Volume 11, Issue 1 (Spring 2025 2025)
JMIS 2025, 11(1): 109-124 |
Back to browse issues page
Ethics code: 1
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Kashani M. Intelligent referral system in electronic health records: A comprehensive review of models, challenges, and future perspectives. JMIS 2025; 11 (1) :109-124
URL: http://jmis.hums.ac.ir/article-1-592-en.html
URL: http://jmis.hums.ac.ir/article-1-592-en.html
Department of Health Information Technology, Sirjan School of Medical Sciences, Sirjan, Iran.
Abstract: (724 Views)
Introduction: This systematic review aimed to examine computational models, implementation challenges, and future pathways of intelligent referral systems integrated with Electronic Health Records (EHRs), with the goal of identifying research gaps and proposing sustainable development directions.
Information sources or data: A comprehensive search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar for studies published between 2006 and 2025, including English-language gray literature.
Selection methods for study: Following standard systematic review guidelines, 2,235 initial records were identified. After removing duplicates and screening titles and abstracts, 350 full texts were assessed, and 20 eligible studies were included. Data extraction was performed using NVivo, and study quality was evaluated using AMSTAR-2 and RoB-2 tools.
Combine content and results: Findings indicated that machine learning (40%) and explainable AI (20%) were the dominant approaches, demonstrating strong performance in risk prediction and referral prioritization. Fuzzy logic was applied to manage uncertainty, and blockchain technologies were used to enhance security and interoperability. Major challenges included data integration, privacy concerns, user acceptance, and infrastructural limitations. Sixty percent of the studies were rated as high quality, with a clear increase in publications after 2019.
Conclusion: Intelligent referral systems hold significant potential to advance digital health, yet their effectiveness depends on overcoming technical and ethical barriers. Emphasis on user training, standard development, and research in low-resource environments is recommended to improve their global applicability.
Information sources or data: A comprehensive search was conducted in PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar for studies published between 2006 and 2025, including English-language gray literature.
Selection methods for study: Following standard systematic review guidelines, 2,235 initial records were identified. After removing duplicates and screening titles and abstracts, 350 full texts were assessed, and 20 eligible studies were included. Data extraction was performed using NVivo, and study quality was evaluated using AMSTAR-2 and RoB-2 tools.
Combine content and results: Findings indicated that machine learning (40%) and explainable AI (20%) were the dominant approaches, demonstrating strong performance in risk prediction and referral prioritization. Fuzzy logic was applied to manage uncertainty, and blockchain technologies were used to enhance security and interoperability. Major challenges included data integration, privacy concerns, user acceptance, and infrastructural limitations. Sixty percent of the studies were rated as high quality, with a clear increase in publications after 2019.
Conclusion: Intelligent referral systems hold significant potential to advance digital health, yet their effectiveness depends on overcoming technical and ethical barriers. Emphasis on user training, standard development, and research in low-resource environments is recommended to improve their global applicability.
Keywords: Electronic Health Records, Artificial Intelligence, Intelligent Referral, Machine Learning, Implementation Challenges.
Type of Study: Review |
Subject:
Special
Received: 2025/08/15 | Accepted: 2024/12/30 | Published: 2025/03/21
Received: 2025/08/15 | Accepted: 2024/12/30 | Published: 2025/03/21
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Contact Us
Post Address: Bandar Abbas, Imam Hossein Boulevard, campus of University of Medical Sciences, School of Nursing and Midwifery.
Tel: +(98) 763 331 7723
Cell Phone: +(98) 939 654 9816
jmis
hums.ac.ir
