Saved in:
Bibliographic Details
Main Authors: Kocaman, Veysel, Santas, Muhammed, Gul, Yigit, Butgul, Mehmet, Talby, David
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.20794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908292344709120
author Kocaman, Veysel
Santas, Muhammed
Gul, Yigit
Butgul, Mehmet
Talby, David
author_facet Kocaman, Veysel
Santas, Muhammed
Gul, Yigit
Butgul, Mehmet
Talby, David
contents We evaluate the performance of four leading solutions for de-identification of unstructured medical text - Azure Health Data Services, AWS Comprehend Medical, OpenAI GPT-4o, and John Snow Labs - on a ground truth dataset of 48 clinical documents annotated by medical experts. The analysis, conducted at both entity-level and token-level, suggests that John Snow Labs' Medical Language Models solution achieves the highest accuracy, with a 96% F1-score in protected health information (PHI) detection, outperforming Azure (91%), AWS (83%), and GPT-4o (79%). John Snow Labs is not only the only solution which achieves regulatory-grade accuracy (surpassing that of human experts) but is also the most cost-effective solution: It is over 80% cheaper compared to Azure and GPT-4o, and is the only solution not priced by token. Its fixed-cost local deployment model avoids the escalating per-request fees of cloud-based services, making it a scalable and economical choice.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Zero-Shot Commercial APIs Deliver Regulatory-Grade Clinical Text DeIdentification?
Kocaman, Veysel
Santas, Muhammed
Gul, Yigit
Butgul, Mehmet
Talby, David
Computation and Language
Cryptography and Security
Information Retrieval
Machine Learning
H.3; F.2.2; I.2.7
We evaluate the performance of four leading solutions for de-identification of unstructured medical text - Azure Health Data Services, AWS Comprehend Medical, OpenAI GPT-4o, and John Snow Labs - on a ground truth dataset of 48 clinical documents annotated by medical experts. The analysis, conducted at both entity-level and token-level, suggests that John Snow Labs' Medical Language Models solution achieves the highest accuracy, with a 96% F1-score in protected health information (PHI) detection, outperforming Azure (91%), AWS (83%), and GPT-4o (79%). John Snow Labs is not only the only solution which achieves regulatory-grade accuracy (surpassing that of human experts) but is also the most cost-effective solution: It is over 80% cheaper compared to Azure and GPT-4o, and is the only solution not priced by token. Its fixed-cost local deployment model avoids the escalating per-request fees of cloud-based services, making it a scalable and economical choice.
title Can Zero-Shot Commercial APIs Deliver Regulatory-Grade Clinical Text DeIdentification?
topic Computation and Language
Cryptography and Security
Information Retrieval
Machine Learning
H.3; F.2.2; I.2.7
url https://arxiv.org/abs/2503.20794