Discrepancies Between MDT Recommendations and AI-Generated Decisions in Gynecologic Oncology: A Retrospective Comparative Cohort Study
Open accessAbstract
Background: Multidisciplinary tumor boards (MDTs) remain the foundation of gynecologic cancer management, yet increasing diagnostic complexity and rapidly evolving molecular classifications have intensified interest in artificial intelligence (AI) as a potential decision-support tool. This study aimed to evaluate the concordance between MDT-derived recommendations and those generated by ChatGPT 5.0 across a large, real-world cohort of gynecologic oncology cases. Methods: This single-center retrospective analysis included 599 consecutive patients with cervical, endometrial, ovarian, or vulvar cancer evaluated during MDT meetings over a 2-month period. Standardized anonymized case summaries were entered into ChatGPT 5.0, which was instructed to follow current ESGO guidelines. AI-generated staging and treatment recommendations were compared with MDT decisions. Discrepancies were independently assessed by two reviewers and stratified by malignancy type, disease stage, and treatment domain. Results: Overall concordance for FIGO staging was 77.0%, while treatment-related decisions demonstrated lower discordance, particularly in chemotherapy (8.2%) and targeted therapy (6.8%). The highest staging disagreement occurred in early-stage endometrial cancer (32.6%), reflecting the complexity of newly revised molecular classifications. In recurrent ovarian and cervical cancer, discrepancies were more pronounced in surgical and systemic therapy recommendations, suggesting limited AI capacity to integrate multimodal imaging, prior treatments, and individualized considerations. Vulvar cancer cases showed the highest overall agreement. Conclusions: ChatGPT 5.0 aligns with MDT decisions in many straightforward scenarios but falls short in complex or nuanced cases requiring contextual, multimodal, and patient-specific reasoning. These findings underscore the need for prospective, real-time evaluation, multimodal data integration, external validation, and explainable AI frameworks before LLMs can be safely incorporated into routine gynecologic oncology decision-making.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Pergialiotis et al. evaluated ChatGPT-5 against MDT decisions in 599 gynecologic cancer cases, reporting high overall concordance but recurrent discrepancies in advanced and recurrent disease, with staging disagreements predominating.
“Most recently, Pergialiotis et al. evaluated ChatGPT-5 against MDT decisions in 599 gynecologic cancer cases, reporting high overall concordance but recurrent discrepancies in advanced and recurrent disease, with staging disagreements predominating [15].”
From Feasibility and Concordance of a Large Language Model (ChatGPT-5) as a Clinical Decision Support Tool in Gynecologic Oncology Tumor Boards: A Blinded, Multi-Observer Study (2026) · cites this paper as [15]
The Results report 599 patients and 77.0% agreement on FIGO staging; the Discussion (section 4.2) identifies advanced and recurrent cases as challenging and staging disagreement as the most prominent issue. But the Conclusions characterize overall agreement with MDT decisions as moderate, not high, so the claim overstates that aspect. (LLM, conf=0.87)
Experimental — accuracy not yet measuredPergialiotis et al. evaluated ChatGPT-5 against MDT decisions in 599 cases and found that concordance deteriorated in advanced and recurrent disease, with staging and multimodal decisions driving discordance.
“Pergialiotis et al. evaluated the same model (ChatGPT-5) against MDT decisions in a larger cohort of 599 cases and likewise found that concordance deteriorated in advanced and recurrent disease, with staging and multimodal decisions driving discordance [15].”
Our findings align closely with Pergialiotis et al.
“Our findings align closely with the most directly comparable study: Pergialiotis et al.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Abbas, Q., Jeong, W., & Lee, S. W. (2025) · Healthcare · doi:10.3390/healthcare13172154 · Cited by 236 · cited 1× · see citing works
“On the other hand, a systematic review focusing on the use of AI in clinical decision-support systems denoted that transparency and interpretability are critical elements to help establish clinician trust, accountability, and safe integration [25].”
Meyer, B., Kfuri‐Rubens, R., Schmidt, G., Tariq, M., Riedel, C., Recker, F., Riedel, F., Kiechle, M., & Riedel, M. (2025) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.70251 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 23
- [1]Taberna M. Gil Moncayo F. Jané-Salas E. Antonio M. Arribas L. Vilajosana E. Peralvez Torres E. Mesía R. The Multidisciplinary Team (MDT) Approach and Quality of Care Front. Oncol. 2020 10 85 10.3389/fonc.2020.00085 32266126 PMC7100151 · DOI
- [2]Concin N. Matias-Guiu X. Cibula D. Colombo N. Creutzberg C.L. Ledermann J. Mirza M.R. Vergote I. Abu-Rustum N.R. Bosse T. ESGO–ESTRO–ESP guidelines for the management of patients with endometrial carcinoma: Update 2025 Lancet Oncol. 2025 26 e423 e435 10.1016/S1470-2045(25)00167-6 40744042 · DOI
- [3]Colombo N. Sessa C. du Bois A. Ledermann J. McCluggage W.G. McNeish I. Morice P. Pignata S. Ray-Coquard I. Vergote I. ESMO-ESGO consensus conference recommendations on ovarian cancer: Pathology and molecular biology, early and advanced stages, borderline tumours and recurrent disease Ann. Oncol. 2019 30 672 705 10.1093/annonc/mdz062 31048403 · DOI · Paper page
- [4]Cibula D. Raspollini M.R. Planchamp F. Centeno C. Chargari C. Felix A. Fischerová D. Jahnn-Kuch D. Joly F. Kohler C. ESGO/ESTRO/ESP Guidelines for the management of patients with cervical cancer—Update 2023 Int. J. Gynecol. Cancer 2023 33 649 666 10.1136/ijgc-2023-004429 37127326 PMC10176411 · DOI
- [5]Oonk M.H.M. Planchamp F. Baldwin P. Mahner S. Mirza M.R. Fischerová D. Creutzberg C.L. Guillot E. Garganese G. Lax S. European Society of Gynaecological Oncology Guidelines for the Management of Patients with Vulvar Cancer—Update 2023 Int. J. Gynecol. Cancer 2023 33 1023 1043 10.1136/ijgc-2023-004486 37369376 PMC10359596 · DOI
- [6]Lambin P. Leijenaar R.T.H. Deist T.M. Peerlings J. de Jong E.E.C. van Timmeren J. Sanduleanu S. Larue R. Even A.J.G. Jochems A. Radiomics: The bridge between medical imaging and personalized medicine Nat. Rev. Clin. Oncol. 2017 14 749 762 10.1038/nrclinonc.2017.141 28975929 · DOI · Paper page
- [7]Ghasemi S.F. Amiri P. Galavi Z. Advantages and Limitations of ChatGPT in Healthcare: A Scoping Review Health Sci. Rep. 2025 8 e71219 10.1002/hsr2.71219 40950935 PMC12423551 · DOI
- [8]Li C.-P. Jakob J. Menge F. Reißfelder C. Hohenberger P. Yang C. Comparing ChatGPT-3.5 and ChatGPT-4’s alignments with the German evidence-based S3 guideline for adult soft tissue sarcoma iScience 2024 27 111493 10.1016/j.isci.2024.111493 39759026 PMC11699281 · DOI
- [9]Ayers J.W. Poliak A. Dredze M. Leas E.C. Zhu Z. Kelley J.B. Faix D.J. Goodman A.M. Longhurst C.A. Hogarth M. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum JAMA Intern. Med. 2023 183 589 596 10.1001/jamainternmed.2023.1838 37115527 PMC10148230 · DOI · Paper page
- [10]Guo S. Li G. Gou J. Gong Y. Zhao W. Li Z. Yang X. Liu Z. Li Z. Lei J. The Performance of ChatGPT-4.0 and ChatGPT-4omni on Answering Thyroid Question: A Multicenter Study J. Surg. Res. 2025 313 500 508 10.1016/j.jss.2025.06.066 40706228 · DOI
- [11]Nasra M. Jaffri R. Pavlin-Premrl D. Kok H.K. Khabaza A. Barras C. Slater L.A. Yazdabadi A. Moore J. Russell J. Can artificial intelligence improve patient educational material readability? A systematic review and narrative synthesis Intern. Med. J. 2025 55 20 34 10.1111/imj.16607 39720869 · DOI
- [12]Umapathy V.R. Rajinikanth B S. Raj R.D.S. Yadav S. Munavarah S.A. Anandapandian P.A. Mary A.V. Padmavathy K. R A. Perspective of Artificial Intelligence in Disease Diagnosis: A Review of Current and Future Endeavours in the Medical Field Cureus 2023 15 e45684 10.7759/cureus.45684 37868519 PMC10590060 · DOI
- [13]Chatziisaak D. Burri P. Sparn M. Hahnloser D. Steffen T. Bischofberger S. Concordance of ChatGPT artificial intelligence decision-making in colorectal cancer multidisciplinary meetings: Retrospective study BJS Open 2025 9 zraf040 10.1093/bjsopen/zraf040 40331891 PMC12056934 · DOI
- [14]Holden C.A. Poprawski D. Singhal N. Buckley E. Caruso J. Wichmann M.W. Price T. A systematic scoping review of determinants of multidisciplinary cancer team access and decision-making in the management of older patients diagnosed with colorectal cancer J. Geriatr. Oncol. 2020 11 909 916 10.1016/j.jgo.2019.11.002 31734077 · DOI
- [15]Ebner F. Hartkopf A. Veselinovic K. Schochter F. Janni W. Lukac S. Dayan D. A Comparison of ChatGPT and Multidisciplinary Team Meeting Treatment Recommendations in 10 Consecutive Cervical Cancer Patients Cureus 2024 16 e67458 10.7759/cureus.67458 39310414 PMC11415775 · DOI
- [17]Levin G. Gotlieb W. Ramirez P. Meyer R. Brezinov Y. ChatGPT in a gynaecologic oncology multidisciplinary team tumour board: A feasibility study Bjog 2025 132 99 101 10.1111/1471-0528.17929 39140200 PMC11612612 · DOI
- [18]Gungor N.D. Esen F.S. Tasci T. Gungor K. Cil K. Navigating Gynecological Oncology with Different Versions of ChatGPT: A Transformative Breakthrough or the Next Black Box Challenge? Oncol. Res. Treat. 2024 48 102 111 10.1159/000543173 39689699 · DOI
- [19]Rosati A. Criscione M. Oliva R. Scambia G. Fagotti A. The Role Of AI Language Models As A Clinical Decision Support System (CDSS) Or Consultation Service Platform (CSP) In Gynecologic Oncology: A Systematic Review Of The Literature Int. J. Gynecol. Cancer 2025 35 100963 10.1016/j.ijgc.2024.100963 · DOI
- [20]Aikemu B. Xue P. Hong H. Jia H. Wang C. Li S. Huang L. Ding X. Zhang H. Cai G. Artificial Intelligence in Decision-Making for Colorectal Cancer Treatment Strategy: An Observational Study of Implementing Watson for Oncology in a 250-Case Cohort Front. Oncol. 2020 10 594182 10.3389/fonc.2020.594182 33628729 PMC7899045 · DOI
- [21]Ammo T. Guillaume V.G.J. Hofmann U.K. Ulmer N.M. Buenting N. Laenger F. Beier J.P. Leypold T. Evaluating ChatGPT-4o as a decision support tool in multidisciplinary sarcoma tumor boards: Heterogeneous performance across various specialties Front. Oncol. 2025 14 1526288 10.3389/fonc.2024.1526288 39896191 PMC11782276 · DOI
- [22]Khassan T. Smitten E. Wood N. Fotopoulou C. Morrison J. MacDonald M. Baxter K. Edmondson R.J. MDT practice determines treatment pathway for patients with advanced ovarian cancer: A multi-centre observational study Eur. J. Surg. Oncol. 2023 49 1504 1510 10.1016/j.ejso.2023.03.210 36958949 · DOI
- [23]Liu P. Zhang J. Chen S. Chen S. Human-AI teaming in healthcare: 1 + 1 > 2? npj Artif. Intell. 2025 1 47 10.1038/s44387-025-00052-4 · DOI
- [24]Jiang Y. Chen J. Li Z. Liu L. Clarkson P.J. AI-Augmented Co-Design in Healthcare: Log-Based Markers of Teamwork Behaviors and Collective Intelligence Outcomes Behav. Sci. 2025 15 1704 10.3390/bs15121704 41464047 PMC12729299 · DOI
Cited by
Sorted by citations
Asoglu, H., Kose, S., Kayim, O., Abaci, A., Khatib, G., Vardar, M. A., Kilic Bagir, E., Gumurdulu, D., Kidi, M. M., Bayram, E., et al. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15124451 · Cited by 1 · see citing works
“Most recently, Pergialiotis et al. evaluated ChatGPT-5 against MDT decisions in 599 gynecologic cancer cases, reporting high overall concordance but recurrent discrepancies in advanced and recurrent disease, with staging disagreements predominating [15].”
Influential
- Authors
- Pergialiotis, V., Thomakos, N., Lygizos, V., Fanaki, M., Varthaliti, A., Vlachos, D. E., & Haidopoulos, D.
- Affiliations
- National and Kapodistrian University of Athens (GR)
- First Department of Obstetrics and Gynecology, Division of Gynecologic Oncology, National and Kapodistrian University of Athens, 115 27 Athens, Greece
- Corresponding author
- Pergialiotis, Vasilios
- ORCID
- Venue
- Cancers
- Publisher
- MDPI AG
- Published
- 2026-01-30
- Volume
- 18
- Issue
- 3
- Pages
- 452
- ISSN
- 2072-6694 (ISSN-L)
- PMC
- PMC12897028
- OpenAlex
- W7126268745
- Cited by
- 5
- References
- 2
- Citations by year
- 2026: 5
- FWCI
- 9.83
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Cancers (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by)
- Funders
- National and Kapodistrian University of Athens
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- artificial intelligence, ChatGPT, multidisciplinary tumor board, gynecologic cancer, clinical decision support, FIGO staging, endometrial cancer, cervical cancer, ovarian cancer, vulvar cancer, large language models, concordance, molecular classification, chemotherapy, targeted therapy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
