Beyond Negation Detection: Comprehensive Assertion Detection Models for Clinical NLP
This work addresses a critical gap in clinical NLP for healthcare applications by providing domain-adapted models that improve accuracy over existing commercial tools, though it is incremental as it builds on existing methods like fine-tuning and deep learning.
The paper tackled the problem of assertion status detection in clinical NLP, which is crucial for accurately attributing medical facts, by developing state-of-the-art models that outperform commercial solutions like GPT-4o and cloud APIs, with a fine-tuned LLM achieving the highest overall accuracy of 0.962 and notable gains in specific assertion categories such as Hypothetical (+23.4%).
Assertion status detection is a critical yet often overlooked component of clinical NLP, essential for accurately attributing extracted medical facts. Past studies have narrowly focused on negation detection, leading to underperforming commercial solutions such as AWS Medical Comprehend, Azure AI Text Analytics, and GPT-4o due to their limited domain adaptation. To address this gap, we developed state-of-the-art assertion detection models, including fine-tuned LLMs, transformer-based classifiers, few-shot classifiers, and deep learning (DL) approaches. We evaluated these models against cloud-based commercial API solutions, the legacy rule-based NegEx approach, and GPT-4o. Our fine-tuned LLM achieves the highest overall accuracy (0.962), outperforming GPT-4o (0.901) and commercial APIs by a notable margin, particularly excelling in Present (+4.2%), Absent (+8.4%), and Hypothetical (+23.4%) assertions. Our DL-based models surpass commercial solutions in Conditional (+5.3%) and Associated-with-Someone-Else (+10.1%) categories, while the few-shot classifier offers a lightweight yet highly competitive alternative (0.929), making it ideal for resource-constrained environments. Integrated within Spark NLP, our models consistently outperform black-box commercial solutions while enabling scalable inference and seamless integration with medical NER, Relation Extraction, and Terminology Resolution. These results reinforce the importance of domain-adapted, transparent, and customizable clinical NLP solutions over general-purpose LLMs and proprietary APIs.