This is my Insight Health Data Science Project for Summer 2018. Please see secondmind.xyz to see the project app.

How do you find a good doctor for a second opinion? To frame the problem further, how does someone with a cancer diagnosis find an expert doctor in their field.

Data is acquired from 4 sources: Most of data acquisition is detailed in the file importdata.py

1. Healthgrades.com: Medical Oncologists in NYC
2. NY Magazine: Best Medical Oncologists in NYC
3. Pubmed.gov: Publications of all doctors in my Data
4. Scopus: Number of citations for each of these publications

Data is cleaned in CleanData.ipynb

Initial data exploration is detailed in InitialDataExploration.ipynb

Features are created from publication data in Feature Engineering.ipynb

The model is detailed in Data Fitting.ipynb