Predicting Breast cancer occurrence using Machine learning: Decision tree algorithm

Breast cancer, the one human malignancy, is diagnosed visually, beginning with a clinical screening and potentially by Dermoscopic analysis, and pathologies. Automated prediction of breast cancer using open source solutions would aid to reduce the occurrence of breast cancer and mortality rate.

Your crush sitting next to you might be a victim of breast cancer and might be ignorant !! , i bet you want to tackle this as an open source engineer. In machine learning Decision trees and its performance can be improved using bagging, boosting or random forests or regressions . in this talk i will implement these techniques to predict breast cancer from routine blood tests. Many datasets about breast cancer contain information about the tumor which normally exists. However, my dataset contains routine blood tests information of patients with and without breast cancer. Potentially, if we can accurately predict if a patient has cancer, that patient could receive very early treatments, even before a tumor is noticeable! and that would reduce mortality rates which is caused when the cancer eats deep into the patient or prospective patient.

Technical requirements: A computer system where slides would be projected(definitely would be available) Even though i might not practically be the best speaker on a Machine learning topic, i have researched a lot on machine learning technologies and have practically focused on making them public for social good and furthermore have decided to share that knowledge and skills for the general public and also demystify the principles and hardcore logic behind some of these systems in order to create an army of Machine learning engineers.

Furthermore, i break down the hardest stuff and complex codes into very simple statements and simple english, so anyone can attend my talks, and leave there with an intermediate level of whatever was taught or spoken about. Furthermore, i’ve spoken in some conferences about machine learning technologies, so i can prolly say i have a knack for it.