Clinically relevant AI literacy
Connect AI concepts with diagnosis, prognosis, triage, workflow support and clinical decision-making contexts.
Professional Certification Programme · Online Mode
Organised by CoE-AI, NSUT Delhi · Clinical Partner: Sir Ganga Ram HospitalAI in Healthcare
A clinician-friendly, hands-on certification programme for doctors, medical students, researchers, faculty, healthcare administrators, HealthTech teams and industry professionals who need practical AI literacy for modern healthcare.
15 Weeks
120 Contact Hours
Weekend: 4h Sat + 4h Sun
Designed for non-coders
Final interactive case presentation
Clinical AI Learning MapLive cohort
Clinical interpretationRisk scores, thresholds, sensitivity and specificity.
Week 4–6Medical imaging AICNN, Grad-CAM, U-Net, ResNet, YOLO and ViT.
Week 8–10GenAI for medical assistanceClinical summaries, patient education and responsible prompts.
Week 11Responsible adoptionPrivacy, ethics, governance and doctor-in-the-loop decisions.
Week 14–15Hands-on confidence curve
Why this programme
Clinical AI learning built around interpretation, practice and responsible adoption.
The programme blends conceptual AI foundations, clinical interpretation, practical demonstrations, case studies and responsible AI use so participants can engage confidently with modern healthcare-AI systems.
Integrated hands-on sessions
Practice with data cleaning, clinical prediction models, diagnostic evaluation, Grad-CAM, SHAP/LIME and GenAI prompts.
Academic + clinical ecosystem
Organised by Centre of Excellence in Artificial Intelligence, NSUT Delhi, with Sir Ganga Ram Hospital as clinical partner.
Responsible adoption
Evaluate reliability, uncertainty, bias, subgroup performance, privacy, consent and governance before applying AI in healthcare.
120contact hours
15weeks
Onlinelive weekend mode
Beginnerfriendly AI foundation
75%attendance criterion
Healthcare AI in practice
Clinical and operational use cases covered in the programme.
Each use case is framed around interpretation, reliability and responsible adoption in healthcare settings.
Classify, localize and explain medical images using CNNs, heatmaps and Grad-CAM.
Interpret risk scores, thresholds, ROC-AUC, calibration and false-positive / false-negative trade-offs.
Understand doctor-in-the-loop alert generation for diagnosis, prognosis and triage.
Use GenAI tools for clinical summaries, patient education material and responsible prompt design.
Clean small clinical datasets, handle missing values, class imbalance and train-test splits.
Analyse errors, robustness, uncertainty, data shift, subgroup performance and model failure cases.
Participant-wise takeaways
What every participant group takes away.
Each learner enters with a different background; the programme creates a shared healthcare-AI vocabulary.
Doctors & clinicians
Interpret AI-assisted outputs, risk scores and imaging explanations before using them in clinical contexts.
Researchers & PhD scholars
Connect ML/DL workflows with real healthcare datasets, validation, reliability and explainability.
Faculty members
Develop teaching-ready examples, demos and responsible AI case discussions for healthcare education.
UG / PG students
Build a strong AI-in-healthcare foundation without needing advanced coding or mathematics.
Industry & HealthTech
Understand clinical workflow fit, reliability, user trust, regulatory questions and deployment risk.
Administrators & policy learners
Assess AI adoption, data governance, privacy, operational readiness and safe implementation.
Curriculum roadmap
15 weeks across five practical phases.
The weekly plan is grouped into a clean roadmap so learners can see the progression from AI literacy to final interactive case presentation.
Foundations
AI in healthcare, learning paradigms, clinical data and basic interpretation for doctors.
Core machine learning
Classical ML, clinical prediction, model evaluation, metrics, calibration and validation.
Deep learning & imaging
Neural networks, CNNs, medical imaging, computer vision and benchmark architectures.
Explainable, GenAI & decision support
SHAP, LIME, Grad-CAM, GenAI assistance, clinical decision support and reliability.
Responsible adoption
Privacy, ethics, governance and final interactive healthcare-AI case presentation.
📘Learn
Interactive lectures and conceptual AI foundations.
🔎Interpret
Clinical outputs, metrics, risk scores and uncertainty.
🧪Apply
Demos, data cleaning, image explanations and GenAI prompts.
✅Validate
Case studies, reliability checks and final presentation.
Interactive weekly plan
Search the 15-week curriculum.
Open each week to view the teaching component and practical / case-study component.
Fees, assessment & timelines
Programme fees, assessment and key timelines.
Students · UG / PG / PhD
₹25,000
Inclusive of GST · valid student ID required.
Professionals / Industry
₹40,000
Inclusive of GST · doctors, faculty, administrators, industry and HealthTech participants.
Assessment
- Final Presentation: 50%
- Quizzes / MCQs: 30%
- Case-study assignments: 20%
Timelines
- Programme starts: August 01, 2026
- Application deadline: July 15, 2026
- Online weekend classes
Contact
Email: coe.ai@nsut.ac.in
Organised by CoE-AI, NSUT Delhi · Clinical Partner: Sir Ganga Ram Hospital, Delhi.
Ready to register?
The registration form is now on a separate page. After submission, candidates can proceed to the NSUT portal / payment page via QR or button.