# Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset

arXiv: https://arxiv.org/abs/2505.23030 · HTML: https://mlsanity.com/paper/2505.23030/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://mlsanity.com/paper/2211.12737/) (2022)
- [Automated Clinical Coding: What, Why, and Where We Are?](https://mlsanity.com/paper/2203.11092/) (2022)
- [CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output](https://mlsanity.com/paper/2006.15229/) (2020)
- [Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey](https://mlsanity.com/paper/2304.11461/) (2023)
- [Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings](https://mlsanity.com/paper/2311.01349/) (2023)

## Abstract (arXiv)

General-purpose clinical natural language processing (NLP) tools are increasingly used for the automatic labeling of clinical reports. However, independent evaluations for specific tasks, such as pediatric chest radiograph (CXR) report labeling, are limited. This study compares four commercial clinical NLP systems - Amazon Comprehend Medical (AWS), Google Healthcare NLP (GC), Azure Clinical NLP (AZ), and SparkNLP (SP) - for entity extraction and assertion detection in pediatric CXR reports. Additionally, CheXpert and CheXbert, two dedicated chest radiograph report labelers, were evaluated on the same task using CheXpert-defined labels. We analyzed 95,008 pediatric CXR reports from a large academic pediatric hospital. Entities and assertion statuses (positive, negative, uncertain) from the findings and impression sections were extracted by the NLP systems, with impression section entities mapped to 12 disease categories and a No Findings category. CheXpert and CheXbert extracted the same 13 categories. Outputs were compared using Fleiss Kappa and accuracy against a consensus pseudo-ground truth. Significant differences were found in the number of extracted entities and assertion distributions across NLP systems. SP extracted 49,688 unique entities, GC 16,477, AZ 31,543, and AWS 27,216. Assertion accuracy across models averaged around 62%, with SP highest (76%) and AWS lowest (50%). CheXpert and CheXbert achieved 56% accuracy. Considerable variability in performance highlights the need for careful validation and review before deploying NLP tools for clinical report labeling.