Document Type : Review Article
Authors
1
Department of Knowledge and Information Science, Payame Noor University, Tehran, Iran
2
Infectious Diseases Research Center, Gonabad University of Medical Sciences, Gonabad, Iran
10.30491/hpr.2025.546425.1508
Abstract
Background: Artificial Intelligence (AI), as a transformative technology, has found widespread applications in the health and hospital sectors.
Objectives: The present study aimed to analyze scientific articles related to AI in hospitals using text mining methods to identify dominant topics and emerging trends.
Methods: In the present study, text mining and topic modeling approaches were used to analyze research trends and identify dominant topics. The research steps included data collection from Scopus, text preprocessing, extraction of frequent words, topic modeling using Latent Dirichlet Allocation (LDA), and visualization. All steps were performed using the Python programming language and open-source libraries, such as NLTK, Gensim, Matplotlib, scikit-learn, and pyLDAvis.
Results: A total of 2238 records related to AI in hospitals were collected from Scopus since 2000. The terms "patient," "model," "machine learning," and "artificial intelligence" were identified as the most frequently used terms. The dominant topic clusters included "patient monitoring," "data-driven systems," "service innovation and emerging technologies," "clinical outcome prediction," "COVID-19 risk prediction," "mortality and hospitalization prediction," "health tourism," "management and implementation," and "hospital death prediction." Most articles were in the clusters "clinical outcome prediction modeling" (663 documents) and "mortality and hospitalization prediction" (335 documents). The publication trend has accelerated significantly since 2018, especially in the clusters "clinical outcome prediction" and "management and implementation."
Conclusion: Conclusion: Artificial intelligence in hospitals has grown rapidly over the last two decades. The shift from limited applications in modeling and prediction to interdisciplinary areas and innovative services indicates the gradual growth of this technology and its role in improving the quality of care, optimizing organizational processes, and developing new services.
Keywords
