Articles In Press
Back to the articles list |
Back to browse issues page
Ethics code: 1
Sirjan School of Medicine
Abstract: (220 Views)
Introduction: This systematic review aimed to comprehensively examine computational models, implementation challenges, and future perspectives of intelligent referral systems in Electronic Health Records (EHRs) to identify research gaps and propose sustainable development strategies.
Information sources or data: A systematic search was conducted in databases including PubMed, Scopus, Web of Science, and IEEE Xplore, as well as the Google Scholar search engine. Relevant keywords such as "Electronic Health Records," "Intelligent Referral Systems," and "Artificial Intelligence in Healthcare" were used to retrieve articles published between 2006 and 2025, covering both English-language sources and gray literature.
Selection methods for study: The study adhered to standard systematic review guidelines. Inclusion criteria focused on computational models and clinical applications. Out of 2,235 initial records, duplicates were removed (435), followed by title/abstract screening of 1,800 records (excluding 1,450 irrelevant ones). Full-text assessment was performed on 350 articles, resulting in the selection of 20 studies. Data extraction was conducted via NVivo, and quality appraisal was performed using AMSTAR-2 and RoB 2 tools.
Combine content and results: The results indicated that machine learning models (40%) and explainable AI (20%) were the dominant approaches, demonstrating high accuracy in risk prediction and referral prioritization. Fuzzy rules were utilized for uncertainty management, while blockchain technology was employed for security and interoperability. Identified challenges included data integration, privacy concerns, user acceptance, and infrastructural limitations. It was found that 60% of the studies were of high quality, with a notable surge in publications post-2019.
Conclusion: Intelligent referral systems hold transformative potential for digital health; however, their success depends on addressing technical and ethical barriers. Future recommendations include focusing on user training, standardization, and research in low-resource settings to enhance global efficiency.
Information sources or data: A systematic search was conducted in databases including PubMed, Scopus, Web of Science, and IEEE Xplore, as well as the Google Scholar search engine. Relevant keywords such as "Electronic Health Records," "Intelligent Referral Systems," and "Artificial Intelligence in Healthcare" were used to retrieve articles published between 2006 and 2025, covering both English-language sources and gray literature.
Selection methods for study: The study adhered to standard systematic review guidelines. Inclusion criteria focused on computational models and clinical applications. Out of 2,235 initial records, duplicates were removed (435), followed by title/abstract screening of 1,800 records (excluding 1,450 irrelevant ones). Full-text assessment was performed on 350 articles, resulting in the selection of 20 studies. Data extraction was conducted via NVivo, and quality appraisal was performed using AMSTAR-2 and RoB 2 tools.
Combine content and results: The results indicated that machine learning models (40%) and explainable AI (20%) were the dominant approaches, demonstrating high accuracy in risk prediction and referral prioritization. Fuzzy rules were utilized for uncertainty management, while blockchain technology was employed for security and interoperability. Identified challenges included data integration, privacy concerns, user acceptance, and infrastructural limitations. It was found that 60% of the studies were of high quality, with a notable surge in publications post-2019.
Conclusion: Intelligent referral systems hold transformative potential for digital health; however, their success depends on addressing technical and ethical barriers. Future recommendations include focusing on user training, standardization, and research in low-resource settings to enhance global efficiency.
Keywords: Electronic Health Records, Artificial Intelligence, Intelligent Referral, Machine Learning, Implementation Challenges
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
