The Role of Nursing and Radiology Professionals in Improving the Quality of Medical Coding for Sinonasal Diseases Using Artificial Intelligence Technologies: A Systematic Review

Abstract

Background: Artificial intelligence (AI) has transformed clinical workflows in otorhinolaryngology, enhancing diagnostic precision and data-driven decision-making. Its integration into sinonasal disease management provides opportunities for radiology and nursing professionals to collaboratively enhance medical coding quality and efficiency.
Objective: This systematic review synthesizes current empirical evidence on the role of nursing and radiology professionals in improving coding accuracy for sinonasal diseases using AI-driven technologies.
Methods: Following PRISMA 2020 guidelines, ten peer-reviewed studies published between 2018 and 2025 were analyzed. Databases searched included PubMed, Scopus, Web of Science, Embase, and IEEE Xplore. Eligible studies reported AI-assisted sinonasal diagnostics and coding applications involving healthcare professionals.

Results: AI systems demonstrated diagnostic accuracies of 91–99% and AUCs up to 0.993 across CT, MRI, and CBCT datasets. Integration of self-supervised learning, AutoML, and hybrid deep learning models enhanced diagnostic speed and coding standardization. Nursing professionals contributed to annotation, data integrity, and ICD validation, while radiology experts curated imaging datasets and interpreted algorithmic outputs. Combined efforts reduced coding time by 46% and improved interprofessional collaboration.

Conclusion: Radiology and nursing collaboration within AI-assisted frameworks significantly improves sinonasal diagnostic accuracy and medical coding consistency. These advancements enhance workflow efficiency and documentation quality, highlighting the necessity of multidisciplinary AI literacy in clinical practice.

although platelet aggregation caused by cyclooxygenase inhibition has little or no effect on carrageenan-induced thrombosis in rat tails.