Breast-cancer-prediction
OpenML dataset with id 43687
Author name not available (Why is that?)
Full work available at URL: https://api.openml.org/data/v1/download/22102512/Breast-cancer-prediction.arff
Upload date: 24 March 2022
Dataset Characteristics
Number of features: 12 (numeric: 1, symbolic: 2 and in total binary: 2 )
Number of instances: 39,998
Number of instances with missing values: 0
Number of missing values: 0
Context This dataset includes data from a random sample of 20,000 digital and 20,000 film-screen mammograms received by women age 60-89 years within the Breast Cancer Surveillance Consortium (BCSC) between January 2005 and December 2008. Some women contribute multiple examinations to the dataset. Data is useful in teaching about data analysis, epidemiological study designs, or statistical methods for binary outcomes or correlated data. Content The data set contains 39998 rows and 13 cols. Attributes are described as follows:
Field Name Type (Format) Description
AgeAtTheTimeOf_Mammography number Patient's age in years at time of mammogram
Radiologists_Assessment
string
Radiologist's assessment based on the BI-RADS scale
---
---
---
IsBinaryIndicatorOfCancer_Diagnosis
boolean
Binary indicator of cancer diagnosis within one year of screening mammogram (false= No cancer diagnosis, true= Cancer diagnosis)
---
---
---
ComparisonMammogramFrom_Mammography
string
Comparison mammogram from prior mammography examination available
---
---
---
PatientsBIRADSBreastDensity
string
Patient's BI-RADS breast density as recorded at time of mammogram
---
---
---
FamilyHistoryOfBreastCancer
string
Family history of breast cancer in a first degree relative
---
---
---
CurrentUseOfHormoneTherapy
string
Current use of hormone therapy at time of mammogram
---
---
---
Binary_Indicator
string
Binary indicator of whether the woman had ever received a prior mammogram
---
---
---
HistoryOfBreast_Biopsy
string
Prior history of breast biopsy
---
---
---
IsFilmOrDigitalMammogram
boolean
Film or digital mammogram (true=Digital mammogram, false=Film mammogram)
---
---
---
Cancer_Type
string
Type of cancer
---
---
---
Acknowledgements
We acknowledge the Breast Cancer Surveillance Consortium (BCSC) for making this data set available for research purposes.
This page was built for dataset: Breast-cancer-prediction
