1.1 From Decision Support to Diagnostic Intelligence

1.2 What Makes AI in Medicine Unique?

1.3 Types of Machine Learning in Medicine

1.4 Common Algorithms and What They Do in Healthcare

1.5 Real-World Use Cases Across Medical Specialties

1.6 Debunking Myths About AI in Healthcare

1.7 Real Tools in Use by Clinicians Today

1.8 Hands-on: Medical Imaging Analysis using MediScan AI

2.1 Introduction to Neural Networks: Unlocking the Power of AI

2.2 Convolutional Neural Networks (CNNs) for Visual Data: Seeing with AI’s Eyes

2.3 Image Modalities in Medical AI: AI’s Multi-Modal Vision

2.4 Model Training Workflow: From Data Labeling to Deployment – The AI Lifecycle in Medicine 2.5 Human-AI Collaboration in Diagnosis: The Power of Augmented Intelligence

2.6 FDA-Approved AI Tools in Diagnostic Imaging: Trust and Validation

2.7 Hands-on Activity: Exploring AI-Powered Differential Diagnosis with Symptoma

3.1 Understanding Clinical Data Types – EHRs, Vitals, Lab Results

3.2 Structured vs. Unstructured Data in Medicine

3.3 Role of Dashboards and Visualization in Clinical Decisions

3.4 Pattern Recognition and Signal Detection in Patient Data

3.5 Identifying At-Risk Patients via Trends and AI Scores

3.6 Interactive Activity: AI Assistant for Clinical Note Insights

4.1 Predictive Models for Risk Stratification – Sepsis and Hospital Readmissions

4.2 Logistic Regression, Decision Trees, Ensemble Models

4.3 Real-Time Alerts – Early Warning Systems (MEWS, NEWS)

4.4 Sensitivity vs. Specificity – Metric Choice by Clinical Need

4.5 ICU and ER Use Cases for AI-Triggered Interventions

5.1 Foundations of NLP in Healthcare

5.2 Large Language Models (LLMs) in Medicine

5.3 Prompt Engineering in Clinical Contexts

5.4 Generative AI Use Cases – Summarization, Counselling Scripts, Translation

5.5 Ambient Intelligence: Next-Gen Clinical Documentation

5.6 Limitations & Risks of NLP and Generative AI in Medicine

5.7 Case Study: Transforming Clinical Documentation and Enhancing Patient Care with Nabla Copilot

6.1 Algorithmic Bias – Race, Gender, Socioeconomic Impact

6.2 Explainability and Transparency (SHAP and LIME)

6.3 Validating AI Across Populations

6.4 Regulatory Standards – HIPAA, GDPR, FDA/EMA Compliance

6.5 Drafting Ethical AI Use Policies

6.6 Case Study – Biased Pulse Oximetry Detection

7.1 Core Metrics: Understanding the Basics

7.2 Confusion Matrix & ROC Curve Interpretation

7.3 Metric Matching by Clinical Context

7.4 Interpreting AI Outputs: Enhancing Clinical Decision-Making

7.5 Critical Evaluation of Vendor Claims: Ensuring Reliability and Effectiveness

7.6 Red Flags in Commercial AI Tools: Recognizing and Mitigating Risks

7.7 Checklist: “10 Questions to Ask Before Buying AI Tools”

7.8 Hands-on

8.1 Identifying Department-Specific AI Use Cases

8.2 Mapping AI to Workflows (Pre-diagnosis, Treatment, Follow-up)

8.3 Pilot Planning: Timeline, Data, Feedback Cycles

8.4 Team Roles – Clinical Champion, AI Specialist, IT Admin

8.5 Monitoring AI Errors – Root Cause Analysis

8.6 Change Management in Clinical Teams

8.7 Example: ER Workflow with Triage AI Integration

8.8 Scaling AI Solutions Across the Healthcare System

8.9 Evaluating AI Impact and Performance Post-Deployment