Přístupnostní navigace
E-application
Search Search Close
Master's Thesis
Author of thesis: Bc. Anar Davaajargal
Acad. year: 2025/2026
Supervisor: Ing. Kryštof Novotný
Reviewer: prof. Ing. Jiří Mekyska, Ph.D.
Mild cognitive impairment is a clinical condition characterized by cognitive decline that exceeds the expected boundaries of normal aging, and is associated with an elevated risk of developing dementia. Speech alterations may serve as early indicators of this decline. The aim of this study is to design and validate a set of linguistic parameters for a machine learning model that automatically assesses cognitive status from speech transcripts. Recordings of spontaneous monologues and descriptions of the Cookie Theft picture from healthy individuals and patients with various forms of mild cognitive impairment were analyzed. Linguistic features were extracted from automated transcripts and classified using an XGBoost model. Statistical analysis revealed significant deviations in speech production, which manifested as specific patterns across individual disease subtypes, such as an overall reduction in speech volume, simplification of syntax, or a decline in information content. Binary classification of mild cognitive impairment in Parkinson's disease against healthy controls based on the picture description achieved a balanced accuracy of 63% and a sensitivity of 70%. The results of this study confirm that automatic linguistic analysis offers the potential to identify specific cognitive deficits and represents a promising tool for the objective screening of neurodegenerative diseases in clinical practice.
mild cognitive impairment, linguistic analysis, natural language processing, linguistic parameters, dementia, Alzheimer's disease, Parkinson's disease, dementia with Lewy bodies, machine learning
Date of defence
11.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
A
Process of defence
Student prezentoval výsledky své práce a komise byla seznámena s posudky. Otázky oponenta a komise: Odůvodněte návrh vzorce pro výpočet indexu deskriptivnosti. Student obhájil diplomovou práci a odpověděl na otázky členů komise a oponenta.
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Telecommunications
Study programme
Audio Engineering (MPC-AUD)
Specialization
Audio Production and Recording (AUDM-ZVUK)
Composition of Committee
PhDr. Aleš Dvořák (člen) prof. Ing. Jiří Mekyska, Ph.D. (předseda) doc. Ing. MgA. Mgr. Dan Dlouhý, Ph.D. (místopředseda) Ing. Miroslav Balík, Ph.D. (člen) Ing. Michal Švento (člen)
Supervisor’s reportIng. Kryštof Novotný
Grade proposed by supervisor: A
Reviewer’s reportprof. Ing. Jiří Mekyska, Ph.D.
Grade proposed by reviewer: A
Responsibility: Mgr. et Mgr. Hana Odstrčilová