{"id":{"repo_id":"odu","oai_identifier":"oai:digitalcommons.odu.edu:computerscience_etds-1193"},"canonical_url":"https://search.ndltd.org/etd/odu/oai:digitalcommons.odu.edu:computerscience_etds-1193","repository":{"repo_id":"odu","name":"Old Dominion University","base_url":"https://digitalcommons.odu.edu/do/oai/"},"display":{"title":"Large Language Models (LLMS) for Clinical Note Generation: International Classification of Disease (ICD) Code, Knowledge Graph (KG) and Prompt Evaluation","abstract":"In the past decade, a surge in the amount of electronic health record (EHR) data in the United States occurred, driven by a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients’ assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering them. Manually writing these notes is time-consuming, increasing patient waiting times and potentially delaying diagnoses. Large language models (LLMs), such as GPT-4o, possess the ability to generate news articles that closely resemble human-written ones. In this work, we present several Chain-of-Thought (CoT) prompt engineering strategies that improve the LLM’s response in clinical note generation. In our prompts, we incorporate International Classification of Diseases (ICD) codes and basic patient information along with similar clinical case examples which effectively enhance the LLMs to formulate clinical notes. We evaluated our CoT prompt strategies on six clinical cases from the CodiEsp test dataset against several LLMs and our results show that it outperformed the standard one-shot prompt.","abstract_html":"In the past decade, a surge in the amount of electronic health record (EHR) data in the United States occurred, driven by a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients’ assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering them. Manually writing these notes is time-consuming, increasing patient waiting times and potentially delaying diagnoses. Large language models (LLMs), such as GPT-4o, possess the ability to generate news articles that closely resemble human-written ones. In this work, we present several Chain-of-Thought (CoT) prompt engineering strategies that improve the LLM’s response in clinical note generation. In our prompts, we incorporate International Classification of Diseases (ICD) codes and basic patient information along with similar clinical case examples which effectively enhance the LLMs to formulate clinical notes. We evaluated our CoT prompt strategies on six clinical cases from the CodiEsp test dataset against several LLMs and our results show that it outperformed the standard one-shot prompt.","abstract_has_math":false,"creators":["Makohon, Ivan P."],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Yaohang Li","Vikas G. Ashok","Michele C. Weigle","Jian Wu","David S. Courson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:34:08Z","subjects":["Chain-of-Though (CoT)","Clinical note generation","Generative AI","Information retrieval","Large language models","Natural language processing","Artificial Intelligence and Robotics","Bioinformatics","Computer Sciences"],"languages":[],"rights":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["9798276040196"],"render_values":[{"text":"9798276040196","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.odu.edu/computerscience_etds/197","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.odu.edu/computerscience_etds/197","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.odu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.odu.edu%3Acomputerscience_etds-1193","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Yaohang Li","Vikas G. Ashok","Michele C. Weigle","Jian Wu","David S. Courson"]},{"key":"dc:creator","label":"Author","values":["Makohon, Ivan P."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-02-17T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Chain-of-Though (CoT)","Clinical note generation","Generative AI","Information retrieval","Large language models","Natural language processing","Artificial Intelligence and Robotics","Bioinformatics","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["9798276040196","https://digitalcommons.odu.edu/computerscience_etds/197"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In the past decade, a surge in the amount of electronic health record (EHR) data in the United States occurred, driven by a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients’ assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering them. Manually writing these notes is time-consuming, increasing patient waiting times and potentially delaying diagnoses. Large language models (LLMs), such as GPT-4o, possess the ability to generate news articles that closely resemble human-written ones. In this work, we present several Chain-of-Thought (CoT) prompt engineering strategies that improve the LLM’s response in clinical note generation. In our prompts, we incorporate International Classification of Diseases (ICD) codes and basic patient information along with similar clinical case examples which effectively enhance the LLMs to formulate clinical notes. We evaluated our CoT prompt strategies on six clinical cases from the CodiEsp test dataset against several LLMs and our results show that it outperformed the standard one-shot prompt."]},{"key":"dc:title","label":"Title","values":["Large Language Models (LLMS) for Clinical Note Generation: International Classification of Disease (ICD) Code, Knowledge Graph (KG) and Prompt Evaluation"]}]}],"canonical_facts":{"dc:contributor":["Yaohang Li","Vikas G. Ashok","Michele C. Weigle","Jian Wu","David S. Courson"],"dc:creator":["Makohon, Ivan P."],"dc:date.available":["2026-02-17T08:00:00Z"],"dc:date.created":["2025-12-01T08:00:00Z"],"dc:description.abstract":["In the past decade, a surge in the amount of electronic health record (EHR) data in the United States occurred, driven by a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients’ assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering them. Manually writing these notes is time-consuming, increasing patient waiting times and potentially delaying diagnoses. Large language models (LLMs), such as GPT-4o, possess the ability to generate news articles that closely resemble human-written ones. In this work, we present several Chain-of-Thought (CoT) prompt engineering strategies that improve the LLM’s response in clinical note generation. In our prompts, we incorporate International Classification of Diseases (ICD) codes and basic patient information along with similar clinical case examples which effectively enhance the LLMs to formulate clinical notes. We evaluated our CoT prompt strategies on six clinical cases from the CodiEsp test dataset against several LLMs and our results show that it outperformed the standard one-shot prompt."],"dc:identifier":["9798276040196","https://digitalcommons.odu.edu/computerscience_etds/197"],"dc:rights":["<p>In Copyright. URI: <a href=\"http://rightsstatements.org/vocab/InC/1.0/\">http://rightsstatements.org/vocab/InC/1.0/</a> This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).</p>"],"dc:subject":["Chain-of-Though (CoT)","Clinical note generation","Generative AI","Information retrieval","Large language models","Natural language processing","Artificial Intelligence and Robotics","Bioinformatics","Computer Sciences"],"dc:title":["Large Language Models (LLMS) for Clinical Note Generation: International Classification of Disease (ICD) Code, Knowledge Graph (KG) and Prompt Evaluation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-11-19T08:34:08Z"}