Sirvi Autor "Haug, Markus, juhendaja" järgi

Nüüd näidatakse 1 - 5 5

Andmepõhiste ravitrajektooride konstrueerimise meetodite süstemaatiline analüüs
(Tartu Ülikool, 2025) Valt, Kirke; Haug, Markus, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
In recent years health care has undergone a digital revolution where an increasingly central role is played by the systematic collection and analysis of health data. This Bachelor's thesis investigates methods for constructing data-driven health trajectories. The objective was to map existing solutions, evaluate their reproducibility and implement them in the RITA-MAITT project on the HPC-SAPU server. A total of 622 articles were examined, from which 15 passed the literary analysis. Reproducibility analysis resulted in three remaining articles, out of which two were implemented. The findings highlight that even though many innovative solutions have been suggested for health trajectory mapping, their transferability is constrained by lack of documentation and compatibility issues with new versions of analytical software.
Patsientide enim levinud ravitrajektooride leidmine DTW
(Tartu Ülikool, 2022) Loorits, Brandon; Kolde, Raivo, juhendaja; Haug, Markus, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Lõputöö eesmärk on luua töövoog, mis aitab leida kasutajal enim levinud ravitrajektoorid teatud haigusega seotud patsientide kohordil. Välja pakutud töövoog koosneb 7 osast - andmete soovitud kujule viimine, sarnasusmaatriksi arvutamine dünaamilise ajadeformatsiooni meetodil, klasterdamine, siluetianalüüs, trajektooride korrigeerimine, tulemustrajektooride loomine ja visualiseerimine. Lõputöös pakutakse välja töövoog, mis potentsiaalselt aitab leida kasutajal enim levinud ravitrajektoorid automaatselt. Antud töövoog kasutab ravitrajektooride sarnasuse määramiseks dünaamilist ajadeformatsiooni, klasterdamise meetodina hierarhilist aglomeratiivset klasterdamist ning klasterdamise hindamiseks siluetianalüüsi. Töövoo tulemused visualiseeritakse kui ka prinditakse väljundina.
Patsientide ravimikasutuse klasterdamine ATC koodide alusel
(Tartu Ülikool, 2024) Konsa, Charleen; Haug, Markus, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Healthcare data provides an opportunity to study patients’ drug trajectories. This thesis aims to create a workflow that clusters patients based on their drug use using ATC codes. In addition, a user interface is developed that can be used to interactively run the workflow. The workflow consists of 5 parts: filtering, drug trajectories compilation, drug trajectories comparison, drug trajectories clustering, and cluster analysis. As a result of the workflow, patients are divided into clusters, which are given a simple overview. The results can be used for further research to find the reasons for the different drug trajectories. The user interface consists of 4 parts. Its sidebar displays the main user inputs that can influence patient selection, clustering, and analysis. Tabs display the results of clustering and analysis. The results and the used parameters in the user interface can be downloaded as RDS and CSV files.
Psoriaasi kaasuvate haiguste uurimine Coxi regressiooni abil
(Tartu Ülikool, 2024) Sild, Ami; Kolde, Raivo, juhendaja; Haug, Markus, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The aim of this thesis was to find out how does the risks of comorbidities vary between psoriasis patients and non-psoriasis patients. Psoriasis is a chronic skin condition, that brings daily physical and emotional burden for those who are diagnosed with it. This disease has many comorbidities. Early treatment could significantly increase the quality of life for patients and also decrease the costs in case the disease progresses further. The data used in this research was collected by University of Tartu. It includes health data from approximately 10% of Estonian population. The comorbidities analyzed were selected based on existing research. A total of 13 comorbidities were included in the final analysis. This Master’s thesis could help doctors focus more on patients who are more likely to develop certain diseases. It could lead to changes in the treatment to prevent these comorbidities. The result of this thesis could also be used to make targeted screening tests to prevent comorbidities in psoriasis patients.
R-pakett OMOP CDM kujul andmete elukestusanalüüsiks
(Tartu Ülikool, 2024) Aava, Greete Kelli; Haug, Markus, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
The Bachelor's thesis focuses on the creation of a survival analysis tool for health data in the form of the Observational Medical Outcomes Partnership (OMOP) common data model. The goal is to create an R package that includes database query generation, execution of database queries and visualization of results with a graphical user interface. The work is divided into a theoretical part, where the survival analysis methodology and a common data model are introduced, and a practical part, where the created R-package and its capabilities are described.