Medical decision-making is a central process in medical practice and science. To assume appropriate responsibility, physicians must have a clearly informed decision-making process that is based on a rational process and consistent with evidence-based medicine and medical practice. Regardless of the nature, pathway, and support of the decision-making process, the responsibility for the decision always rests with the health care professional and the patient who accepts the decision.
Decision-making is a cognitive process in which a choice is made from a set of options. Decision-making may be intuitive or reasoned, biased or unbiased, and the quality of the decision clearly depends on the input variables, which may be the result of learning, search, and measurement processes, each of which is subject to bias. Information technology supports medical decision making with a variety of knowledge-based methods. The ability to search large amounts of information and process data in a short period of time, as well as machine learning, can contribute to rational decision making.
The main objective of the course is to familiarize students with the decision-making process and the formalization of decision-making, and to explain and understand the chosen methods of decision-making with direct application in medicine. Course content includes interpretation and adoption of information about the decision-making process and formalization, consequences of decision-making, risk assessment in decision-making, decision rules, knowledge-based decision-making methods, machine learning, pattern recognition, artificial neural networks, and artificial intelligence in medical decision-making.
 

The list of lectures (with topics and descriptions):
1. Introductory lecture / Decision making process and formalization
Lecture 1 is an introductory course lecture. The students will receive basic information about the course, schedule, teaching and assessment. They are acquainted with the definition and emergence of decision-making process and formalization. Students are familiarized with the structure and scope of the topics covered by the course.
Learning outcome: To define the decision-making process and the concept of decision-making formalization.
2. Decision tree / decision rules
The students will receive basic knowledge about decision tree method for multicriteria decision- making and decision rules in biomedicine.
Learning outcome: Compare the decision tree and decision rules methods.
3. Knowledge-based decision-making methods
Lecture 3 is introductory about knowledge-based decision-making methods as ELECTRE (ELimination Et Choice Translating REality  ), TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution ), AHP (Analytic Hierarchy Process ) and ANP (Analytic Network Process)                          Learning outcome: Identify knowledge-based decision-making methods, describe advantages and disadvantages.
4. Artificial Intelligence (Neural Networks and Pattern Recognition)
In lecture 4 is described the application of artificial intelligence (pattern recognition and artificial neural networks ) in the decision-making process in medicine. Learning outcome: Compare methods of pattern recognition and artificial neural networks.
5. Decision making modeling (project) 
The lecture is interactive discussion, students and teacher are gathered together at the end of the course, guidance for further learning and development in the application of information technology and multicriteria  decision-making methods in medicine are provided.

The list of seminars:
1-2 Practical implication of decision-making process in medicine 
3-4 Free software for decision making modeling 
5-6 How to transform decision tree into decision rules (Rapid Miner tool)
7-8-Clinical decision rules – case studies
9-10 Analysis of decision-making methods
11-12 Graphic type of decision-making model using the AHP method
13-14 Applying the Analytic Hierarchy Process in healthcare research
15-16 Neural networks in medicine
17-18 Deep dive in clinical data (The Hypothetico-Deductive model of reasoning, and pattern recognition)
19-20 Decision making modeling with Superdecisions tool