Practical Deep Learning for Healthcare

This textbook bridges cutting-edge AI research and real-world clinical practice. Written by a unique team of professors, industry leaders specializing in AI for healthcare, and senior Ph.D. students, this textbook provides both theoretical foundations and hands-on implementation for building healthcare AI systems. Whether you're a clinician, data scientist, or researcher, this textbook equips you with the knowledge and tools to develop and deploy effective AI solutions for real healthcare challenges.

Part I: Foundation

• 1 Introduction
• 2 Healthcare Data
  • Electronic Health Records (EHRs): The Digital Foundation
  • Medical Imaging: Visual Data for Diagnosis
  • Physiological Signals: Continuous Monitoring Data
  • Other Types of Data
  • Data Integration
• 3 Mathematical Foundations
  • Linear Algebra Colab
  • Calculus Colab
  • Probability
  • Machine Learning
• 4 Deep Neural Networks
  • The Perceptron: Building Block of Neural Networks Colab
  • From Single to Multi-Layer Perceptrons Colab
  • Training a Deep Neural Network Colab
  • Case Study: Breast Cancer Detection

Part II: Basic Deep Learning Architectures

• 5 Convolutional Neural Networks (CNN)
  • Introduction to Convolutional Neural Networks Colab
  • Modern Convolutional Neural Networks Colab
  • Case Study: X-ray Disease Classification with CNN Colab
• 6 Recurrent Neural Networks (RNN)
  • Introduction to Recurrent Neural Networks Colab
  • Variants of the RNN Model Colab
  • Case Study: Heart Failure Onset Prediction with LSTM Colab
• 7 Graph Neural Networks (GNN)
  • Introduction to Graph Neural Networks Colab
  • Advancements in Graph Neural Networks
  • Case Study: Graph Neural Networks for Drug Property Prediction Colab
• 8 Attention Models
  • Sequence-to-Sequence Task Colab
  • Cross Attention for Seq-to-Seq Task Colab
  • Case Study: CAML: Disease Prediction with Clinical Notes Colab
  • Case Study: Heart Failure Prediction with RETAIN Model Colab

Part III: Advanced Deep Learning Architectures

• 9 Transformers
  • Introduction to the Transformer Model Colab
  • Case Study: Drug Recommendation with the Transformer Model Colab
  • From Transformer to BERT Colab
  • Transformers Beyond Text Data
  • Case Study: Medical Coding with the ClinicalBERT Model Colab
• 10 Generative Models in Healthcare
  • Variational Auto-encoders (VAE) Colab
  • Generative Adversarial Networks (GAN) Colab
  • Diffusion Models Colab
  • Case Study: Chest X-ray Image Generation with VAE, GAN, and Diffusion Model Part 1 Part 2 Part 3
• 11 PyHealth
  • Introduction to PyHealth Colab
  • Case Study: Build Clinical Predictive Models with PyHealth Colab

Part IV: Large-Scale Foundation Models

• 12 Generative Large Language Models in Healthcare
  • How to Use LLMs in Healthcare Applications Colab
  • Training Your Own LLMs for Healthcare
  • Case Study: Using and Fine-tuning LLMs for Healthcare
  • LLM Inference in Healthcare Applications Part 1 Part 2
  • Instruction Tuning with Qwen2.5 on MedCalc-Bench Colab
  • RLVR: Reinforcement Learning with Verifiable Rewards on MedCalc-Bench Colab
• 13 Large Language Model Agents and Tool Use
  • LLM Agents and Tool Use
  • Retrieval-Augmented Generation as Tool Use Part 1 Part 2
  • Code Generation as Tool-Augmented Reasoning
  • Tool-Augmented APIs and Structured Interfaces
  • Multi-Agent Collaboration for Complex Tasks
  • Case Study: Implementing a SQL Agent for Patient Analysis with LangGraph Colab
• 14 Multimodal Foundation Models
  • Vision-Language Models Part 1 Part 2
  • Other Modalities Beyond Vision
  • Case Study: Using a Medical VLM for Visual Question Answering Colab