|
|
Algorithms for anomaly detection in data from clinical trials and health registries
Bondarenko, Maxim ; Blaha, Milan (referee) ; Schwarz, Daniel (advisor)
This master's thesis deals with the problems of anomalies detection in data from clinical trials and medical registries. The purpose of this work is to perform literary research about quality of data in clinical trials and to design a personal algorithm for detection of anomalous records based on machine learning methods in real clinical data from current or completed clinical trials or medical registries. In the practical part is described the implemented algorithm of detection, consists of several parts: import of data from information system, preprocessing and transformation of imported data records with variables of different data types into numerical vectors, using well known statistical methods for detection outliers and evaluation of the quality and accuracy of the algorithm. The result of creating the algorithm is vector of parameters containing anomalies, which has to make the work of data manager easier. This algorithm is designed for extension the palette of information system functions (CLADE-IS) on automatic monitoring the quality of data by detecting anomalous records.
|
|
|
Revision of the electronic diabetic file at Clinic of Diabetology IKEM
Fialová, Lenka ; Blaha, Milan (referee) ; Provazník, Ivo (advisor)
Electronic diabetic record (EDR) is an electronic medical record used in Diabetology Clinics, Instittute for Clinical and Experimental Medicine (IKEM), Prague. EDR is complex record of patient statistical and clinical data. It´s complexity and large time demands on filling in all items make EDR not user friendly. Thus, benefits of electronic medical record are not fully utilized. The paper describes solution that leads to simpler user interface as component of outpatient message allowing easy entering data. The new interface has been designed and created in the form of program module. There are described other procedures to implement module into IKEM information system Zlatokop. At the end, there are discussed the advantages and shortcomings of this revised vision and current status of project of EDR. The first part of the work is about the basic concepts and problems regarding EDR. It is about e-health, specially about the electronic health record, databases, specially about Caché, which is used in Zlatokop, about diabetes mellitus and about user experience.
|
|
|
Algorithms for anomaly detection in data from clinical trials and health registries
Bondarenko, Maxim ; Blaha, Milan (referee) ; Schwarz, Daniel (advisor)
This master's thesis deals with the problems of anomalies detection in data from clinical trials and medical registries. The purpose of this work is to perform literary research about quality of data in clinical trials and to design a personal algorithm for detection of anomalous records based on machine learning methods in real clinical data from current or completed clinical trials or medical registries. In the practical part is described the implemented algorithm of detection, consists of several parts: import of data from information system, preprocessing and transformation of imported data records with variables of different data types into numerical vectors, using well known statistical methods for detection outliers and evaluation of the quality and accuracy of the algorithm. The result of creating the algorithm is vector of parameters containing anomalies, which has to make the work of data manager easier. This algorithm is designed for extension the palette of information system functions (CLADE-IS) on automatic monitoring the quality of data by detecting anomalous records.
|
|
|
Detection and analysis of eye movement
Křístek, Jakub ; Blaha, Milan (referee) ; Provazník, Ivo (advisor)
This thesis deals with the movements of eyes and it describes the matters related to its measurement and data processing. Theoretic part is focused on eye‘s anatomy and electrophysiology, types of eye’s muscles and their movements. Even more methods, not just used electrooculography, are described thoroughly. In the second part of this thesis are designed two experiments and the measurement is realized on a group of ten tested subjects. Acquired signals are saved and processed in Matlab software, statistically analyzed and the results are interpreted.
|
|
|
Analysis of cytology images
Pavlík, Jan ; Blaha, Milan (referee) ; Kolář, Radim (advisor)
This master’s thesis is focused on automating the process of differential leukocyte count in peripherial blood using image processing. It deals with the design of the processing of digital images - from scanning and image preprocessing, segmentation nucleus and cytoplasm, feature selection and classifier, including testing on a set of images that were scanned in the context of this work. This work introduces used segmentation methods and classification procedures which separate nucleus and the cytoplasm of leukocytes. A statistical analysis is performed on the basis of these structures. Following adequate statistical parameters, a set of features has been chosen. This data then go through a classification process realized by three artificial neural networks. Overall were classified 5 types of leukocytes: neutropfiles, lymphocytes, monocytes, eosinophiles and basophiles. The sensitivity and specificity of the classification made for 4 out of 5 leukocyte types (neutropfiles, lymphocytes, monocytes, eosinophiles) is higher than 90 %. Sensitivity of classiffication basophiles was evaluated at 75 % and specificity at 67 %. The total ability of classification has been tested on 111 leukocytes and was approximately 91% successful. All algorithms were created in the MATLAB program.
|
|
|
3D vizualiazace a deep learning v mapách Stabilního katastru Čech
BLÁHA, Milan
This bachelor's thesis entitled "3D Visualization and Deep Learning in Maps of the Stable Cadastre of Bohemia" is devoted to several goals. The first one is to get acquainted with a stable cadastral map and deep learning. These terms are characterised and their meaning and other requisites are explained. Another aim of this thesis is to present the overall description of the monitored area and to cover its fundamental characteristics, historical development, physical-geographical aspects, population, settlements and a selected municipality. It also introduces the workflow of completing the practical part, which deals with the 2D and 3D visualizations of selected parts of the village of Nová Ves by Klikov, the Czech Republic. These visualisations are created on the basis of the original maps of the stable cadastre from 1827, and are made in ArcGIS Pro. Furthermore, the practical part of this thesis indicates possible practical use of these visualizations, maps of stable cadastre and deep learning.
|
|
| |
|
|
Erythrocytapheresis in the Treatment of Patients with Hereditary Haemochromatosis
Řeháček, Vít ; Bláha, Milan (advisor) ; Gašová, Zdenka (referee) ; Penka, Miroslav (referee)
BACKGROUND: Hereditary hemochromatosis (HH) is one of the most common hereditary diseases of the Euro-American population. The disease is caused by increased absorption of iron from the intestine, regardless of its current stores in the body. Excess iron is stored in tissues and organs and causes their significant damage. HH treatment consists of regular blood withdrawal, activation of erythropoesis causes the utilization of excess iron and normalization of its reserves. The standard method of blood withdrawal is venipuncture, an alternative method with the possibility of collecting larger red cell volume in one procedure is erythrocytapheresis. The aim of the research was to create a group of patients with newly diagnosed HH, apply erythrocytapheresis, verify their effectiveness, optimize and standardize treatment to reduce ferritin levels in the induction phase of treatment below 50 μg/l and subsequently keep ferritin levels below 100 μg / l in the maintenance phase of treatment. METHODS: The group of patient was created in cooperation with hepatology departments of the Hradec Králové region, by testing related patients with HH and by screening blood donors. For erythrocytapheresis, a Haemonetics MCS+ separator (Haemonetics Corp., Braintree, MA, USA) was used. The SW of MCS+ can modify red cell...
|
|
| |
|
|
Methods of molecular and cell biology in the frame of secondary school education
Blaha, Milan ; Ehler, Edvard (advisor) ; Pavlasová, Lenka (referee)
Teaching of cell and molecular biology is often restricted by financial and material limitations as well as a lack of expertise. These problems may be overcome by cooperation with scientific institutions and universities. Some scientists teach select courses under the auspices of high school. Others allow students to fulfill internships at their workplaces. The first aim of this thesis is to describe the characteristics of summer school, wherein the participants are integral for providing feedback on what matters most to them. The second goal of the study is to perform four molecular biology lab lessons in the advanced placement genetics course. The results of a qualitative research conducted among summer school participants have shown the benefits present due to contact that occurs between people of the same genuine interest. Student evaluation of molecular biology lessons performed in the advanced placement course revealed that the lab lessons are feasible and positively accepted by students. The thesis also highlights the importance of cooperation between high school and academia. Key words: molecular biology, DNA, secondary schools, gifted students
|
guest ::
RSS feed.