Opendatabay APP

Cancer Prediction Dataset

Patient Health Records & Digital Health

Related Searches

Cancer Risk Assessment

Machine Learning in Healthcare

Cancer Detection

Cancer Prediction

Healthcare Analytics

Education Research

Public Health

Trusted By
Trusted by company1Trusted by company2Trusted by company3
Cancer Prediction Dataset Dataset on Opendatabay data marketplace

"No reviews yet"

Free

About

This dataset includes medical and lifestyle information for 1,500 patients. It is designed to predict whether someone has cancer-based on various Features. The dataset provides a realistic challenge for creating predictive models in healthcare.

Dataset Features:

  • Age: Patient's age in years, ranging from 20 to 80.
  • Gender: Patient's gender, classified as male or female.
  • Body Mass Index (BMI): A continuous value indicating body fat based on height and weight, ranging from 15 (underweight) to 40 (obese).
  • Smoking Status: Indicates if the patient is a smoker (Yes or No).
  • Genetic Risk: Evaluates hereditary health influences as Low, Medium, or High risk.
  • Physical Activity: Time spent on physical activities per week, measured in hours (0 to 10).
  • Alcohol Intake: Weekly alcohol consumption, ranging from 0 to 5 units.
  • Cancer History: Indicates personal history of cancer (Yes or No).
  • Diagnosis: States whether the patient has been diagnosed with a condition (Yes or No).

Usage:

The dataset is ideal for training and testing machine learning models in cancer prediction. Potential applications include:
  • Training and evaluating predictive models.
  • Analysing feature importance in cancer prediction.
  • Benchmarking machine learning algorithms in a healthcare context.

Coverage:

The dataset covers key demographic, lifestyle, and genetic risk factors associated with cancer risk, supporting a broad range of modelling approaches and feature engineering techniques.

License:

CC0 (Public Domain)

Who can use it:

This dataset is intended for data scientists, machine learning practitioners, researchers, and students interested in exploring healthcare predictive analytics.

How to use it:

  • Develop predictive models, conduct feature analysis, or compare different algorithms.
  • Investigate the relationships between mental health, study habits, and academic performance through correlation analysis.
  • Analyse trends in mental health factors across demographics within the student population through data exploration.

Dataset Information

VIEWS

26

DOWNLOADS

0

LICENSE

CC0

REGION

GLOBAL

UDQSSQUALITY

5 / 5

VERSION

1.0

Free