Attention-Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental condition characterized by difficulties in attention, impulsivity, and/or hyperactivity, whose diagnosis is primarily based on clinical and behavioral criteria. This approach may introduce subjectivity and variability in the assessment, making the identification of neurophysiological patterns potentially valuable as support for the diagnostic process. This work aims to explore the use of electroencephalographic signals (EEG) and Machine Learning (ML) techniques for the automatic classification of ADHD. Following an introductory section outlining the theoretical background and the EEG patterns associated with the disorder, a possible analytical approach is described, based on signal preprocessing and on the extraction of relevant features. These features are subsequently employed in a Support Vector Machine (SVM) classification model. The results are discussed in terms of their potential clinical application, highlighting the limitations and future perspectives of the proposed approach.
Il Disturbo da Deficit di Attenzione e Iperattività (ADHD) è una condizione neuro-evolutiva caratterizzata da difficoltà di attenzione, impulsività e/o iperattività, la cui diagnosi si basa principalmente su criteri clinici e comportamentali. Questa impostazione può introdurre soggettività e variabilità di valutazione, rendendo promettente l’individuazione di pattern neurofisiologici a supporto del processo diagnostico. Questo elaborato si propone di analizzare l’utilizzo di segnali elettroencefalografici (EEG) e tecniche di Machine Learning (ML) per la classificazione automatica dell’ADHD. Infatti, dopo una parte introduttiva riguardante le basi teoriche e i pattern EEG legati al disturbo, viene descritto un possibile approccio di analisi basato sul preprocessing e sull’estrazione di caratteristiche significative dei segnali. Tali features vengono successivamente impiegate in un modello di classificazione mediante Support Vector Machine (SVM). I risultati vengono discussi in termini di potenziale applicazione clinica, evidenziando limiti e prospettive future dell’approccio.
Analisi di segnali EEG per la classificazione dell’ADHD mediante Machine Learning
GREGGIO, CHIARA
2025/2026
Abstract
Attention-Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental condition characterized by difficulties in attention, impulsivity, and/or hyperactivity, whose diagnosis is primarily based on clinical and behavioral criteria. This approach may introduce subjectivity and variability in the assessment, making the identification of neurophysiological patterns potentially valuable as support for the diagnostic process. This work aims to explore the use of electroencephalographic signals (EEG) and Machine Learning (ML) techniques for the automatic classification of ADHD. Following an introductory section outlining the theoretical background and the EEG patterns associated with the disorder, a possible analytical approach is described, based on signal preprocessing and on the extraction of relevant features. These features are subsequently employed in a Support Vector Machine (SVM) classification model. The results are discussed in terms of their potential clinical application, highlighting the limitations and future perspectives of the proposed approach.| File | Dimensione | Formato | |
|---|---|---|---|
|
Greggio_Chiara.pdf
Accesso riservato
Dimensione
593.69 kB
Formato
Adobe PDF
|
593.69 kB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/110818