BMM208

School of Engineering \ Biomedical Engineering

3

6

Compulsory

Turkish

MAT 201

Department of Biomedical Engineering

Introduction to AI applications in healthcare. Medical data types (tabular, text, imaging). Supervised and unsupervised learning. Feature extraction. Feature selection methods. Machine learning algorithms (K-nearest neighbor, K-means clustering, linear regression, artificial neural networks). Cross-validation methods. Performance metrics. Ethical issues and the future of AI in healthcare.

R. O. Duda, P. E. Hart and D. G. Stork, “Pattern Classification,” 2nd Edition, John Wiley and Sons, Inc., New York, 2001.
Ethem Alpaydin. Introduction to Machine Learning 4th Edition. The MIT Press. 2014.
Various journal publications

The aim of this course is to show students the application areas of artificial intelligence in medicine and to equip them with the ability to use AI methods to solve complex medical or biology-focused problems they may encounter in the future.

1. Understands the problems related to artificial intelligence in health.
2. Have knowledge about medical data types.
3. Have knowledge about the development of artificial intelligence models.
4. Understands model development strategies.
5. Derives new ideas to analyse data or develop a new method in the field of health.

Week 1: Introduction to Artificial Intelligence Applications in Health
Week 2: Basic Statistics and Linear Algebra
Week 3: Medical Data Types
Week 4: Guided and Unguided Learning
Week 5: Feature Extraction
Week 6: Feature Selection Methods
Week 7: Machine Learning Algorithms
Week 8: Machine Learning Algorithms
Week 9: Classification and Prediction Model Development
Week 10: Cross Validity Methods
Week 11: Performance Metrics
Week 12: Future of Artificial Intelligence in Health