Analiza skupova podataka o dijabetesu metodama strojnog učenja

undergraduate thesis

• Title (english): Machine learning based analysis of diabetes datasets
• Author: Niko Kaštelan
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Mihael Kovač (član povjerenstva)
• Committee member: Andrej Slapničar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Dijabetes tipa 2 sve je češća bolest, a broj oboljelih raste zbog promjene načina života. Iako postoje načini da sami usporimo širenje dijabetesa, ovaj rad pokušava objasniti koji elementi utječu na nastanak dijabetesa te što utječe na hospitalizaciju uzrokovanu dijabetesom. Strojnim učenjem analiziraju se dva skupa podataka, s jednim se pokušava umanjiti vjerojatnost brzog ponovnog prijema u bolnicu nakon otpusta i tako zaštititi pacijente koji su u najvećem riziku od bolničke hospitalizacije dok se s drugim analiziraju pacijenti s dijabetesom kako bi se pronašle značajke koje dovode do te bolesti. U oba slučaja korišten je klasifikator slučajne šume te metode odabira značajki i uravnoteženja nebalansiranih razreda ciljnih varijabli.

Abstract (english)

Type 2 diabetes is an increasingly common disease, and the number of patients is mostly rising due to the changes in our way of life. Although there are ways to slow down the spread of diabetes, this paper aims to explain which factors influence the onset of diabetes and what affects hospitalization caused by diabetes. Machine learning is used to analyze two data sets: one aims to reduce the likelihood of rapid readmission to the hospital after discharge, thus protecting patients at the highest risk of hospital readmission, while the other analyzes patients with diabetes to identify the main features that cause the disease. In both cases, a random forest classifier was used, along with feature selection methods and techniques for balancing imbalanced target variable classes.

• Keywords: strojno učenje; dijabetes; bolnička hospitalizacija; slučajna šuma; odabir značajki; neuravnoteženost razreda; centroidi klastera
• Keywords (english): machine learning; diabetes; hospital readmission; random forest; feature selection; class imbalance; cluster centroids
• Language: croatian
• URN:NBN: urn:nbn:hr:168:501961
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 21:02:25