NAPOVEDNI MODELI V BIOMEDICINI

Fazlija, Diana

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	NAPOVEDNI MODELI V BIOMEDICINI
Authors:	ID Fazlija, Diana (Author) ID Štiglic, Gregor (Mentor) More about this mentor...
Files:	MAG_Fazlija_Diana_2016.pdf (1,02 MB) MD5: D1348EA9E8CA82DBB9136AE0A2F598B4
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FZV - Faculty of Health Sciences
Abstract:	Ljudje so že tisočletja imeli željo, da bi lahko napovedali prihodnost. Zelo pogosta je želja po tem, da bi predvideli, kaj se nam obeta v prihodnosti, kakšno bo naše življenje nekega dne. Prav takšno željo imajo tudi različna podjetja in raziskovalne ustanove, saj želijo vedeti ali bo nek izdelek ali storitev uspešen na trgu ter ali se bodo naložbe v prihodnosti izplačale. Na veliko veselje vseh je doba digitalizacije, s pomočjo podatkovnih baz in z močjo analitike, to omogočila z uporabo napovednih modelov. V magistrskem delu smo predstavili definicijo napovednih modelov in raziskali, kateri so tisti napovedni modeli, ki se najpogosteje uporabljajo na področju biomedicine. Najpogosteje uporabljene napovedne modele smo tudi podrobneje opisali in prikazali z grafičnim prikazom. Predstavili smo tudi uporabnost napovednih modelov na različnih področjih in njihovo praktično uporabo v programskem okolju R. Zastavili smo si dve raziskovalni vprašanji, na kateri smo dobili odgovore s pomočjo analize znanstvenih člankov iz baze PubMed. Kot prvo raziskovalo vprašanje smo ugotavljali, kateri so trije najpogostejši napovedni modeli, kot drugo raziskovalno vprašanje pa nas je zanimalo, kako se je v zadnjih dvajsetih letih spreminjalo število člankov, v katerih so uporabljeni napovedni modeli. Iz baze PubMed smo povzeli statistične podatke za zadnjih dvajset let in s pomočjo MS Excela prišli do zanimivih rezultatov. Ugotovili smo, da se kot trije najpogosteje uporabljeni napovedni modeli pojavljajo logistična regresija, linearna regresija in nevronske mreže. Po pričakovanjih pa smo tudi ugotovili, da je število člankov z uporabljenimi napovednimi metodami v zadnjih dvajsetih letih naraščalo, kar pomeni, da so jih raziskovalci vedno pogosteje vključevali v svoje raziskave. Iz tega lahko sklepamo, da se napovedni modeli v raziskovanju in praksi uporabljajo vse pogosteje, kar kaže na njihov pozitiven vpliv pri napovedovanju dogodkov in izidov.
Keywords:	napovedni modeli, napovedno modeliranje, R studio, biomedicina
Place of publishing:	Maribor
Publisher:	[D. Fazlija]
Year of publishing:	2016
PID:	20.500.12556/DKUM-64484
UDC:	004.43
COBISS.SI-ID:	2287012
NUK URN:	URN:SI:UM:DK:YFUACZON
Publication date in DKUM:	02.12.2016
Views:	1803
Downloads:	205
Metadata:
Categories:	FZV
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:	English
Title:	PREDICTIVE MODELING IN BIOMEDICINE
Abstract:	For thousands of years people had desire to be able to predict the future. A desire to see what is there for us in the future or how our life will change some day is very often among people. Various companies and research institutions have also the same desire or goal because they want to know whether a specific product or service will be successful on the market and whether the investments will be paid off in the future. The era of digitalization, use of databases with the power of analytics have this desire made possible by using predictive models. In master thesis we introduce the definition of predictive models and which are the most commonly used predictive models in the field of biomedicine. The most often used predictive models were described in details and visualized. The applicability of predictive models in various fields of science was also demonstrated as well as their practical application in the programming environment R. We have set two research questions and searched for answers through the analysis of scientific articles from the PubMed database. Our first question was to determine which are three most often used predictive models in biomedicine. And for the second question we were interested in how the number of articles using the predictive models has changed in the last twenty years. We summarized statistic data from the PubMed database for the last twenty years and by using MS Excel came up with some interesting results. We found out that three most often used predictive models are logistic regression, linear regression and neural networks. As expected, we also found out that the number of scientific articles using predictive models has increased during the last twenty years which suggests that researchers include them more often in their researches. From this results we can make a conclusion that the predictive models are used more often in research and practice environment, which shows their positive influence in predicting events and outcomes.
Keywords:	predictive models, predtive modeling, R studio, biomedicine

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back