{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/164664"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/164664","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"CONDOR: Clinical Ontology-aware Networked Data Organization and Retrieval","abstract":"Until now, state-of-the-art research into AI-driven clinical workflows has been confined to proprietary, closed-source systems from vendors like Epic and Oracle, or private experiments like Stanford’s ChatEHR, creating a critical barrier to academic innovation. This thesis introduces CONDOR, the first fully open-source and replicable research environment designed to simulate an agentic, conversational AI interacting with a high-fidelity Electronic Health Record (EHR). By integrating an open-source, FHIR-native EHR (Medplum) with a complex, realistic public clinical dataset (MIMIC-IV FHIR), CONDOR provides a foundational testbed that has been previously unavailable to the research community. The framework’s primary contribution is a novel alignment and evaluation methodology that adapts the principles of SelfCite to the clinical domain. We propose a ‘ClinicalConfidence‘ score to quantify the trustworthiness of generated statements and programmatically generate a high-quality preference dataset for alignment using Simple Preference Optimization (SimPO). We compare a standard vector-based Retrieval-Augmented Generation (RAG) baseline against a more advanced GraphRAG architecture that leverages a two-tiered knowledge graph of patient data and medical ontologies. Our results demonstrate that the full CONDOR system, combining GraphRAG with SimPO alignment, significantly improves citation quality and verifiability, establishing a new open-source benchmark for the development of safe and reliable clinical AI.","abstract_html":"Until now, state-of-the-art research into AI-driven clinical workflows has been confined to proprietary, closed-source systems from vendors like Epic and Oracle, or private experiments like Stanford’s ChatEHR, creating a critical barrier to academic innovation. This thesis introduces CONDOR, the first fully open-source and replicable research environment designed to simulate an agentic, conversational AI interacting with a high-fidelity Electronic Health Record (EHR). By integrating an open-source, FHIR-native EHR (Medplum) with a complex, realistic public clinical dataset (MIMIC-IV FHIR), CONDOR provides a foundational testbed that has been previously unavailable to the research community. The framework’s primary contribution is a novel alignment and evaluation methodology that adapts the principles of SelfCite to the clinical domain. We propose a ‘ClinicalConfidence‘ score to quantify the trustworthiness of generated statements and programmatically generate a high-quality preference dataset for alignment using Simple Preference Optimization (SimPO). We compare a standard vector-based Retrieval-Augmented Generation (RAG) baseline against a more advanced GraphRAG architecture that leverages a two-tiered knowledge graph of patient data and medical ontologies. Our results demonstrate that the full CONDOR system, combining GraphRAG with SimPO alignment, significantly improves citation quality and verifiability, establishing a new open-source benchmark for the development of safe and reliable clinical AI.","abstract_has_math":false,"creators":["Dongo Aguirre, Gyalpo Melchisedeck"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Madden, Samuel"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-09","date_published":"2025-09","updated_at":"2026-07-22T22:21:50Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/164664","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Madden, Samuel"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Dongo Aguirre, Gyalpo Melchisedeck"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-29T15:06:43Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-29T15:06:43Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-09"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/164664"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Until now, state-of-the-art research into AI-driven clinical workflows has been confined to proprietary, closed-source systems from vendors like Epic and Oracle, or private experiments like Stanford’s ChatEHR, creating a critical barrier to academic innovation. This thesis introduces CONDOR, the first fully open-source and replicable research environment designed to simulate an agentic, conversational AI interacting with a high-fidelity Electronic Health Record (EHR). By integrating an open-source, FHIR-native EHR (Medplum) with a complex, realistic public clinical dataset (MIMIC-IV FHIR), CONDOR provides a foundational testbed that has been previously unavailable to the research community. The framework’s primary contribution is a novel alignment and evaluation methodology that adapts the principles of SelfCite to the clinical domain. We propose a ‘ClinicalConfidence‘ score to quantify the trustworthiness of generated statements and programmatically generate a high-quality preference dataset for alignment using Simple Preference Optimization (SimPO). We compare a standard vector-based Retrieval-Augmented Generation (RAG) baseline against a more advanced GraphRAG architecture that leverages a two-tiered knowledge graph of patient data and medical ontologies. Our results demonstrate that the full CONDOR system, combining GraphRAG with SimPO alignment, significantly improves citation quality and verifiability, establishing a new open-source benchmark for the development of safe and reliable clinical AI."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["CONDOR: Clinical Ontology-aware Networked Data Organization and Retrieval"]}]}],"canonical_facts":{"dc:contributor.advisor":["Madden, Samuel"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Dongo Aguirre, Gyalpo Melchisedeck"],"dc:date.accessioned":["2026-01-29T15:06:43Z"],"dc:date.available":["2026-01-29T15:06:43Z"],"dc:date.issued":["2025-09"],"dc:description.abstract":["Until now, state-of-the-art research into AI-driven clinical workflows has been confined to proprietary, closed-source systems from vendors like Epic and Oracle, or private experiments like Stanford’s ChatEHR, creating a critical barrier to academic innovation. This thesis introduces CONDOR, the first fully open-source and replicable research environment designed to simulate an agentic, conversational AI interacting with a high-fidelity Electronic Health Record (EHR). By integrating an open-source, FHIR-native EHR (Medplum) with a complex, realistic public clinical dataset (MIMIC-IV FHIR), CONDOR provides a foundational testbed that has been previously unavailable to the research community. The framework’s primary contribution is a novel alignment and evaluation methodology that adapts the principles of SelfCite to the clinical domain. We propose a ‘ClinicalConfidence‘ score to quantify the trustworthiness of generated statements and programmatically generate a high-quality preference dataset for alignment using Simple Preference Optimization (SimPO). We compare a standard vector-based Retrieval-Augmented Generation (RAG) baseline against a more advanced GraphRAG architecture that leverages a two-tiered knowledge graph of patient data and medical ontologies. Our results demonstrate that the full CONDOR system, combining GraphRAG with SimPO alignment, significantly improves citation quality and verifiability, establishing a new open-source benchmark for the development of safe and reliable clinical AI."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/164664"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["CONDOR: Clinical Ontology-aware Networked Data Organization and Retrieval"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:50Z"}