Chapter 1: Introduction to AI and feasibility
- AI, ML, Big Data: What do the buzzwords mean?
- Defining a problem
- What can and cannot be solved
- Common algorithmic alternatives
- You think you need AI, now what?
- Data considerations for Healthcare & Patient Privacy
- Cautionary tales of AI Snake Oil in Healthcare
Chapter 2: AI in theory
- Classification problems in the field of healthcare
- Decision trees
- Logistic regression
- Support vector, achines
- Neural Networks and Deep Learning
- Convolutional Neural Networks
- Evaluation metrics for AI-driven diagnostic tools
Chapter 3: Overview of Programming
- Introduction to Python and environment set up
- Control Structures & Loops
- Data structures
- Functions
- File I/O
- Classes
- Packages/Libraries
- Numpy & Matplotlib
Chapter 4: Project #1 ML & Diabetes
- Problem overview and why ML might be the best
- Introduction to scikit-learn
- Data Pre-processing- Try 1: Decision Trees
- Try 2: k Nearest Neighbors
- k-fold Cross Validation
- Takeaways
Chapter 5: Project #2 Neural Networks & Heart Disease
- Problem overview and why neural networks might work
- Introduction to keras
- Data Pre-processing
- Model design and implementation
- Measure Efficacy
- Takeaways
Chapter 6: Project #3 CNNs & Brain Tumor Detection
- Problem overview
- Overview of segmentation problems and Mask-RCNN
- Data Pre-processing & Working with MRI images- Data Augmentation
- Model design and implementation
- Measure Efficacy with Dice Score and AP metrics
- Takeaways
Chapter 7: The Future of Healthcare and AI
- Review of book
- Problems in Medical AI: Data Issues
- Medical Problems waiting to be solved
