ANALYZING DISCREPANCIES BETWEEN AI-GENERATED AND ONCOLOGIST-FINALIZED TREATMENT RECOMMENDATIONS IN VIRTUAL CANCER CARE: IMPACT ON CLINICAL WORKFLOW AND PATIENT OUTCOMES

The application of AI to virtual cancer care has made a tremendous impact on the clinical decision-making process, as it has aided the process of diagnosis, treatment planning, and therapeutic advice, but the gap between the AI-based treatment advice and the finalized decision of the oncologist has become a crucial issue. Such discrepancies can influence clinical practice, drug safety, and patient outcomes especially in digitally mediated oncology environments. The objective of this narrative review is to examine the nature and degree of difference between AI-generated and oncologist-finalized treatment advice during virtual cancer care and to investigate their effect on clinical workflow, oncology pharmacotherapy, medication safety, and patient outcomes. The literature search involved PubMed, Scopus, and Google Scholar, including those that were published as early as 2018 to 2026 and assessed AI-aided oncology decision-making, clinician-AI discordance, workflow implications, and patient-related outcomes. The examined literature indicates that there is a general range of 60-80 percent AI-clinician concordance, but the discrepancies are caused by both quantitative (regimen selection and line of therapy) and qualitative (patient comorbidities, preferences, and contextual clinical judgment) factors. These inconsistencies frequently require extra verification procedures, augment cognition, and expand the multidisciplinary decision-making. Notably, oncology pharmacists can have the key role of reducing the risk of AI-based recommendations by validating chemotherapy regimens, making sure of adequate dose, potential drug-drug interactions, and medication safety. To sum up, although AI has a potential to improve efficiency and standardization in virtual oncology care, the ongoing discrepancies highlight the significance of human-in-the-loop models, explainable AI systems, and active participation of oncology pharmacists to streamline the workflow, protect the use of medications, and promote patient-centered outcomes.

• Jiang, Fei, et al. ‘Artificial Intelligence in Healthcare: Past, Present and Future’. Stroke and Vascular Neurology, Dec. 2017; 2(4): 230–43. DOI.org (Crossref), https://doi.org/10.1136/svn-2017-000101.
• K.-A. So, E.-B. Jang, S.-H. Shim, S.-J. Lee, and T.-J. Kim, “Diagnostic Accuracy of Artificial Intelligence vs. Oncologist Interpretation in Digital Cervicography for Abnormal Cervical Cytology,” J. Clin. Med., Mar. 2025; 14(5): 1763. doi: 10.3390/jcm14051763.
• S. Suwanvecho et al., “Comparison of an oncology clinical decision-support system’s recommendations with actual treatment decisions,” J. Am. Med. Informatics Assoc., Mar. 2021; 28(4): 832–838. doi: 10.1093/jamia/ocaa334.
• P. Tini et al., “Assessing ChatGPT-4 as a clinical decision support tool in neuro-oncology radiotherapy: a prospective comparative study,” J. Neurooncol., Jan. 2026; 176(1): 13. doi: 10.1007/s11060-025-05254-z.
• S. P. Somashekhar et al., “Watson for Oncology and breast cancer treatment recommendations: agreement with an expert multidisciplinary tumor board,” Ann. Oncol., Feb. 2018; 29(2): 418–423. doi: 10.1093/annonc/mdx781.
• J. Li et al., “A comparison between clinical decision support system and clinicians in breast cancer,” Heliyon, May 2023; 9(5): e16059. doi: 10.1016/j.heliyon.2023.e16059.
• I. Dogan et al., “Chat GPT Performance in Multi-Disciplinary Boards—Should AI Be a Member of Cancer Boards?,” Healthcare, Sep. 2025; 13(18): 2254. doi: 10.3390/healthcare13182254.
• Z. Jie, Z. Zhiying, and L. Li, “A meta-analysis of Watson for Oncology in clinical application,” Sci. Rep., Mar. 2021; 11(1): 5792. doi: 10.1038/s41598-021-84973-5.
• G. Duwe et al., “Challenges and perspectives in use of artificial intelligence to support treatment recommendations in clinical oncology,” Cancer Med., Jun. 2024; 13: 12. doi: 10.1002/cam4.7398.
• K. Jeziorski and R. Olszewski, “Artificial Intelligence in Oncology,” Appl. Sci., Dec. 2024; 15(1): 269. doi: 10.3390/app15010269.
• C. Jones, J. Thornton, and J. C. Wyatt, “Artificial intelligence and clinical decision support: clinicians’ perspectives on trust, trustworthiness, and liability,” Med. Law Rev., Nov. 2023; 31(4): 501–520. doi: 10.1093/medlaw/fwad013.
• Y. Madan, A. Perivolaris, R. C. Adams-McGavin, and J. J. Jung, “Clinician interaction with artificial intelligence systems: a narrative review,” J. Med. Artif. Intell., Sep. 2025; 8: 22–22. doi: 10.21037/jmai-24-279.
• F. Madanay, L. S. O’Donohue, and B. J. Zikmund-Fisher, “Patient Reactions to Artificial Intelligence–Clinician Discrepancies: Web-Based Randomized Experiment,” J. Med. Internet Res., May 2025; 27: e68823. doi: 10.2196/68823.
• E. Ogut, “Artificial Intelligence in Clinical Medicine: Challenges Across Diagnostic Imaging, Clinical Decision Support, Surgery, Pathology, and Drug Discovery,” Clin. Pract., Sep. 2025; 15(9): 169. doi: 10.3390/clinpract15090169.
• Q. Abbas, W. Jeong, and S. W. Lee, “Explainable AI in Clinical Decision Support Systems: A Meta-Analysis of Methods, Applications, and Usability Challenges,” Healthcare, Aug. 2025; 13(17): 2154. doi: 10.3390/healthcare13172154.
• V. Sivaraman, L. A. Bukowski, J. Levin, J. M. Kahn, and A. Perer, “Ignore, Trust, or Negotiate: Understanding Clinician Acceptance of AI-Based Treatment Recommendations in Health Care,” in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, New York, NY, USA: ACM, Apr. 2023; 1–18. doi: 10.1145/3544548.3581075.
• L. Wang et al., “Artificial intelligence in clinical decision support systems for oncology,” Int. J. Med. Sci., 2023; 20(1): 79–86. doi: 10.7150/ijms.77205.
• S. Emani et al., “Physicians’ Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle–Income Countries,” JMIR Cancer, Apr. 2022; 8(2): e31461. doi: 10.2196/31461.
• F. Kücking et al., “Impact of AI recommendation correctness on diagnostic accuracy in clinical decision-making,” Int. J. Med. Inform., Mar. 2026; 207: 106223. doi: 10.1016/j.ijmedinf.2025.106223.
• M. Xu et al., “Global research trends in the application of artificial intelligence in oncology care: a bibliometric study,” Front. Oncol., Jan. 2025; 14. doi: 10.3389/fonc.2024.1456144.
• P. Istasy et al., “The Impact of Artificial Intelligence on Health Equity in Oncology: Scoping Review,” J. Med. Internet Res., Nov. 2022; 24(11): e39748. doi: 10.2196/39748.
• E. A. Nicu, P. Rijkschroeff, E. Wartewig, K. Nazmi, and B. G. Loos, “Characterization of oral polymorphonuclear neutrophils in periodontitis patients: a case-control study,” BMC Oral Health, Dec. 2018; 18(1): 149. doi: 10.1186/s12903-018-0615-2.