{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/30425140"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/30425140","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Temporal Reasoning in Clinical Narratives: From Information Extraction to Early Disease Detection","abstract":"Timely and accurate prediction of chronic disease risk, such as Type 2 Diabetes, requires models that can reason over complex, longitudinal clinical narratives. This thesis presents a unified framework for temporally grounded patient modeling that integrates structured event representations, fine-grained temporal reasoning, and scalable predictive architectures. Initial experiments show that concept-based models paired with visit-level temporal modeling outperform traditional baselines that ignore temporal dynamics, motivating a deeper exploration into concept and temporal relation extraction from clinical narratives. Towards this, I introduce GraphTREx, a state-of-the-art temporal relation extraction approach that achieves a 5% F1 improvement on the end-to-end temporal relation extraction task in the I2B2 2012 challenge with ~9% gains on long-distance relations. GraphTREx generalizes well, showing strong performance on the E3C corpus and robust out-of-domain results (without additional adaptation) on a newly annotated UI Health dataset with dense temporal relations, highlighting its portability. Building on these temporal graphs, I develop HiTGNN—a Hierarchical Temporal Graph Neural Network that integrates intra-document temporal relations, inter-visit dynamics, and external medical knowledge, enabling reasoning across both local event structures and longitudinal patient trajectories. I also introduce ReVeAL (Reasoning with Verifier Aided Labeling), an inference-time scaling framework where a smaller LLM validates predictions from a larger frozen LLM, inheriting interpretability and improving accuracy without full retraining. While our LLM-based approach offers explanations, HiTGNN outperforms it (and other LLM baselines) in accuracy and efficiency, especially over shorter prediction horizons, demonstrating the strength of lightweight, temporally grounded graph-based models, well-suited for low-resource, privacy-sensitive clinical settings. Rigorous dataset curation, ablations, and analyses reinforce robustness of these approaches. Together, these contributions establish a generalizable framework for clinical prediction by integrating concept abstraction, temporal structure, and semantic enrichment to support robust, privacy-conscious AI systems for real-world clinical decision support.","abstract_html":"Timely and accurate prediction of chronic disease risk, such as Type 2 Diabetes, requires models that can reason over complex, longitudinal clinical narratives. This thesis presents a unified framework for temporally grounded patient modeling that integrates structured event representations, fine-grained temporal reasoning, and scalable predictive architectures. Initial experiments show that concept-based models paired with visit-level temporal modeling outperform traditional baselines that ignore temporal dynamics, motivating a deeper exploration into concept and temporal relation extraction from clinical narratives. Towards this, I introduce GraphTREx, a state-of-the-art temporal relation extraction approach that achieves a 5% F1 improvement on the end-to-end temporal relation extraction task in the I2B2 2012 challenge with ~9% gains on long-distance relations. GraphTREx generalizes well, showing strong performance on the E3C corpus and robust out-of-domain results (without additional adaptation) on a newly annotated UI Health dataset with dense temporal relations, highlighting its portability. Building on these temporal graphs, I develop HiTGNN—a Hierarchical Temporal Graph Neural Network that integrates intra-document temporal relations, inter-visit dynamics, and external medical knowledge, enabling reasoning across both local event structures and longitudinal patient trajectories. I also introduce ReVeAL (Reasoning with Verifier Aided Labeling), an inference-time scaling framework where a smaller LLM validates predictions from a larger frozen LLM, inheriting interpretability and improving accuracy without full retraining. While our LLM-based approach offers explanations, HiTGNN outperforms it (and other LLM baselines) in accuracy and efficiency, especially over shorter prediction horizons, demonstrating the strength of lightweight, temporally grounded graph-based models, well-suited for low-resource, privacy-sensitive clinical settings. Rigorous dataset curation, ablations, and analyses reinforce robustness of these approaches. Together, these contributions establish a generalizable framework for clinical prediction by integrating concept abstraction, temporal structure, and semantic enrichment to support robust, privacy-conscious AI systems for real-world clinical decision support.","abstract_has_math":false,"creators":["Rochana Chaturvedi (19781646)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-08-01T00:00:00Z","date_published":"2025-08-01T00:00:00Z","updated_at":"2026-07-27T21:34:47Z","subjects":["Computer Science","Artificial Intelligence","Health Informatics"],"languages":[],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.30425140.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Rochana Chaturvedi (19781646)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-08-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Temporal_Reasoning_in_Clinical_Narratives_From_Information_Extraction_to_Early_Disease_Detection/30425140"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Science","Artificial Intelligence","Health Informatics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.30425140.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Timely and accurate prediction of chronic disease risk, such as Type 2 Diabetes, requires models that can reason over complex, longitudinal clinical narratives. This thesis presents a unified framework for temporally grounded patient modeling that integrates structured event representations, fine-grained temporal reasoning, and scalable predictive architectures. Initial experiments show that concept-based models paired with visit-level temporal modeling outperform traditional baselines that ignore temporal dynamics, motivating a deeper exploration into concept and temporal relation extraction from clinical narratives. Towards this, I introduce GraphTREx, a state-of-the-art temporal relation extraction approach that achieves a 5% F1 improvement on the end-to-end temporal relation extraction task in the I2B2 2012 challenge with ~9% gains on long-distance relations. GraphTREx generalizes well, showing strong performance on the E3C corpus and robust out-of-domain results (without additional adaptation) on a newly annotated UI Health dataset with dense temporal relations, highlighting its portability. Building on these temporal graphs, I develop HiTGNN—a Hierarchical Temporal Graph Neural Network that integrates intra-document temporal relations, inter-visit dynamics, and external medical knowledge, enabling reasoning across both local event structures and longitudinal patient trajectories. I also introduce ReVeAL (Reasoning with Verifier Aided Labeling), an inference-time scaling framework where a smaller LLM validates predictions from a larger frozen LLM, inheriting interpretability and improving accuracy without full retraining. While our LLM-based approach offers explanations, HiTGNN outperforms it (and other LLM baselines) in accuracy and efficiency, especially over shorter prediction horizons, demonstrating the strength of lightweight, temporally grounded graph-based models, well-suited for low-resource, privacy-sensitive clinical settings. Rigorous dataset curation, ablations, and analyses reinforce robustness of these approaches. Together, these contributions establish a generalizable framework for clinical prediction by integrating concept abstraction, temporal structure, and semantic enrichment to support robust, privacy-conscious AI systems for real-world clinical decision support."]},{"key":"dc:title","label":"Title","values":["Temporal Reasoning in Clinical Narratives: From Information Extraction to Early Disease Detection"]}]}],"canonical_facts":{"dc:creator":["Rochana Chaturvedi (19781646)"],"dc:date":["2025-08-01T00:00:00Z"],"dc:description":["Timely and accurate prediction of chronic disease risk, such as Type 2 Diabetes, requires models that can reason over complex, longitudinal clinical narratives. This thesis presents a unified framework for temporally grounded patient modeling that integrates structured event representations, fine-grained temporal reasoning, and scalable predictive architectures. Initial experiments show that concept-based models paired with visit-level temporal modeling outperform traditional baselines that ignore temporal dynamics, motivating a deeper exploration into concept and temporal relation extraction from clinical narratives. Towards this, I introduce GraphTREx, a state-of-the-art temporal relation extraction approach that achieves a 5% F1 improvement on the end-to-end temporal relation extraction task in the I2B2 2012 challenge with ~9% gains on long-distance relations. GraphTREx generalizes well, showing strong performance on the E3C corpus and robust out-of-domain results (without additional adaptation) on a newly annotated UI Health dataset with dense temporal relations, highlighting its portability. Building on these temporal graphs, I develop HiTGNN—a Hierarchical Temporal Graph Neural Network that integrates intra-document temporal relations, inter-visit dynamics, and external medical knowledge, enabling reasoning across both local event structures and longitudinal patient trajectories. I also introduce ReVeAL (Reasoning with Verifier Aided Labeling), an inference-time scaling framework where a smaller LLM validates predictions from a larger frozen LLM, inheriting interpretability and improving accuracy without full retraining. While our LLM-based approach offers explanations, HiTGNN outperforms it (and other LLM baselines) in accuracy and efficiency, especially over shorter prediction horizons, demonstrating the strength of lightweight, temporally grounded graph-based models, well-suited for low-resource, privacy-sensitive clinical settings. Rigorous dataset curation, ablations, and analyses reinforce robustness of these approaches. Together, these contributions establish a generalizable framework for clinical prediction by integrating concept abstraction, temporal structure, and semantic enrichment to support robust, privacy-conscious AI systems for real-world clinical decision support."],"dc:identifier":["10.25417/uic.30425140.v1"],"dc:relation":["https://figshare.com/articles/thesis/Temporal_Reasoning_in_Clinical_Narratives_From_Information_Extraction_to_Early_Disease_Detection/30425140"],"dc:rights":["In Copyright"],"dc:subject":["Computer Science","Artificial Intelligence","Health Informatics"],"dc:title":["Temporal Reasoning in Clinical Narratives: From Information Extraction to Early Disease Detection"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:34:47Z"}