Decision Support Algorithms in Healthcare

Data is displayed for academic year: 2023./2024.

Course Description

Clinical decision support systems: historical overview and current status. Application of artificial intelligence in biomedical informatics. Design of decision support systems. Artificial intelligence algorithms in biomedical informatics: symbolic approach and connectivist approach. Computer ontologies in biomedical informatics. Machine learning algorithms with clear interpretation: trees and decision rules, probabilistic models, interpretation of deep models. Machine learning algorithms without clear interpretation and their application: ensemble methods and deep neural network methods. The context of using a decision support system. Evaluating different approaches.

Study Programmes

Learning Outcomes

  1. Enumerate examples of usage of AI algorithms in biomedical informatics
  2. Classify the AI algorithms for decision support in clinical practice
  3. Analyze the means of decision support system design, in context of wider software architecture for medical procedures
  4. Identify the requirements for decision support systems
  5. Plan and design knowledge database structure, and select appropriate AI algorithms for decision support
  6. Justify appropriate decision support AI algorithm usage clinical setting

Forms of Teaching

Lectures

Independent assignments

Laboratory

Week by Week Schedule

  1. Lectures: Course administration. Introduction to clinical decision support systems.
  2. Lectures: Symbolic approaches in designing decision support systems: logic, rule-based systems, probabilistic systems., Laboratory: Symbolic approaches in designing decision support systems: logic, rule-based systems, probabilistic systems.
  3. Lectures: Computer ontologies in decision support systems., Laboratory: Computer ontologies in decision support systems.
  4. Lectures: Machine learning algorithms with clear interpretation: decision trees and decision rules., Laboratory: Machine learning algorithms with clear interpretation: decision trees and decision rules.
  5. Lectures: Machine learning algorithms without clear interpretation: ensemble methods.
  6. Lectures: Machine learning algorithms without clear interpretation: deep learning methods., Laboratory: Machine learning algorithms without clear interpretation: ensembles.
  7. Lectures: Machine learning algorithms without clear interpretation: deep learning methods., Laboratory: Machine learning algorithms without clear interpretation: deep learning methods.
  8. Lectures: Midterm exam.
  9. Lectures: Methods for interpreting deep learning models., Laboratory: Methods for interpreting deep learning models.
  10. Lectures: Design of clinical decision support system.
  11. Lectures: Design of clinical decision support system.
  12. Lectures: Applications of clinical decision support systems.
  13. Lectures: Evaluation of clinical decision support systems.
  14. Lectures: Project presentations.
  15. Lectures: Final exam.

Literature

(.), Subasi A. Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques. Academic Press, 2019, ISBN 978-0-12-817444-9,
(.), Samek W, Montavon G, Vedaldi A, Hansen LK, Müller K-R. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Lecture Notes in Artificial Intelligence 11700, Springer, 2019, ISBN 978-3-030-28953-9,
(.), Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: Practical Machine Learning Tools and Techniques. 4th ed., Morgan Kaufmann, 2016, ISBN 978-0-12-804291-5,
(.), Rangayyan RM. Biomedical Signal Analysis, 2nd Edition. Wiley-IEEE Press, 2015, ISBN: 978-0-470-91139-6Berner ES, Clinical Decision Support Systems, Theory and Practice. Health Informatics, Springer, 2007, ISBN 978-0387-33914-6,

For students

General

ID 261446
  Winter semester
5 ECTS
L3 English Level
L1 e-Learning