This is an introductory lecture for doctors and medical students to learn medical AI. This lecture is made by a person having M.D. and MSc in Artificial Intelligence.

🧠 1. Introduction to AI in Medicine

🎯 Learning Objectives

• Understand what AI is (without heavy math)
• Recognize where AI is already used in medicine
• Distinguish AI vs traditional statistics

🧩 Key Content

• What is AI / ML / Deep Learning?
• Examples:
  • Radiology (image classification)
  • Pathology (slide analysis)
  • Clinical prediction models
• AI vs Evidence-Based Medicine (EBM)

🏥 Clinical Example

• Pneumonia detection from chest X-ray (CNN model)

💡 Teaching Tip

Doctors care about:
👉 “Will this help my patient?”
👉 “Can I trust it?”

📊 2. How Machine Learning Works

🎯 Learning Objectives

• Understand training vs testing
• Learn core concepts without equations

🧩 Key Content

• Supervised learning:
  • Input (features) → Output (label)
• Dataset splitting:
  • Training / Validation / Test
• Overfitting vs Generalization

🏥 Clinical Example

• Predicting:
  • ICU admission
  • Mortality risk

💡 Simple Analogy

• “AI learns like a medical student doing case repetition”

🧪 3. Evaluating AI Models

🎯 Learning Objectives

• Interpret AI performance like diagnostic tests

🧩 Key Content

• Confusion matrix:
  • Sensitivity (Recall)
  • Specificity
  • Precision
• ROC curve / AUC

🏥 Clinical Example

• Cancer screening AI:
  • High sensitivity vs high specificity trade-off

💡 Key Message

👉 “AI evaluation = same logic as diagnostic tests”

🧬 4. Deep Learning in Medical Imaging

🎯 Learning Objectives

• Understand how AI “sees” images

🧩 Key Content

• CNN basics (no math)
• Feature extraction (edges → shapes → patterns)
• Heatmaps (explainability)

🏥 Clinical Example

• Tumor detection in CT/MRI
• Breast cancer screening