EUVIMEDEUVIMED entdecken
Open Access

Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study

Muhammad Tayyab Zamir iD, Safir Ullah Khan iD, Alexander Gelbukh iD, Edgardo Manuel Felipe Riverón iD, Irina Gelbukh iD

JMIR Formative Research · 14.10.2025 · 9 · e77482

DOI: 10.2196/77482 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 14.10.2025. Verfasst von Muhammad Tayyab Zamir und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centro de Investigación en Computación (CIC), Instituto Politécnico Nacional (IPN), Ciudad de México, CDMX, Mexico. Hauptthemen laut MEDLINE: Artificial Intelligence, Radiology. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) is increasingly being integrated into clinical diagnostics; yet, its lack of transparency hinders trust and adoption among health care professionals. The explainable artificial intelligence (XAI) has the potential to improve the interpretability and reliability of AI-based decisions in clinical practice.

Objective

This study evaluates the use of XAI for interpreting radiology reports to improve health care practitioners’ confidence and comprehension of AI-assisted diagnostics.

Methods

This study used the Indiana University chest x-ray dataset containing 3169 textual reports and 6471 images. Textual data were being classified as either normal or abnormal by using a range of machine learning approaches. This includes traditional machine learning models and ensemble methods, deep learning models (long short-term memory network), and advanced transformer-based language models (GPT-2, T5, LLaMA-2, and LLaMA-3.1). For image-based classifications, convolutional neural networks, including DenseNet121 and DenseNet169, were used. Top-performing models were interpreted using XAI methods SHAP (Shapley Adaptive Explanations) and Local Interpretable Model-Agnostic Explanations to support clinical decision making by enhancing transparency and trust in model predictions.

Results

The LLaMA-3.1 model achieved the highest accuracy of 98% in classifying the textual radiology reports. Statistical analysis confirmed the model’s robustness, with Cohen κ (k=0.981) indicating near-perfect agreement beyond chance. Both the chi-square and Fisher exact tests revealed a highly significant association between the actual and predicted labels (P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceRadiologyHumansReproducibility of ResultsMachine LearningNeural Networks, Computer

Stichwörter der Autor:innen

LIMELocal Interpretable Model-Agnostic ExplanationsSHAPShapley Adaptive Explanationsartificial intelligenceexplainable AInatural language processingradiology

Autor:innen und Institutionen

  • Centro de Investigación en Computación (CIC), Instituto Politécnico Nacional (IPN), Ciudad de México, CDMX, Mexico.
  • Department of Cell Biology, Center for Research and Advanced Studies of the National Polytechnic Institute, Ciudad de México, CDMX, Mexico.

ORCID-Profile: Muhammad Tayyab Zamir, Safir Ullah Khan, Alexander Gelbukh, Edgardo Manuel Felipe Riverón, Irina Gelbukh

Zitieren

APA

Zamir, M. T., Khan, S. U., Gelbukh, A., Felipe Riverón, E. M., & Gelbukh, I. (2025). Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study. JMIR Formative Research, 9, e77482. https://doi.org/10.2196/77482

Vancouver

Zamir MT, Khan SU, Gelbukh A, Felipe Riverón EM, Gelbukh I. Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study. JMIR Formative Research. 2025;9:e77482. doi:10.2196/77482

BibTeX
@article{Zamir2025,
  author = {Zamir, Muhammad Tayyab and Khan, Safir Ullah and Gelbukh, Alexander and Felipe Riverón, Edgardo Manuel and Gelbukh, Irina},
  title = {Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study},
  journal = {JMIR Formative Research},
  year = {2025},
  volume = {9},
  pages = {e77482},
  doi = {10.2196/77482}
}
Kostenlos starten →