Date of Award

Fall 12-2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Computer Science

Program/Concentration

Computer Science

Committee Director

Yaohang Li

Committee Member

Vikas G. Ashok

Committee Member

Michele C. Weigle

Committee Member

Jian Wu

Committee Member

David S. Courson

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.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ 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).

DOI

10.25777/7vkp-y347

ORCID

0000-0002-3627-7242

Download

Share

COinS