Course detail

Artificial Intelligence in Medicine

FEKT-AUINAcad. year: 2012/2013

The subject deals with the areas of artificial intelligence applied in the decision-making process in medicine. It is focused on resolution methods, introduction to artificial neural networks and fundamental principles of expert systems. It also deals with application of probability methods for uncertainty decision-making and with the use of fuzzy logic in approximation decision-making

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

doc. Ing. Jiří Kozumplík, CSc.

Department

Department of Biomedical Engineering (UBMI)

Learning outcomes of the course unit

A fundamental knowledge of symptomatic classification methods, neural network and expert systems. The ability to design simple medical classification and decision-making systems.

Prerequisites

Knowledge at secondary school level and of completed subjects in the study area

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Teaching methods depend on the type of course unit as specified in the article 7 of BUT Rules for Studies and Examinations.

Assesment methods and criteria linked to learning outcomes

Requirements for successful completion of the subject are specified by guarantor’s regulation updated for every academic year.

Course curriculum

Artificial intelligence. Resolution, deterministic and statistical classifiers. Learning prediction classifiers, neural network. Expert system principles. Deduction logic, proposition logic, prediction logic. Uncertainty decision-making and inaccurate inference. Fuzzy sets, language variable, fuzzy logic and approximation conclusion.

Work placements

Not applicable.

Aims

To provide the students with understanding of the areas of artificial intelligence used in the decision-making process in medicine. To explain the theoretical principles of computer-aided medical diagnostics.

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

Extent and forms are specified by guarantor’s regulation updated for every academic year.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Kozumplík, J., Provazník, I.: Umělá inteligence v medicíně. Elektronická skripta. ÚBMI FEKT VUT v Brně, Brno, 2007. (CS)

Recommended reading

Šnorek, M.: Neuronové sítě a neuropočítače. Skripta ČVUT, Praha, 2002 (CS)

Classification of course in study plans

  • Programme BTBIO-A Bachelor's

    branch A-BTB , 3. year of study, winter semester, compulsory

  • Programme EEKR-CZV lifelong learning

    branch ET-CZV , 1. year of study, winter semester, compulsory

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

doc. Ing. Jiří Kozumplík, CSc.
prof. Ing. Valentine Provazník, Ph.D.

Syllabus

Introduction to artificial intelligence, applications in medical practice. Decision-making principles in medicine.
Recognition. Symptom selection and arrangement, symptomatic recognition methods, cluster analysis.
Deterministic classifiers. Discriminance function method. Minimal distance classification.
Statistical classifiers. Criterion of minimal probability decision error. Bayes criterion.
Learning classifiers. Introduction to neural network. Single neuron, perceptron. Hamming’s network.
Classification possibilities of one- or multi-layer perceptrons. Hopfield network. Learning of forward networks.
Expert systems. Expert system languages, programming language CLIPS.
Expert system principles. Deduction logic, proposition logic, prediction logic.
Logic systems and the resolution method. Inference – forward and back sequencing.
Uncertainty and inaccurate inference, probability, certainty factors, the Dempster-Shafer theory.
Fuzzy sets and operation. Language variable, fuzzy numbers and fuzzy relations.
Fuzzy logic, approximate search, fuzzy inference composition rule. Defuzzyfication.
Expert engineering, the principles of expert system design.

Exercise in computer lab

13 hours, compulsory

Teacher / Lecturer

Ing. Marina Filipenská, Ph.D.
Ing. Martin Chrobák

Syllabus

Computer exercises in Matlab and CLIPS
Deterministic classifiers and statistical classifiers in Matlab
Neural network in Matlab
The language CLIPS
The simple decision-making (expert) system using the language CLIPS
Uncertainty inferences (fuzzy rules) in CLIPS
Construction of simple fuzzy rules in CLIPS

The other activities

13 hours, compulsory

Teacher / Lecturer

doc. Ing. Jiří Kozumplík, CSc.

Syllabus

Deterministic classifiers in Matlab
Statistical classifiers in Matlab
Neural networks in Matlab
Implementation of simple decision-making (expert) systems using the language CLIPS
Implementation of simple fuzzy inferences using the language CLIPS