Automatizirano postavljanje kliničke dijagnoze korištenjem znanja iz vanjskih izvora

master's thesis

• Title (english): Automated Inference of Clinical Diagnosis from External Sources
• Author: Kristijan Palić
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Marko Đurasević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Danas se skrb o pacijentima uglavnom dokumentira u elektroničkim zdravstvenim zapisima, što pruža puno tekstualnih podataka u digitalnom formatu. Iako su takvi zapisi prvenstveno namijenjeni arhiviranju podataka o pacijentu i obavljanju određenih administrativnih zadataka, mnogi ih istraživači koriste i u različitim primjenama kliničke informatike, poput automatizirane kliničke dijagnoze.

Tema diplomskoga rada jest zadatak mapiranja anamneze i dijagnoze u kojem se za postavljanje dijagnoze koristi vanjsko znanje. Cilj diplomskog rada nije bio stvaranje sustava koji se može koristiti u stvarnom životu, već postavljanje temelja za buduća istraživanja koja bi to uspjela. Dobiveni razultati pokazuju kako se čak i uz ograničenu infrastrukuru i vrijeme mogu dobiti modeli koji koriste vanjsko znanje za postavljanje kliničke dijagnoze. Uz bolju infrastrukturu i medicinske stručnjake, bilo bi moguće izraditi sustav koji bi se koristio u stvarnom životu.

Abstract (english)

Nowadays patient care is mostly documented in electronic health records (EHRs), thus providing a lot of textual information in the digital format. While primarily designed for archiving patient information and performing administrative healthcare tasks like billing, many researchers have found secondary use of these records for various clinical informatics applications, such as automated clinical diagnosis.

The topic of the thesis is the task of clinical note-diagnosis mapping that uses external knowledge for diagnosis inference. The goal of the thesis was not to create a system that can be used in a real life scenario, but to create a foundation for some future research. Obtained results showed that even with limited infrastructure and time, it is possible to utilize the external knowledge to infer clinical diagnosis. With better infrastructure and field specialists, models based on approaches given in this thesis might actually be used in real life.

• Keywords: strojno učenje; duboko učenje; klinička dijagnoza; obrada prirodnog jezika; reprezentacijsko učenje; sličnost dokumenata
• Keywords (english): machine learning; deep learning; medical diagnosis; natural language processing; representation learning; document similarity
• Language: english
• URN:NBN: urn:nbn:hr:168:381995
• 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: 2023-01-13 13:23:32