{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308334882"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308334882","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Pacientų pasitraukimo iš gydymo įstaigos analizė taikant statistinius ir mašininio mokymosi metodus /","abstract":"This bachelor’s thesis analyzes the termination of patient enrollment at X polyclinic, treated as a patient churn problem. The aim of the thesis is to apply statistical and machine learning methods to evaluate factors associated with patients switching to other healthcare institutions and to assess the extent to which the available administrative and serviceuse data are suitable for predicting this process. The study uses anonymised data from the internal database and the State Patient Fund infor mation platform „SVEIDRA”. Two datasets were constructed, differing in the intervals of the feature and churn observation periods. Patient behaviour was described using demographic, administrative, appointmentrelated, serviceuse, branch, diagnosis, referral and medication history variables. The analysis applied binary logistic regression, elastic net regression, the SMOTE class imbalance reduc tion method, and Cox semiparametric regression. The results showed that predicting patient deregistration using only structured administrative and visit history data is difficult. The best AUC achieved by the logistic regression models was 0.6567. Class imbalance reduction methods did not substantially improve predictive quality. Therefore, the main value of the thesis lies not in individuallevel churn prediction but in the interpretation of factors associated with patient deregistration. Lower odds of deregistration were associated with longer patient loyalty, older age, higher expenditure, living in an urban area, more active use of services, and higher appointment conver sion. Higher odds of deregistration were associated with more frequent reregistration within the polyclinic, a higher number of referrals, a longer time since the last appointment registration, and certain diagnoses and branch groups.","abstract_html":"This bachelor’s thesis analyzes the termination of patient enrollment at X polyclinic, treated as a patient churn problem. The aim of the thesis is to apply statistical and machine learning methods to evaluate factors associated with patients switching to other healthcare institutions and to assess the extent to which the available administrative and serviceuse data are suitable for predicting this process. The study uses anonymised data from the internal database and the State Patient Fund infor mation platform „SVEIDRA”. Two datasets were constructed, differing in the intervals of the feature and churn observation periods. Patient behaviour was described using demographic, administrative, appointmentrelated, serviceuse, branch, diagnosis, referral and medication history variables. The analysis applied binary logistic regression, elastic net regression, the SMOTE class imbalance reduc tion method, and Cox semiparametric regression. The results showed that predicting patient deregistration using only structured administrative and visit history data is difficult. The best AUC achieved by the logistic regression models was 0.6567. Class imbalance reduction methods did not substantially improve predictive quality. Therefore, the main value of the thesis lies not in individuallevel churn prediction but in the interpretation of factors associated with patient deregistration. Lower odds of deregistration were associated with longer patient loyalty, older age, higher expenditure, living in an urban area, more active use of services, and higher appointment conver sion. Higher odds of deregistration were associated with more frequent reregistration within the polyclinic, a higher number of referrals, a longer time since the last appointment registration, and certain diagnoses and branch groups.","abstract_has_math":false,"creators":["Repečka, Ignas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:55Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308334882&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308334882&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308334882","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Repečka, Ignas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308334882/308334882.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308334882&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This bachelor’s thesis analyzes the termination of patient enrollment at X polyclinic, treated as a patient churn problem. The aim of the thesis is to apply statistical and machine learning methods to evaluate factors associated with patients switching to other healthcare institutions and to assess the extent to which the available administrative and serviceuse data are suitable for predicting this process. The study uses anonymised data from the internal database and the State Patient Fund infor mation platform „SVEIDRA”. Two datasets were constructed, differing in the intervals of the feature and churn observation periods. Patient behaviour was described using demographic, administrative, appointmentrelated, serviceuse, branch, diagnosis, referral and medication history variables. The analysis applied binary logistic regression, elastic net regression, the SMOTE class imbalance reduc tion method, and Cox semiparametric regression. The results showed that predicting patient deregistration using only structured administrative and visit history data is difficult. The best AUC achieved by the logistic regression models was 0.6567. Class imbalance reduction methods did not substantially improve predictive quality. Therefore, the main value of the thesis lies not in individuallevel churn prediction but in the interpretation of factors associated with patient deregistration. Lower odds of deregistration were associated with longer patient loyalty, older age, higher expenditure, living in an urban area, more active use of services, and higher appointment conver sion. Higher odds of deregistration were associated with more frequent reregistration within the polyclinic, a higher number of referrals, a longer time since the last appointment registration, and certain diagnoses and branch groups."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Pacientų pasitraukimo iš gydymo įstaigos analizė taikant statistinius ir mašininio mokymosi metodus /","Analysis of patient churn using statistical and machine learning methods."]}]}],"canonical_facts":{"dc:creator":["Repečka, Ignas,"],"dc:date":["2026"],"dc:description":["This bachelor’s thesis analyzes the termination of patient enrollment at X polyclinic, treated as a patient churn problem. The aim of the thesis is to apply statistical and machine learning methods to evaluate factors associated with patients switching to other healthcare institutions and to assess the extent to which the available administrative and serviceuse data are suitable for predicting this process. The study uses anonymised data from the internal database and the State Patient Fund infor mation platform „SVEIDRA”. Two datasets were constructed, differing in the intervals of the feature and churn observation periods. Patient behaviour was described using demographic, administrative, appointmentrelated, serviceuse, branch, diagnosis, referral and medication history variables. The analysis applied binary logistic regression, elastic net regression, the SMOTE class imbalance reduc tion method, and Cox semiparametric regression. The results showed that predicting patient deregistration using only structured administrative and visit history data is difficult. The best AUC achieved by the logistic regression models was 0.6567. Class imbalance reduction methods did not substantially improve predictive quality. Therefore, the main value of the thesis lies not in individuallevel churn prediction but in the interpretation of factors associated with patient deregistration. Lower odds of deregistration were associated with longer patient loyalty, older age, higher expenditure, living in an urban area, more active use of services, and higher appointment conver sion. Higher odds of deregistration were associated with more frequent reregistration within the polyclinic, a higher number of referrals, a longer time since the last appointment registration, and certain diagnoses and branch groups."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308334882&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308334882/308334882.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Pacientų pasitraukimo iš gydymo įstaigos analizė taikant statistinius ir mašininio mokymosi metodus /","Analysis of patient churn using statistical and machine learning methods."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:55Z"}