Course

Unit 1

Unit 1:

Introduction to AI in Healthcare and Diagnostics, Overview of AI and ML in healthcare, Evolution of diagnostic technologies, Types of AI systems in medical diagnostics, Benefits, limitations, and challenges, Overview of regulatory landscape

Unit 2

Unit 2:

Machine Learning Fundamentals for Diagnostics, Supervised, unsupervised, and reinforcement learning, Data preprocessing and feature extraction, Model selection and evaluation metrics, Common algorithms: Decision Trees, SVM, Random Forest, k-NN, Neural Networks

Unit 3

Unit 3:

Image Analysis and Pattern Recognition, Role of AI in medical imaging (X-rays, MRIs, CT scans), Deep learning for image classification and segmentation (CNNs, U-Nets, Tensorflow, Pytorch), Use cases in radiology and pathology, Hands-on example: Tumor detection in medical scans

Unit 4

Unit 4:

Predictive Analytics and Decision Support, Predictive modeling using patient records, Risk stratification and early disease detection, AI-based clinical decision support systems (CDSS), Integration with EHRs (Electronic Health Records)

Unit 5

Unit 5:

AI in Genomics and Laboratory Diagnostics, Introduction to bioinformatics and genomics data, ML for variant calling, gene expression profiling, AI applications in lab test data interpretation, Use cases in personalized medicine and oncology

Unit 6

Unit 6:

Case Studies, Ethics, and Future Directions, Real-world case studies across different diagnostic fields, Explainable AI (XAI) in healthcare, Ethical, legal, and privacy considerations, Challenges in clinical adoption and the road ahead.

(45 classes)

Preamble

AI in Diagnostics introduces students to the growing role of artificial intelligence and machine learning in modern diagnostic systems. The course covers algorithms used for image analysis, pattern recognition, predictive analytics, and decision support in medical diagnostics. Real-world case studies will highlight AI integration in pathology, oncology, radiology, genomics, and lab data interpretation.

Course outcomes

CO1: Explain the evolution, types, and role of AI in healthcare diagnostics.

CO2: Apply basic machine learning algorithms for healthcare data analysis.

CO3: Analyze medical images using AI tools like CNNs for diagnostic purposes.

CO4: Build predictive models for disease risk and decision support.

CO5: Interpret genomic and lab data using AI for personalized diagnostics.

CO6: Evaluate case studies and ethical issues in clinical AI applications.

Program outcome

PO1: Bioscience Knowledge

PO2: Problem Analysis

PO3: Design/Development of Solutions

PO4: Conduct Investigations of complex problems

PO5: Modern tools usage

PO6: Bioscientist and Society

PO7: Environment and Sustainability

PO8: Ethics

PO9: Individual & Team work

PO10: Communication

PO11: Project management & Finance

PO12: Lifelong learning

0 – No affinity; 1 – low affinity; 2 – Medium affinity; 3 – High affinity

Program-specific outcome

PSO 1 – Emerging technologies in clinical diagnostics

PSO 2 – Biomolecules in Medicine

PSO 3 – Molecular dysregulation in diseases

PSO 4 – Molecular technology in diagnosis and therapy

PSO 5 – Applying lab discoveries to clinical practice

PSO 6 – Microorganisms in Medicine

PSO 7 – Statistical methods to interpret and validate diagnostic results

PSO 8 – Integrate molecular diagnostics into personalized medicine

PSO 9 – Compounds as biomarkers and its specificity

PSO 10 – Bioinformatics and biological data use

0 – No affinity; 1 – low affinity; 2 – Medium affinity; 3 – High affinity

Textbook:

Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial Intelligence in Healthcare: Past, Present and Future. Stroke and Vascular Neurology. 2017;2(4):230–243.

Reference Book:

Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial Intelligence in Radiology. Nat Rev Cancer. 2018;18(8):500–510.