2).

  • preexisting.cancer. integer. If there was a history of cancer before the colon cancer. Set to 1 if there has been a cancer in the past and to 0 if not.

  • age. numeric. The age of the patient in years.


dirttee documentation built on Sept. 14, 2022, 5:06 p.m.