Logo image
Back
Utilizing Large Language Models to Predict ICD-10 Diagnosis Codes from Patient Medical Records
Conference proceeding

Utilizing Large Language Models to Predict ICD-10 Diagnosis Codes from Patient Medical Records

Rudransh Pathak, Gabriel Vald, Yusuf Sermet and Ibrahim Demir
2024 IEEE MIT Undergraduate Research Technology Conference (URTC), pp.1-5
10/11/2024
DOI: 10.1109/URTC65039.2024.10937521

View Online

Abstract

The application of Large Language Models (LLMs) has been a deeply explored topic, but with little focus on utilizing LLMs for predicting ICD-10 patient diagnoses in the medical field. Using LLMs to predict these patient codes has significant potential to streamline medical processes and reduce human burden drastically. In this work, we use GPT-4o to test four prompting techniques: Base GPT-4o, GPT-4o with Chain of Thought (CoT) prompting, GPT-4o with Retrieval-Augmented Generation (RAG), and GPT-4o with both CoT and RAG. Our results show that combining CoT and RAG significantly improve predictive accuracy of GPT-4o in patient diagnosis.
 Medical Diagnosis Accuracy Chain of Thought Prompting Codes Hallucination Large language models Medical diagnostic imaging Prompt engineering Reliability Retrieval augmented generation Training Transforms

Details

Metrics

40 Record Views
Logo image