HoneyPotSeeker / BreastCancerCoimbra

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Breast Cancer Coimbra Project

Breast cancer is the most common malignancy among women worldwide. While there is extensive literature on the relationship between body weight and breast cancer risk, uncertainties remain about the roles of adipokines, insulin, glucose, and their interactions. This project aims to explore the relationships between body mass index (BMI), glycaemia, insulinemia, insulin resistance, blood adipokine levels, and breast cancer.

Data Set Information

The dataset contains 10 quantitative predictors and a binary dependent variable indicating the presence or absence of breast cancer. These predictors include anthropometric data and parameters obtainable from routine blood analyses. Accurate prediction models based on these predictors could serve as biomarkers for breast cancer.

Attribute Information

Quantitative Attributes

  1. Age (years)
  2. BMI (kg/m²)
  3. Glucose (mg/dL)
  4. Insulin (µU/mL)
  5. HOMA (Homeostasis Model Assessment)
  6. Leptin (ng/mL)
  7. Adiponectin (µg/mL)
  8. Resistin (ng/mL)
  9. MCP-1 (pg/dL) - Chemokine Monocyte Chemoattractant Protein 1

Labels

  • 1: Healthy controls
  • 2: Patients

Abbreviations

  • BC: Breast cancer
  • BMI: Body mass index
  • HOMA: Homeostasis Model Assessment
  • MCP-1: Chemokine Monocyte Chemoattractant Protein 1

Goals

The primary goal of this exploratory study is to develop and evaluate a prediction model that could potentially be used as a biomarker for breast cancer. The model will be based on anthropometric data and parameters available from routine blood analyses. In medical testing, the key indicators of success are specificity and sensitivity, with the ideal aim being 100% in both metrics.

Dataset

You can download the dataset from the following link: Breast Cancer Coimbra Dataset

Future Work

  • Investigate the individual and combined effects of adipokines, insulin, and glucose on breast cancer risk.
  • Enhance the prediction model by incorporating additional relevant biomarkers.
  • Validate the model with a larger and more diverse dataset to improve generalizability.

By advancing our understanding of these relationships, this project aims to contribute to more effective early detection and treatment strategies for breast cancer.

About


Languages

Language:Jupyter Notebook 100.0%