vipul818 / ai_for_medicine

AI for Medicine Specialization

This project is based on the course AI for Medicine offered by deeplearning.ai on Coursera.

Instructors: Pranav Rajpurkar, Bora Uyumazturk, Amirhossein Kiani and Eddy Shyu.

Features

AI is transforming the practice of medicine. It’s helping doctors diagnose patients more accurately, make predictions about patients’ future health, and recommend better treatments. This specialization helps to learn how to:

• Diagnose diseases from X-Rays and 3D MRI brain images
• Predict patient survival rates more accurately using tree-based models
• Estimate treatment effects on patients using data from randomized trials
• Automate the task of labeling medical datasets using natural language processing

Credits

This repo contains my work for this specialization. The code base and diagrams are taken from the AI for Medicine Specialization, unless specified otherwise.

Programming Assignments

Course 1: AI for Medical Diagnosis

• Week 1
  • Assignment:
    • Chest X-Ray Medical Diagnosis with Deep Learning
  • Labs:
    • Data Exploration & Image Pre-Processing
    • Counting labels and weighted loss function
    • Densenet
    • Patient Overlap - Practice
• Week 2
  • Assignment:
    • Evaluation of Diagnostic Models
    • ROC Curve and Threshold
• Week 3
  • Assignment:
    • Brain Tumor Auto-Segmentation for Magnetic Resonance Imaging (MRI)
  • Labs:
    • Explore MRI data
    • Get a sub section
    • Implement U-Net

Course 2: AI for Medical Prognosis

• Week 1
  • Assignment:
    • Diagnosing Diseases using Linear Risk Models
  • Labs:
    • Create a linear model
    • Risk Scores, Pandas and Numpy
    • Combine Features
    • Concordance index
• Week 2
  • Assignment:
    • Risk Models Using Machine Learning
  • Labs:
    • Decision trees
    • Missing data and applying a mask
    • Imputation
• Week 3
  • Assignment:
    • Non-Parametric Estimators for Survival Analysis
  • Labs:
    • Counting patients
    • Kaplan Meier
• Week 4
  • Assignment:
    • Cox Proportional Hazards and Random Survival Forests
  • Labs:
    • Categorical variables
    • Hazard function
    • Permissible pairs

Course 3: AI For Medical Treatment

• Week 1
  • Assignment:
    • Estimating Treatment Effect Using Machine Learning
  • Labs:
    • Pandas operations on Medical Data
    • Model Training Tuning Basics with Sklearn
    • Logistic Regression Model Interpretation
• Week 2
  • Assignment:
    • Natural Language Entity Extraction
  • Labs:
    • Cleaning Text
    • BioC format and the NegBio Library
    • Preparing Input for Text Classification
• Week 3
  • Assignment:
    • ML Interpretation
  • Labs:
    • Permutation method
    • GradCam Part 1
    • GradCam Part 2