Διπλωματική εργασία--Πανεπιστήμιο Μακεδονίας, Θεσσαλονίκη, 2025.
(EL)
The advancement in natural language processing (NLP) technologies has revolutionized various sectors, but their application in medical domains remain relatively underdevel-oped in analysing clinical notes and thus carry great potential for improvement. This thesis explores the use of deep neural networks, specifically transformer-based models, in predicting patient characteristics using surgical notes of ovarian cancer patients. The study compares the performance of RoBERTa, a general-purpose language model and GatorTron, a domain-specific model, in binary classification tasks.
(EN)
Made available in DSpace on 2025-02-17T14:21:28Z (GMT). No. of bitstreams: 2
license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)
MavromatidouAnastasiaIoannaMcs2025.pdf: 3545984 bytes, checksum: 810d75eda6a41d1e2ff97268e28aae72 (MD5)
Previous issue date: 2024-12-04
(EN)
Submitted by ΑΝΑΣΤΑΣΙΑ ΙΩΑΝΝΑ ΜΑΥΡΟΜΑΤΙΔΟΥ (
[email protected]) on 2025-02-14T17:58:50Z
No. of bitstreams: 2
license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)
MavromatidouAnastasiaIoannaMcs2025.pdf: 3545984 bytes, checksum: 810d75eda6a41d1e2ff97268e28aae72 (MD5)
(EN)
Approved for entry into archive by Κυριακή Μπαλτά (
[email protected]) on 2025-02-17T14:21:28Z (GMT) No. of bitstreams: 2
license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)
MavromatidouAnastasiaIoannaMcs2025.pdf: 3545984 bytes, checksum: 810d75eda6a41d1e2ff97268e28aae72 (MD5)
(EN)
University of Macedonia
