Articles In Press
Back to the articles list |
Back to browse issues page
Ethics code: 1
Sirjan School of Medicine
Abstract: (8 Views)
Introduction: Intelligent referral systems within Electronic Health Records (EHRs) leverage advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), and blockchain to enhance healthcare quality, improve efficiency, and reduce costs. These systems enable the analysis of complex clinical data, streamline care coordination, and support precise decision-making. Despite digital advancements, challenges like data heterogeneity, privacy concerns, and interoperability issues persist. This systematic review aims to comprehensively examine computational models, implementation challenges, and future prospects of intelligent referral systems, identifying research gaps and proposing sustainable development pathways.
Methods: This review adhered to PRISMA 2020 guidelines. A systematic search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar using keywords such as “Electronic Health Records,” “Intelligent Referral Systems,” and “Artificial Intelligence in Healthcare.” The search spanned 2019–2025, focusing on English-language sources. Inclusion criteria targeted computational models and clinical applications. From 2,235 initial records, 20 studies were selected for qualitative synthesis after screening. Data extraction was performed using NVivo, with quality assessment via AMSTAR-2 and RoB 2.
Results: Analysis revealed that machine learning models (40%) and explainable AI (20%) dominate, offering high accuracy in clinical risk prediction and referral prioritization. Fuzzy rule-based systems manage data uncertainty, while blockchain enhances security and interoperability. Key challenges include data integration, privacy, user acceptance, and infrastructural limitations. Sixty percent of studies were high quality, though some exhibited bias risks due to data heterogeneity.
Methods: This review adhered to PRISMA 2020 guidelines. A systematic search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar using keywords such as “Electronic Health Records,” “Intelligent Referral Systems,” and “Artificial Intelligence in Healthcare.” The search spanned 2019–2025, focusing on English-language sources. Inclusion criteria targeted computational models and clinical applications. From 2,235 initial records, 20 studies were selected for qualitative synthesis after screening. Data extraction was performed using NVivo, with quality assessment via AMSTAR-2 and RoB 2.
Results: Analysis revealed that machine learning models (40%) and explainable AI (20%) dominate, offering high accuracy in clinical risk prediction and referral prioritization. Fuzzy rule-based systems manage data uncertainty, while blockchain enhances security and interoperability. Key challenges include data integration, privacy, user acceptance, and infrastructural limitations. Sixty percent of studies were high quality, though some exhibited bias risks due to data heterogeneity.
Keywords: Electronic Health Records, Artificial Intelligence, Referral and Consultation, Machine Learning, Blockchain
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |