Evaluating Digital Profiles of Patients in the Field of Addiction
Analýza digitálních profilů pacientů v adiktologické doméně
Authors
Supervisors
Reviewers
Editors
Other contributors
Journal Title
Journal ISSN
Volume Title
Publisher
České vysoké učení technické v Praze
Czech Technical University in Prague
Czech Technical University in Prague
Date
Abstract
This master thesis is dedicated to the analysis of data from users of an application designed to treat nicotine addiction. We have compiled several machine-learning models for solving classification and regression problems. First, we constructed a series of classification models to predict the likelihood of successful completion of therapy in individual patients. By examining in detail many of the relevant functions, we tried to identify the most influential parameters that significantly affect the results of treatment. Second, Our investigation extended to regression models focused on adherence parameters. These models were tuned to predict the degree of adherence of patients to the prescribed treatment. By analyzing adherence models, we sought to uncover valuable insights about the effectiveness of therapy. As part of our research, we also measured similarities between different adherence variables, which shed light on potential correlations and revealed new avenues for personalized treatment approaches.
This master thesis is dedicated to the analysis of data from users of an application designed to treat nicotine addiction. We have compiled several machine-learning models for solving classification and regression problems. First, we constructed a series of classification models to predict the likelihood of successful completion of therapy in individual patients. By examining in detail many of the relevant functions, we tried to identify the most influential parameters that significantly affect the results of treatment. Second, Our investigation extended to regression models focused on adherence parameters. These models were tuned to predict the degree of adherence of patients to the prescribed treatment. By analyzing adherence models, we sought to uncover valuable insights about the effectiveness of therapy. As part of our research, we also measured similarities between different adherence variables, which shed light on potential correlations and revealed new avenues for personalized treatment approaches.
This master thesis is dedicated to the analysis of data from users of an application designed to treat nicotine addiction. We have compiled several machine-learning models for solving classification and regression problems. First, we constructed a series of classification models to predict the likelihood of successful completion of therapy in individual patients. By examining in detail many of the relevant functions, we tried to identify the most influential parameters that significantly affect the results of treatment. Second, Our investigation extended to regression models focused on adherence parameters. These models were tuned to predict the degree of adherence of patients to the prescribed treatment. By analyzing adherence models, we sought to uncover valuable insights about the effectiveness of therapy. As part of our research, we also measured similarities between different adherence variables, which shed light on potential correlations and revealed new avenues for personalized treatment approaches.