MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering

TL;DR

MedPromptExtract is an automated tool that combines NLP, prompt engineering, and LLMs to efficiently anonymize and extract high-fidelity clinical data from discharge summaries, aiding medical record digitization especially in resource-limited settings.

Contribution

The paper introduces MedPromptExtract, a novel integrated system that automates anonymization and data extraction from medical records using advanced NLP and prompt engineering techniques.

Findings

Anonymization pipeline takes 3 seconds per summary with successful clinician verification.

NLP extraction achieves 100% accuracy at 0.2 seconds per summary.

High fidelity in extracting AKI-related features with AUCs above 0.9.

Abstract

Introduction: The labour-intensive nature of data extraction from sources like discharge summaries (DS) poses significant obstacles to the digitisation of medical records particularly for low- and middle-income countries (LMICs). In this paper we present a completely automated method MedPromptExtract to efficiently extract data from DS while maintaining confidentiality. Methods: The source of data was Discharge Summaries (DS) from Kokilaben Dhirubhai Ambani Hospital (KDAH) of patients having Acute Kidney Injury (AKI). A pre-existing tool EIGEN which leverages semi-supervised learning techniques for high-fidelity information extraction was used to anonymize the DS, Natural Language Processing (NLP) was used to extract data from regular fields. We used Prompt Engineering and Large Language Model(LLM) to extract custom clinical information from free flowing text describing the patients stay in the hospital. Twelve features associated with occurrence of AKI were extracted. The LLM responses were validated against clinicians annotations. Results: The MedPromptExtracttool first subjected DS to the anonymization pipeline which took three seconds per summary. Successful anonymization was verified by clinicians, thereafter NLP pipeline extracted structured text from the anonymized pdfs at the rate of 0.2 seconds per summary with 100% accuracy.Finally DS were analysed by the LLM pipeline using Gemini Pro for the twelve features. Accuracy metrics were calculated by comparing model responses to clinicians annotations with seven features achieving AUCs above 0.9, indicating high fidelity of the extraction process. Conclusion: MedPromptExtract serves as an automated adaptable tool for efficient data extraction from medical records with a dynamic user interface. Keywords: Digitizing Medical Records, Automated Anonymisation, Information Retrieval, Large Language Models, Prompt Engineering