EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Clinical Text Mining for Treatment Response Extraction in Lung Cancer Notes

Aoi Ito, Bernard Darren

Journal of the Artificial Intelligence Engineers Consortium · 2026

DOI: 10.66238/jaiec57 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Artificial Intelligence Engineers Consortium, 2026. Verfasst von Aoi Ito und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The extraction of treatment response information from unstructured clinical notes is a critical task in oncology research and clinical practice, particularly for lung cancer, where therapeutic paradigms evolve rapidly. Despite the promising capabilities of advanced natural language processing models, their opaque nature significantly limits clinical adoption due to a lack of interpretability and trustworthiness. This paper investigates the development and implementation of an explainable clinical text mining framework explicitly designed to extract treatment response trajectories from unstructured electronic health records pertaining to lung cancer cohorts. By integrating transformer-based language models with robust explainability techniques, the proposed methodology aims to bridge the gap between high predictive performance and clinical transparency. The analysis encompasses an exhaustive review of current natural language processing applications in oncology, a detailed explication of the architectural design prioritizing attention-based interpretability, and a rigorous evaluation against traditional black-box methodologies. The findings demonstrate that augmenting extraction models with explanatory mechanisms not only maintains state-of-the-art accuracy but also significantly enhances clinician trust by providing verifiable linguistic evidence for every automated extraction. This research underscores the necessity of transparent artificial intelligence in high-stakes medical domains and provides a scalable blueprint for deploying explainable text mining systems in real-world oncology workflows.

Zitieren

APA

Ito, A., & Darren, B. (2026). Explainable Clinical Text Mining for Treatment Response Extraction in Lung Cancer Notes. Journal of the Artificial Intelligence Engineers Consortium. https://doi.org/10.66238/jaiec57

Vancouver

Ito A, Darren B. Explainable Clinical Text Mining for Treatment Response Extraction in Lung Cancer Notes. Journal of the Artificial Intelligence Engineers Consortium. 2026. doi:10.66238/jaiec57

BibTeX
@article{Ito2026,
  author = {Ito, Aoi and Darren, Bernard},
  title = {Explainable Clinical Text Mining for Treatment Response Extraction in Lung Cancer Notes},
  journal = {Journal of the Artificial Intelligence Engineers Consortium},
  year = {2026},
  doi = {10.66238/jaiec57}
}
Kostenlos starten →