{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/51175"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/51175","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Predicting psychological treatment dropout using graph neural networks","abstract":"Psychological treatment dropout remains a persistent challenge in mental healthcare, with significant effects for patient outcomes and healthcare resource utilization. This study proposes a framework for predicting treatment dropout using probabilistic Graph Neural Networks (GNNs) applied to data collected from the Wellness and Recovery After Psychosis (WRAP) program at Boston Medical Center. The approach extends the BernGraph [10] model by generalizing probabilistic node encoding to support both binary and continuous clinical variables, the latter transformed into probabilistic representations via z-score standardization and cumulative distribution functions. Edge weights between nodes are computed using conditional probabilities for binary pairs and Gaussian similarity for continuous variables, in order to capture nuanced interdependencies among clinical features. The study’s results show a substantial performance improvement across all models when using GNN-generated features compared to raw clinical inputs. This work presents a promising step towards more GNN applications in computational healthcare research.","abstract_html":"Psychological treatment dropout remains a persistent challenge in mental healthcare, with significant effects for patient outcomes and healthcare resource utilization. This study proposes a framework for predicting treatment dropout using probabilistic Graph Neural Networks (GNNs) applied to data collected from the Wellness and Recovery After Psychosis (WRAP) program at Boston Medical Center. The approach extends the BernGraph [10] model by generalizing probabilistic node encoding to support both binary and continuous clinical variables, the latter transformed into probabilistic representations via z-score standardization and cumulative distribution functions. Edge weights between nodes are computed using conditional probabilities for binary pairs and Gaussian similarity for continuous variables, in order to capture nuanced interdependencies among clinical features. The study’s results show a substantial performance improvement across all models when using GNN-generated features compared to raw clinical inputs. This work presents a promising step towards more GNN applications in computational healthcare research.","abstract_has_math":false,"creators":["Le, Khang"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Systems Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Venkataraman, Archana"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T20:16:41Z","subjects":["Bioinformatics"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0009-6751-6996"],"render_values":[{"text":"0009-0009-6751-6996","href":"https://orcid.org/0009-0009-6751-6996","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2144/51175","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/51175","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F51175","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Venkataraman, Archana"]},{"key":"dc:creator","label":"Author","values":["Le, Khang"]},{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0009-6751-6996"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-08T17:24:21Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-08T17:24:21Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2025-08-29T19:19:44Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Systems Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Bioinformatics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/51175"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["Psychological treatment dropout remains a persistent challenge in mental healthcare, with significant effects for patient outcomes and healthcare resource utilization. This study proposes a framework for predicting treatment dropout using probabilistic Graph Neural Networks (GNNs) applied to data collected from the Wellness and Recovery After Psychosis (WRAP) program at Boston Medical Center. The approach extends the BernGraph [10] model by generalizing probabilistic node encoding to support both binary and continuous clinical variables, the latter transformed into probabilistic representations via z-score standardization and cumulative distribution functions. Edge weights between nodes are computed using conditional probabilities for binary pairs and Gaussian similarity for continuous variables, in order to capture nuanced interdependencies among clinical features. The study’s results show a substantial performance improvement across all models when using GNN-generated features compared to raw clinical inputs. This work presents a promising step towards more GNN applications in computational healthcare research."]},{"key":"dc:title","label":"Title","values":["Predicting psychological treatment dropout using graph neural networks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Venkataraman, Archana"],"dc:creator":["Le, Khang"],"dc:date.accessioned":["2025-09-08T17:24:21Z"],"dc:date.available":["2025-09-08T17:24:21Z"],"dc:date.issued":["2025"],"dc:date.updated":["2025-08-29T19:19:44Z"],"dc:description":["2025"],"dc:description.abstract":["Psychological treatment dropout remains a persistent challenge in mental healthcare, with significant effects for patient outcomes and healthcare resource utilization. This study proposes a framework for predicting treatment dropout using probabilistic Graph Neural Networks (GNNs) applied to data collected from the Wellness and Recovery After Psychosis (WRAP) program at Boston Medical Center. The approach extends the BernGraph [10] model by generalizing probabilistic node encoding to support both binary and continuous clinical variables, the latter transformed into probabilistic representations via z-score standardization and cumulative distribution functions. Edge weights between nodes are computed using conditional probabilities for binary pairs and Gaussian similarity for continuous variables, in order to capture nuanced interdependencies among clinical features. The study’s results show a substantial performance improvement across all models when using GNN-generated features compared to raw clinical inputs. This work presents a promising step towards more GNN applications in computational healthcare research."],"dc:identifier.orcid":["0009-0009-6751-6996"],"dc:identifier.uri":["https://hdl.handle.net/2144/51175"],"dc:language.iso":["en_US"],"dc:subject":["Bioinformatics"],"dc:title":["Predicting psychological treatment dropout using graph neural networks"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Systems Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T20:16:41Z"}