Predictive modeling of medication adherence using machine learning techniques

Georgiou, Konstantina; Γεωργίου, Κωνσταντίνα

dc.contributor.author	Georgiou, Konstantina	en
dc.contributor.author	Γεωργίου, Κωνσταντίνα	el
dc.date.accessioned	2025-06-12T09:13:04Z
dc.date.available	2025-06-12T09:13:04Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/62049
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.29745
dc.description	Εθνικό Μετσόβιο Πολυτεχνείο--Μεταπτυχιακή Εργασία. Διεπιστημονικό-Διατμηματικό Πρόγραμμα Μεταπτυχιακών Σπουδών (Δ.Π.Μ.Σ.) "Μεταφραστική Βιοιατρική Μηχανικής και Επιστήμης"	el
dc.rights	Αναφορά Δημιουργού 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/gr/	*
dc.subject	Φαρμακευτική συμμόρφωση	el
dc.subject	Μηχανική μάθηση	el
dc.subject	Αλγόριθμοι συσταδοποίησης	el
dc.subject	Προσαρμοσμένες παρεμβάσεις υγείας	el
dc.subject	Medication adherence	en
dc.subject	Machine learning	en
dc.subject	Clustering algorithms	en
dc.subject	Tailored healthcare interventions	en
dc.title	Predictive modeling of medication adherence using machine learning techniques	en
heal.type	masterThesis
heal.classification	Meachine learning	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-10
heal.abstract	This thesis develops predictive models to assess medication adherence based on socioeconomic factors, using machine learning techniques. Unsupervised clustering methods, such as K-means and hierarchical clustering, were applied to two datasets: one from 429 patients at Jena University Hospital (Germany) and another from 81 individuals in Greece. The German sample (average age 63.54 years) showed higher adherence, while the Greek sample (average age 54.9 years) demonstrated greater variability. Key factors identified as predictive of higher adherence include age, caregiver involvement, unemployment, and lower education levels. The study highlights the potential of machine learning to create tailored healthcare interventions by predicting adherence behaviors, considering demographic and socioeconomic factors.	en
heal.advisorName	Nikita, Konstantina	en
heal.committeeMemberName	Stamou, Georgios	en
heal.committeeMemberName	Voulodimos, Athanasios	en
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	57 σ.	el
heal.fullTextAvailability	false