Human-in-the-Loop AI in Diagnostic Imaging: Roles of Physician Assistants in Supporting Safe and Efficient Radiology Practice

Artificial intelligence (AI) is increasingly becoming incorporated into diagnostic imaging for image interpretation, triage, reconstruction, quantification, workflow optimization and report generation. The effectiveness of such tools goes beyond the algorithms but also relies on how the AI-derived information is interpreted and translated into actions. Human-in-the-loop systems allow trained medical practitioners to mediate between the AI-derived information and the action taken by the practitioner. This review outlines the potential of Physician Assistants (PAs) to assist in safe and efficient use of artificial intelligence in radiology practice. Evidence has been found to show that the inclusion of AI-assisted interpretations improves selected diagnostic tasks. However, external validation and clinical evidence are key factors to consider. Studies conducted recently have shown degradation in performance on external data, whereas new research on human-AI collaboration has identified automation bias, user interface, integration in the workflow, skill effect and governance as factors contributing to clinical value. PA can add value through provision of clinical context, patient preparation, urgency identification, communication and coordination, discrepancy reporting and quality improvement activities. Safe implementation of AI in radiology involves local validation, training in roles, performance monitoring, escalation process, privacy and multidisciplinary governance. The outputs from AI systems must only be treated as supporting information to make decisions and should never replace qualified radiological analysis.

Artificial intelligence; Diagnostic imaging; Radiology; Physician assistant; Human-in-the-loop; Patient safety

1. Baethge, C., Goldbeck-Wood, S., & Mertens, S. (2019). SANRA—a scale for the quality assessment of narrative review articles. Research Integrity and Peer Review, 4, 5. https://doi.org/10.1186/s41073-019-0064-8 [Google Scholar] [Crossref]

2. Breunig, M., Bafuma, P., & Bludorn, J. (2025). Point-of-care ultrasound curricula in physician assistant programs: Recommendations from a panel of experts. Journal of Physician Assistant Education, 36(3), e240–e247. https://doi.org/10.1097/JPA.0000000000000663 [Google Scholar] [Crossref]

3. External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review. (2022). Radiology. PMID: 35652114. [Google Scholar] [Crossref]

4. Geis, J. R., Brady, A. P., Wu, C. C., Spencer, J., Ranschaert, E., Jaremko, J. L., Langer, S. G., Kitts, A. B., Birch, J., Shields, W. F., van den Hoven van Genderen, R., Kotter, E., Gichoya, J. W., Cook, T. S., Morgan, M. B., Tang, A., Safdar, N. M., & Kohli, M. (2019). Ethics of artificial intelligence in radiology: Summary of the joint European and North American multisociety statement. Radiology, 293(2), 436–440. https://doi.org/10.1148/radiol.201919158 [Google Scholar] [Crossref]

5. Grant, M. J., & Booth, A. (2009). A typology of reviews: An analysis of 14 review types and associated methodologies. Health Information and Libraries Journal, 26(2), 91–108. [Google Scholar] [Crossref]

6. https://doi.org/10.1111/j.1471-1842.2009.00848.x [Google Scholar] [Crossref]

7. Kelly, B. S., Judge, C., Bollard, S. M., Clifford, S., Healy, G. M., Aziz, A., & others. (2022). Radiology artificial intelligence: A systematic review and evaluation of methods (RAISE). European Radiology, 32(11), 7998–8007. [Google Scholar] [Crossref]

8. Kim, J., Adams, L. C., Wiestler, B., & Hedderich, D. M. (2026). Human-AI collaboration in radiology: The blind spots. Radiology: Artificial Intelligence, 8(5), e260325. [Google Scholar] [Crossref]

9. https://doi.org/10.1148/ryai.260325 [Google Scholar] [Crossref]

10. Kim, J., Maranna, S., Watson, C., & Parange, N. (2025). A scoping review on the integration of artificial intelligence in point-of-care ultrasound: Current clinical applications. American Journal of Emergency Medicine, 92, 172–181. https://doi.org/10.1016/j.ajem.2025.03.029 [Google Scholar] [Crossref]

11. Kocak, B., & Cuocolo, R. (2026). Human–AI interaction and collaboration in radiology: From conceptual frameworks to responsible implementation. Diagnostic and Interventional Radiology, 32(5), 535–547. https://doi.org/10.4274/dir.2026.263780 [Google Scholar] [Crossref]

12. Lee, R. C., Hadidchi, R., Coard, M. C., Rubinov, Y., Alamuri, T., Liaw, A., Chandrupatla, R., & Duong, T. Q. (2026). Use of large language models on radiology reports: A scoping review. Journal of the American College of Radiology, 23(3), 437–454. https://doi.org/10.1016/j.jacr.2025.10.005 [Google Scholar] [Crossref]

13. Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., & FUTURE-AI Consortium. (2025). FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare. BMJ, 388, e081554. https://doi.org/10.1136/bmj-2024-081554 [Google Scholar] [Crossref]

14. Mongan, J., Moy, L., & Kahn, C. E., Jr. (2020). Checklist for artificial intelligence in medical imaging (CLAIM): A guide for authors and reviewers. Radiology: Artificial Intelligence, 2(2), e200029. [Google Scholar] [Crossref]

15. https://doi.org/10.1148/ryai.2020200029 [Google Scholar] [Crossref]

16. Schuur, F., Rezazade Mehrizi, M. H., & Ranschaert, E. (2021). Training opportunities of artificial intelligence (AI) in radiology: A systematic review. European Radiology, 31(8), 6021–6029. [Google Scholar] [Crossref]

17. Snyder, H. (2019). Literature review as a research methodology: An overview and guidelines. Journal of Business Research, 104, 333–339. https://doi.org/10.1016/j.jbusres.2019.07.039 [Google Scholar] [Crossref]

18. Suleman, M. U., Mursaleen, M., Khalil, U., Saboor, A., Bilal, M., Khan, S. A., Subhani, M. A., Hussnain, M. A., Tabassum, S. N., & Tahir, M. (2025). Assessing the generalizability of artificial intelligence in radiology: A systematic review of performance across different clinical settings. Annals of Medicine and Surgery, 87(12), 8803–8811. https://doi.org/10.1097/MS9.0000000000004166 [Google Scholar] [Crossref]

19. Tejani, A. S., Klontzas, M. E., Gatti, A. A., et al. (2024). Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update. Radiology: Artificial Intelligence, 6(4), e240300. [Google Scholar] [Crossref]

20. Yan, Y., Liu, C., Fu, H., Xu, K., & Xu, H. (2026). Efficacy evaluation of artificial intelligence in radiological imaging diagnosis based on randomized controlled trials: A scoping review. European Radiology. Advance online publication. https://doi.org/10.1007/s00330-026-12715-0 [Google Scholar] [Crossref]

21. Zak, C. L., & Monti, J. D. (2022). PAs and point-of-care ultrasound: A scoping review. JAAPA, 35(4), 43–50. [Google Scholar] [Crossref]

22. Zhao, D., Packer, T., Jie, X., Shahid, M., Oke, J., & Plüddemann, A. (2025). Diagnostic accuracy of artificial intelligence-assisted radiology assessment of cancer: A systematic review. BJR|Artificial Intelligence, 2(1), ubaf016. https://doi.org/10.1093/bjrai/ubaf016 [Google Scholar] [Crossref]

23. World Health Organization. (2021). Ethics and governance of artificial intelligence for health: WHO guidance. World Health Organization. [Google Scholar] [Crossref]

• Psychosocial Competencies and Well-Being of University Graduates: A Review