MedPromptExtract (Medical Data Extraction Tool): Anonymization and High-Fidelity Automated Data Extraction Using Natural Language Processing and Prompt Engineering
The Journal of Applied Laboratory Medicine · 2025
DOI: 10.1093/jalm/jfaf034 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Applied Laboratory Medicine, 2025. Verfasst von Roomani Srivastava und 5 weiteren Autor:innen. Beteiligte Einrichtung: Koita Centre for Digital Health, Indian Institute of Technology, Bombay, Mumbai, Maharashtra, India. Hauptthemen laut MEDLINE: Natural Language Processing, Electronic Health Records, Acute Kidney Injury, Data Anonymization. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: Koita Foundation.
Abstract (Originalsprache)
Background
The labor-intensive nature of data extraction from sources like discharge summaries (DSs) poses significant obstacles to the digitization 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 were DSs from Kokilaben Dhirubhai Ambani Hospital (KDAH) of patients having acute kidney injury (AKI). A pre-existing tool, Expert-Informed Joint Learning aGgrEatioN (EIGEN), which leverages semi-supervised learning techniques for high-fidelity information extraction, was used to anonymize the DSs, and natural language processing (NLP) was used to extract data from regular fields. We used prompt engineering and a large language model (LLM) to extract custom clinical information from free-flowing text describing the patient’s stay in the hospital. Twelve features associated with the occurrence of AKI were extracted. The LLM’s responses were validated against clinicians’ annotations.
Results
The MedPromptExtract tool first subjected DSs to the anonymization pipeline, which took 3 seconds per summary. Successful anonymization was verified by clinicians, thereafter the NLP pipeline extracted structured text from the anonymized pdfs at the rate of 0.2 s per summary with 100% accuracy. Finally, DSs were analysed by the LLM pipeline using Gemini Pro for the 12 features. Accuracy metrics were calculated by comparing model responses to clinicians’ annotations with 7 features achieving Area Under the Curve (AUC) above 0.9, indicating the high fidelity of the extraction process.
Conclusions
MedPromptExtract serves as an automated adaptable tool for efficient data extraction from medical records with a dynamic user interface.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Koita Centre for Digital Health, Indian Institute of Technology, Bombay, Mumbai, Maharashtra, India.
- Sardar Patel Institute of Technology, Mumbai, Maharashtra, India.
- Laboratory Medicine, Kokilaben Dhirubhai Ambani Hospital and Medical Research Institute, Mumbai, Maharashtra, India.
Förderung
- Koita Foundation
Zitieren
APA
Srivastava, R., Bhat, L., Prasad, S., Deshpande, S., Das, B., & Jadhav, K. (2025). MedPromptExtract (Medical Data Extraction Tool): Anonymization and High-Fidelity Automated Data Extraction Using Natural Language Processing and Prompt Engineering. The Journal of Applied Laboratory Medicine. https://doi.org/10.1093/jalm/jfaf034
Vancouver
Srivastava R, Bhat L, Prasad S, Deshpande S, Das B, Jadhav K. MedPromptExtract (Medical Data Extraction Tool): Anonymization and High-Fidelity Automated Data Extraction Using Natural Language Processing and Prompt Engineering. The Journal of Applied Laboratory Medicine. 2025. doi:10.1093/jalm/jfaf034
BibTeX
@article{Srivastava2025,
author = {Srivastava, Roomani and Bhat, Lipika and Prasad, Suraj and Deshpande, Sarvesh and Das, Barnali and Jadhav, Kshitij},
title = {MedPromptExtract (Medical Data Extraction Tool): Anonymization and High-Fidelity Automated Data Extraction Using Natural Language Processing and Prompt Engineering},
journal = {The Journal of Applied Laboratory Medicine},
year = {2025},
doi = {10.1093/jalm/jfaf034}
}
EUVIMED