2026-09-20T00:28:40Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1626942025-09-19T04:49:05Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Raskar, Ramesh Gregory, Cale Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2025-09-18T14:27:42Z 2025-09-18T14:27:42Z 2025-05 2025-06-23T14:02:02.542Z https://hdl.handle.net/1721.1/162694 This thesis evaluates the validity of current dynamic treatment regime algorithms and presents a novel data structure for extracting treatment decisions from unstructured clinical notes. The main contribution is the Clinical Decision Tree (CDT) which uses large language models (LLMs) to extract key decisions in chronic disease treatment. This addresses the main pain points in dynamic treatment regimes of low interpretability and reliance on poorly collected data for traditional machine learning methods. This work contains extensive experiments on mortality prediction, time series forecasting, and synthetic patient modeling. Experiments show that vital-based representations do not capture enough meaningful data about a patient to accurately predict and evaluate new treatment methods. By utilizing latent embeddings and vector search, experiments show that the collected vitals of patients fail to differentiate the outcomes of the related patients. Conversely, the clinical notes contain complex and substantial information about clinical decision making. LLMs enable the valuable knowledge extraction from unstructured data. Utilizing LLMs, experimental results and expert evaluation indicates that CDTs can extract and distill interpretable treatment decisions. Thus, CDTs are a valuable tool that can be refined to increase confidence in treatment decisions and identifying rare and uncommon medical practices. M.Eng. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ On Dynamic Treatment Regimes: Collaborative Search and LLM-Driven Decision Trees Thesis application/pdf Master Master of Engineering in Electrical Engineering and Computer Science Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="c305549e-631a-447a-8755-5a9adbecba0d"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>On Dynamic Treatment Regimes: Collaborative Search and LLM-Driven Decision Trees</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2025-05</PublicationDate> <Authors> <Author> <DisplayName>Gregory, Cale</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>This thesis evaluates the validity of current dynamic treatment regime algorithms and presents a novel data structure for extracting treatment decisions from unstructured clinical notes. The main contribution is the Clinical Decision Tree (CDT) which uses large language models (LLMs) to extract key decisions in chronic disease treatment. This addresses the main pain points in dynamic treatment regimes of low interpretability and reliance on poorly collected data for traditional machine learning methods. This work contains extensive experiments on mortality prediction, time series forecasting, and synthetic patient modeling. Experiments show that vital-based representations do not capture enough meaningful data about a patient to accurately predict and evaluate new treatment methods. By utilizing latent embeddings and vector search, experiments show that the collected vitals of patients fail to differentiate the outcomes of the related patients. Conversely, the clinical notes contain complex and substantial information about clinical decision making. LLMs enable the valuable knowledge extraction from unstructured data. Utilizing LLMs, experimental results and expert evaluation indicates that CDTs can extract and distill interpretable treatment decisions. Thus, CDTs are a valuable tool that can be refined to increase confidence in treatment decisions and identifying rare and uncommon medical practices.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>