Name: Breast Cancer Prediction
Creator: Kaggle
License: https://creativecommons.org/publicdomain/zero/1.0/

About this Dataset

Breast Cancer Prediction

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

Age_At_The_Time_Of_Mammography	number	Patient's age in years at time of mammogram
Radiologists_Assessment	string	Radiologist's assessment based on the BI-RADS scale
---	---	---
Is_Binary_Indicator_Of_Cancer_Diagnosis	boolean	Binary indicator of cancer diagnosis within one year of screening mammogram (false= No cancer diagnosis, true= Cancer diagnosis)
---	---	---
Comparison_Mammogram_From_Mammography	string	Comparison mammogram from prior mammography examination available
---	---	---
Patients_BI_RADS_Breast_Density	string	Patient's BI-RADS breast density as recorded at time of mammogram
---	---	---
Family_History_Of_Breast_Cancer	string	Family history of breast cancer in a first degree relative
---	---	---
Current_Use_Of_Hormone_Therapy	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
---	---	---
History_Of_Breast_Biopsy	string	Prior history of breast biopsy
---	---	---
Is_Film_Or_Digital_Mammogram	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.

Tables

Data

@kaggle.haithemhermessi_breast_cancer_screening_data_set.data

395.5 kB
39,998 rows
13 columns

CREATE TABLE data (
  "age_at_the_time_of_mammography" BIGINT,
  "radiologists_assessment" VARCHAR,
  "is_binary_indicator_of_cancer_diagnosis" BOOLEAN,
  "comparison_mammogram_from_mammography" VARCHAR,
  "patients_bi_rads_breast_density" VARCHAR,
  "family_history_of_breast_cancer" VARCHAR,
  "current_use_of_hormone_therapy" VARCHAR,
  "binary_indicator" VARCHAR,
  "history_of_breast_biopsy" VARCHAR,
  "is_film_or_digital_mammogram" BOOLEAN,
  "cancer_type" VARCHAR,
  "body_mass_index" VARCHAR,
  "patients_study_id" BIGINT
);