Assessing the interrelationship between different breast cancer diagnostic parameters and their overall effects on patient survival using machine learning tools

Principal Investigator

Name
Balint Balint

Degrees
M.D, PhD

Institution
University of Debrecen

Position Title
senior lecturer

Email
lbalint@med.unideb.hu

About this CDAS Project

Study
PLCO (Learn more about this study)

Project ID
PLCO-524

Initial CDAS Request Approval
Sep 20, 2019

Title
Assessing the interrelationship between different breast cancer diagnostic parameters and their overall effects on patient survival using machine learning tools

Summary
Machine learning has been widely used in predicting the survival of cancer patients. This information is useful for patient planning and medical management. In this study, we aim to assess the interrelationship between various clinical diagnostic parameters for breast cancer such as type of surgery, lymph node status, cancer stage, tumour location, histopathological grade, size, receptor status and tumour markers and to evaluate how they relate with breast cancer patient survival and mortality. Various machine learning algorithms will be modelled and their predictive accuracy compared.

Aims

Identify how various diagnostic parameters relation with each other.
Identify the effects of the above parameters on survival and mortality rate.
Compare the performance of various algorithms on survival prediction.
Modell building on survival and testing the performance of the developed modells.

Collaborators

no external collaborators