Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study
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.
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)
Stichwörter der Autor:innen
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}
}
EUVIMED