Course content
This course introduces students to the basic concepts and evolution of Artificial Intelligence and its role in modern digital environments.
Module 1 - Fundamentals of Digital Health
- Overview of Digital Health: Definition, scope, and importance
- Intersection of public health and technology
- Historical evolution and growth of digital health
- Global trends and innovations in digital health
- Case Study: WHO Digital Health Strategy and global implementations
- Digital health in practice: progress, challenges, and gaps in adoption
Module 2 - Health Information Systems, Data & Learning Health Systems
- Health Information Systems (HIS) and digital data collection tools
- Health data sources: clinical, claims, and social determinants of health
- Applications of Big Data in public health and population health management
- Electronic Health Records (EHR) and Electronic Medical Records (EMR)
- Health Information Exchange (HIE), interoperability, and data standards
- Introduction to Learning Health Systems
- Practical challenges: data quality, fragmentation, and interoperability gaps in real- world systems
Module 3 - Digital Health Technologies & Innovations
- Digital health interventions and technologies
- Mobile health (mHealth), mobile applications, and wearable technologies
- Telehealth and telemedicine
- Social media and patient engagement
- Introduction to Machine Learning (ML) and Artificial Intelligence (AI) in healthcare
- Gamification and behavioral sciences in digital health
- Discussion: Where digital health technologies succeed vs fail in real-world settings
Module 4 - Digital Health Policy, Ethics & Regulation
- Digital health policy frameworks
- Regulatory landscape: HIPAA, GDPR, DPDP Act
- Ethical issues: data privacy, consent, digital divide
- Quality, safety, and equity in digital health
- Cybersecurity threats and risk mitigation strategies
- AI-specific regulation: FDA, CE approvals and responsible AI
- Case studies on cybersecurity breaches and ethical dilemmas
Module 5 - AI in Healthcare – From Model to Deployment
- AI lifecycle: Data → Model → Validation → Deployment → Monitoring
- Understanding sensitivity vs specificity in clinical decision-making
- Model performance vs real-world performance
- Bias, generalizability, and dataset limitations
- Clinical validation vs real-world validation
- Case example: AI detecting abnormalities but limited clinical follow-up
Module 6 - Clinical Workflow, Adoption & Implementation
- Integration of AI into clinical workflows
- Provider adoption and trust in AI systems
- Human-in-the-loop models
- Usability challenges and alert fatigue
- Operational challenges in hospital and public health settings
- Site onboarding, training, and change management
- Discussion: Why many AI solutions fail at the implementation stage
Module 7 - Patient Journey, Funnel Thinking & Impact Measurement
- Patient pathway: Screening → Detection → Referral → Diagnosis → Treatment
- Identifying drop-offs and leakages across the care continuum
- Measuring performance:
- Detection rate
- Referral rate
- Diagnosis conversion
- Treatment initiation
- Linking AI outputs to real-world health outcomes
- Exercise: Mapping a disease-specific care pathway
Module 8 - Business Models, Scale & Real-World Case Studies
- Business models in digital health:
- B2G, B2B, B2B2C
- Pharma and government partnerships
- Pricing, reimbursement, and sustainability
- Scaling digital health solutions in public and private systems
- India context:
- ABDM (Ayushman Bharat Digital Mission)
- Interoperability and digital public infrastructure
- Challenges in LMIC settings
- Case studies:
- AI in radiology
- Telemedicine adoption
- Public health programs
Module 9 - Capstone Project – Designing an AI-Enabled Healthcare Solution
Participants will apply course learnings to design a real-world digital health / AI intervention.
Project Components:
- Problem definition (clinical or public health challenge)
- Entry point of intervention (where AI is applied)
- AI use case and expected outcomes
- Clinical workflow integration
- Patient funnel design and leakage points
- Implementation strategy (sites, training, operations)
- Business model and stakeholder alignment
- Metrics for success (clinical, operational, impact)
Examples:
- AI-enabled lung cancer screening program
- COPD early detection pathway
- Telemedicine-based chronic disease management
