Course detail

Computer-Aided Medical Diagnostics

FEKT-MPDGAcad. year: 2019/2020

The course is oriented ot the use of artifficial intelligence in medicine. It is focused on computer-aided medical diagnostics, principles of decision making in medicine, work with uncertainty in medical data, reasoning under uncertainty, principles of fuzzy representation of uncertain information, and structure of expert systems. Students will get experimental knowledgein programming of expert systems.

Language of instruction

English

Number of ECTS credits

4

Mode of study

Not applicable.

Offered to foreign students

Of all faculties

Learning outcomes of the course unit

The student will be able to:
- describe basic methods of computer processing of biomedical data,
- explain fundamental terms of computer-aided medical diagnostics,
- describe principle of basic methods for probability decision-making,
- discus advantages and disadvantages of the methods,
- design simple expert systems,
- evaluate quality of decision-making methods based on defined requirements.

Prerequisites

The student should be able to explain fundamental principles of probability calculus, should know basic terms of data processing and should be oriented in basic knowledge of database systems. Generally, knowledge of mathematics on the level of Bachelor study is required.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Techning methods include lectures and computer laboratories. Course is taking advantage of e-learning (Moodle) system. Students have to write projects/assignments during the course.

Assesment methods and criteria linked to learning outcomes

up to 30 points from computer exercises (individual project)
up to 70 points from finel written exam
The exam is oriented to verification of orientation in terms of computer-aided medical diagnostics and ability to apply basic principles of decision-making in medicine.

Course curriculum

1. Introduction to expert systems, artifficial intelligence.
2. Probability inference in medicine, diagnostic tests.
3. Probability tests, quality of tests, Bayes theorem.
4. Pre-test and post-test probability, sensitivity and specificity, decision trees.
5. Knowledge representation, production rules.
6. Logic in knowledge representation, Venn diagrams, propositional logic.
7. Inference, modus ponens.
8. Proof of claim, resolution rule.
9. Examples of resolution.
10. Uncertainty and uncertain inference.
11. Fuzzy sets.
12. Fuzzy logic.

Work placements

Not applicable.

Aims

The aim of the course is to inform students about principles of computer-aided diagnostics in medicine using artifficial intelligence and design of simple diagnostics systems used in medicine.

Specification of controlled education, way of implementation and compensation for absences

Computer exercises are obligatory. Excused absence can be substituted.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Giarratano, J., Riley, G.: Expert Systems. Principles and Programming. PWS-Publishing Company, Boston, 632 str., 1998. (EN)
Krishnamoorthy, C. S., Rajeev, S.: Artificial Intelligence and Expert Systems for Engineers. CRC Press, 1996. (EN)
Nguyen, H. T., Walker, E. A.: A First Course in Fuzzy Logic. CRC Press, 1997. (EN)
Provazník, I., Kozumplík, J. Expertní systémy. Brno: VUTIUM, 1999. ISBN 8021414863 (CS)

Recommended reading

Not applicable.

Elearning

Classification of course in study plans

  • Programme EEKR-M Master's

    branch M-BEI , 2 year of study, winter semester, elective specialised

  • Programme EEKR-CZV lifelong learning

    branch EE-FLE , 1 year of study, winter semester, elective specialised

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

Syllabus

Introduction to application of artifficial intelligence (AI) in medicine. Computer-aided medical diagnostics (CAMD), its applications, programming languages of AI, design of CAMD systems, expert systems, meaning and the use of knowledge.
Principles of decision making in medicine, medical data, information, knowledge , metaknowledge, hypotheses, statistics in decision making, diagnosis intrepretation.
Uncertainty in medical data, reasoning under uncertainty, traditional Bayesian probability v. factors of uncertainty in medicine.
Measure of belief and disbelief in inference, similarity with human reasoning, principles of fuzzy representation of uncertain information.
Fuzzy numbers, fuzzy relations and fuzzy logic for CAMD.
Structure of expert systems, meaning of knowledge and facts, inference.
Representation of medical knowledge, production rules, decision trees.
Deductive logic and predicate logic in medical diagnostics.
Logic systems and resolution methods, forward and backward chaining of knowledge.
Programming of expert systems, fundamentals of CLIPS language, examples of design of expert systems in CLIPS.
Knowledge engineering, cooperation of a knowledge engineer and a medical expert in knowledge mining, priciples od expert system design.
Fuzzy rules in expert systems.
Inference composition rule in medical expert systems, defuzzification for diagnosis.

Exercise in computer lab

13 hod., compulsory

Teacher / Lecturer

Syllabus

Individually solved projects of design of expert system as systems of computer-aided medical diagnostics.

Elearning