Logo ČVUT
Loading...
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2011/2012
Faculties | School elective courses | Katalog předmětů ECTS | Česká verze
Welcome page > Faculty of Electrical Engineering > Department of Cybernetics > Biometry and Statistics

Biometry and Statistics

The course is not on the list Without time-table
Code Completion Credits Range Language
X33BOS KZ 4 2+2s Czech
Lecturer:
Tutor:
Supervisor:
Department of Cybernetics
Synopsis:

Aim of the course is to explain methodology to be followed when statistical methods are applied in medicine. Problems concerning planning, realization and statistical evaluation of clinical and animal studies will be discussed. Practical tasks of estimation of parameters and hypothesis testing will be solved. Attention will be payed to GCP (Good Clinical Practice) directive, structure of a standard study as well as ethical aspects of clinical studies and problems of quality control of their execution. In its second part the course will focus on practical problems of biological data mining. The data mining process will be illustrated on prominent medical case studies (e.g., genomics).

Requirements:

Conditions for approval: presence in seminars and labs, measurements, presentation of solved task

Syllabus of lectures:

1. Biostatistical methods - introduction. Statistical tests and hypothesis testing

2. Statistical data analysis - data description, qualitative data, ordinal data, quantitative data. Multivariate data analysis, description of methods of explorational and confirmational analysis

3. Statistical models and their evaluation (linear and logistic regression, sensitivity, specificity, ROC)

4. Selected statistical methods (ANOVA, factor analysis, cluster analysis, survival analysis)

5. Case studies in biometry

6. Clinical and animal studies - planning, realization and statistical evaluation of a study. Definition of sufficient study range, randomization and hypothesis formulation

7. GCP (Good Clinical Practice) directive - structure of a standard study, categorization of study into individual phases. Monitoring and statistical evaluation of studies, ethical aspects of studies

8. Data warehouses and their utilization in data mining. Design and implementation of data warehouses

9. Process of data mininig - CRISP methodology. Statistical and machine learning algorithms

10.Data preprocessing - methods and tools

11.Data mining - case studies

12.Biomedical data on internet

13.Genomics - foundations, genomic and proteomic data modeling

14.Genomic, metabolic and signal transduction networks.

Syllabus of tutorials:

1.Basic biostatistical methods - practical overview

2.Matlab statistical toolbox

3.Other statistical tools - R system, packages

4.Application of methods to real-world biomedical data

5.Data preprocessing of biomedical data

6.Task assignment and solving

7.Task solving

8.Particular examples of clinical studies - case analysis, design of a study, preparation of individual phases

9.Methods for study evaluation, hypothesis formulation, problem of study range

10.Methods of explorational and confirmational analysis

11.Multivariate statistical analysis

12.Machine learning attribute-valued methods - WEKA tools

13.Genomic, metabolic and signal transduction networks - modeling

14.Assignments - presentations, grading

Study Objective:
Study materials:

There is no text-book covering the course completely; any book on modern operating systems can be used. The lecturer will hint resources to particular topics.

Note:
Further information:
No time-table has been prepared for this course
The course is a part of the following study plans:
Generated on 2012-7-9
Copyright © Jiří Kosek, 2010–2012 | Copyright © ČVUT, 2010–2012 | Hosted by Výpočetní a informační centrum ČVUT | Send your questions and comments to HelpDesk ČVUT nebo na spravcekos@cvut.cz
For updated information see http://bilakniha.cvut.cz/en/predmet11595104.html