Enhancing Clinical Note Generation with ICD-10, Clinical Ontology Knowledge Graphs, and Chain-of-Thought Prompting Using GPT-4

TL;DR

This paper enhances clinical note generation by integrating ICD-10 codes, clinical ontology knowledge graphs, and chain-of-thought prompting with GPT-4, leading to more accurate and domain-specific medical documentation.

Contribution

It introduces a novel prompting strategy combining chain-of-thought, semantic search, and knowledge graphs to improve LLM-generated clinical notes.

Findings

Outperforms standard prompts in clinical note quality

Effective integration of ICD-10 and ontology knowledge graphs

Improved relevance and accuracy of generated notes

Abstract

In the past decade a surge in the amount of electronic health record (EHR) data in the United States, attributed to 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 and editing them. Manually writing clinical notes takes a considerable amount of a doctor's valuable time, increasing the patient's waiting time and possibly delaying diagnoses. Large language models (LLMs) possess the ability to generate news articles that closely resemble human-written ones. We investigate the usage of Chain-of-Thought (CoT) prompt engineering to improve the LLM's response in clinical note generation. In our prompts, we use as input International Classification of Diseases (ICD) codes and basic patient information. We investigate a strategy that combines the traditional CoT with semantic search results to improve the quality of generated clinical notes. Additionally, we infuse a knowledge graph (KG) built from clinical ontology to further enrich the domain-specific knowledge of generated clinical notes. We test our prompting technique on six clinical cases from the CodiEsp test dataset using GPT-4 and our results show that it outperformed the clinical notes generated by standard one-shot prompts.