Metrike za procjenu kvalitete kontrole šećerne bolesti temeljene na kontinuiranom mjerenju glukoze

master's thesis

• Title (english): Metrics for Assessing the Quality of Diabetes Control Based on Continuous Glucose Measurement
• Author: Igor Aradski
• Mentor: Ratko Magjarević (mentor)
• Committee member: Ratko Magjarević (predsjednik povjerenstva)
• Committee member: Željka Lučev Vasić (član povjerenstva)
• Committee member: Dinko Oletić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-13, Croatia

Abstract

Broj osoba sa šećernom bolesti 1. tipa u porastu je i postoji potreba za unaprjeđenjem mogućnosti kontrole šećerne bolesti. Sustavi koji automatiziraju upravljanje šećernom bolesti omogućuju bolju kontrolu i olakšavaju život osoba sa šećernom bolesti. U radu su predstavljene metrike koje se koriste za procjenu kvalitete kontrole šećerne bolesti. Implementiran je LSTM model za detekciju obroka iz CGM signala te je treniran i evaluiran na skupovima podataka REPLACE-BG, OhioT1DM i CGM-VV1. Rezultati modela analizirani su zajedno s metrikama kontrole kako bi se prepoznale povezanosti performansi modela s kvalitetom kontrole šećerne bolesti.

Abstract (english)

The number of individuals with type 1 diabetes is increasing, and there is a need for improving diabetes management capabilities. Systems that automate diabetes management enable better control and improve the lives of individuals with diabetes. This paper presents metrics used for assessing diabetes management control. An LSTM model is implemented for meal detection from CGM signals and trained and evaluated on the REPLACE-BG, OhioT1DM, and CGM-VV1 datasets. The results of the model are analysed together with control metrics to identify associations between model performance and the quality of diabetes control.

• Keywords: šećerna bolest; kontinuirano mjerenje glukoze; detekcija obroka; metrike kontrole šećerne bolesti
• Keywords (english): diabetes; continuous glucose monitoring; meal detection; diabetes control metrics
• Language: croatian
• URN:NBN: urn:nbn:hr:168:402162
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 08:17:53