Inspiration

Increasing cases of breast cancer patients are becoming major issue in health industry to treat on time efficiently

What it does

It classifies breast cancer patients among Benign and Malignant condition of their sickness using Machine Learning Algorithm called Gaussian Naive Bayes Classifier.

This small scale project is to upload a file contained with data about the patients suffering from malignant or benign breast cancer. The file should have 30 feature values as follows :

feature_names': array(['mean radius', 'mean texture', 'mean perimeter', 'mean area', 'mean smoothness', 'mean compactness', 'mean concavity', 'mean concave points', 'mean symmetry', 'mean fractal dimension', 'radius error', 'texture error', 'perimeter error', 'area error', 'smoothness error', 'compactness error', 'concavity error', 'concave points error', 'symmetry error', 'fractal dimension error', 'worst radius', 'worst texture', 'worst perimeter', 'worst area', 'worst smoothness', 'worst compactness', 'worst concavity', 'worst concave points', 'worst symmetry', 'worst fractal dimension'],

How I built it

Training is being done by readily available dataset in scikit-learn called sklearn.datasets.load_breast_cancer using Gaussian Naive Bayes Classifier method of machine learning by importing library called sklearn.naive_bayes.GaussianNB.

The user interface has been designed to upload a file consists with many patients data for those 30 features and it shows two sets of pateints. First set shows those patients who are suffering from malignant breast cancer and the other set consists of those who are having benign breast cancer or even don't have at all.

The technologies used are follows :

1) Front-End (Node.JS / HTML / Javascript) 2) Back-End (MongoDB / Python / Scikit-Learn)

Challenges I ran into

Installation of various software like scikit-learn, Node.js, MongoDB are not easy.It took several hours to resolve dependencies issues while installing. To run python code from web application has taken a whole day.

Accomplishments that I'm proud of

This project classifies patients having either malignant and benign breast cancer. That's interesting for health industries.Patients will get preference for treatment accordingly.

What I learned

What's next for Classifying malignant or benign breast cancer patients

To collect real world data and clean them to make them suitable to classify patients to set priority of their treatments and facilities available across the globe

Share this project:

Updates