Analiza omrežja simptomi-bolezni pri človeku

diplomsko delo

Simona Malenšek (Author), Lovro Šubelj (Mentor)

Abstract

Ugotavljanje povezav med simptomi in boleznimi je za diagnostiko in zdravljenje ključnega pomena, saj vplivajo na razumevanje bolezni in oblikovanje zdravil. S pomočjo analize omrežij lahko te povezave podrobno preučimo, zanje izračunamo različne mere in odkrivamo morebitne vzorce. Načinov, kako povezati simptome in bolezni, je več, na primer, da povezave predstavljajo število skupnih pojavitev v osnutkih znanstvenih člankov. V diplomskem delu omrežje simptomov in bolezni zgradimo tako, da za njihove uteži uporabimo število zadetkov, ki jih vrne iskalnik Google za posamezno kombinacijo simptoma in bolezni. Osredotočimo se na projekcijo bolezni na podlagi skupnih simptomov in zanje s pomočjo različnih algoritmov poiščemo skupnosti. Tako pridobljene rezultate analiziramo in interpretiramo, ter jih primerjamo z rezultati referenčne raziskave.

Keywords

analiza omrežij;simptomi;iskalnik Google;odkrivanje skupnosti;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2019
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[S. Malenšek]
UDC:	004:61(043.2)
COBISS:	1538346691
Views:	541
Downloads:	196
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Analysis of human symptoms-disease network
Secondary abstract:	Identifying the links between symptoms and diseases is crucial for diagnosis and treatment, as they affect understanding of the disease and the development of medication. Through network analysis, we can examine these connections in detail by calculating different measures for them and identifying potential patterns. There are several ways to build a network of symptoms and diseases, for example, by linking them with the number of co-occurrences in abstracts of scientific articles. In the thesis, we build a network of symptoms and diseases by using the number of Google Search hits as the edge weight for each combination of symptom and disease. We focus on the network’s projection on diseases based on common symptoms and use different algorithms to find communities of diseases. The results obtained are analyzed, interpreted and compared with the results of a reference study.
Secondary keywords:	network analysis;symptoms;diseases;Google Search;community detection;computer and information science;diploma;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	65 str.
ID:	11222866