The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Evaluating ChatGPT as an Adjunct for the Multidisciplinary Tumor Board Decision–Making in Primary Breast Cancer Cases
Open accessPublished version of a preprint
Abstract
BACKGROUND: As the available information about breast cancer is growing every day, the decision-making process for the therapy is getting more complex. ChatGPT as a transformer-based language model possesses the ability to write scientific articles and pass medical exams. But is it able to support the multidisciplinary tumor board (MDT) in the planning of the therapy of patients with breast cancer? MATERIAL AND METHODS: We performed a pilot study on 10 consecutive cases of breast cancer patients discussed in MDT at our department in January 2023. Included were patients with a primary diagnosis of early breast cancer. The recommendation of MDT was compared with the recommendation of the ChatGPT for particular patients and the clinical score of the agreement was calculated. RESULTS: Results showed that ChatGPT provided mostly general answers regarding chemotherapy, breast surgery, radiation therapy, chemotherapy, and antibody therapy. It was able to identify risk factors for hereditary breast cancer and point out the elderly patient indicated for chemotherapy to evaluate the cost/benefit effect. ChatGPT wrongly identified the patient with Her2 1 + and 2 + (FISH negative) as in need of therapy with an antibody and called endocrine therapy "hormonal treatment". CONCLUSIONS: Support of artificial intelligence by finding individualized and personalized therapy for our patients in the time of rapidly expanding amount of information is looking for the ways in the clinical routine. ChatGPT has the potential to find its spot in clinical medicine, but the current version is not able to provide specific recommendations for the therapy of patients with primary breast cancer.
Overview
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
Figures
Verification
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?
In the citing paper
“In the realm of pharmaceutical research, ChatGPT can contribute by sifting through vast volumes of scientific literature, identifying potential drug candidates, and suggesting innovative research directions.”
In the citing paper
“It can assist in drug discovery, research proposal writing, and summarising complex medical research, expediting the research process [11,24,34,35,36,37,38].”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 2×
“Additionally, the ChatGPT can pass the United States Medical Licensing Exam [10].”
BackgroundInfluentialInternational evaluation of an AI system for breast cancer screening
McKinney, S. M., Sieniek, M., Godbole, V., Godwin, J., Antropova, N., Ashrafian, H., Back, T., Chesus, M., Corrado, G. S., Darzi, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1799-6 · Cited by 3,287 · cited 1×
“McKinney could prove that participation of AI in the double-reading process of mammography screening can reduce the workload of the second reader [13].”
BackgroundTrastuzumab Deruxtecan in Previously Treated HER2-Low Advanced Breast Cancer
Modi, S., Jacot, W., Yamashita, T., Sohn, J., Vidal, M. J., Tokunaga, E., Tsurutani, J., Ueno, N. T., Prat, A., Chae, Y. S., et al. (2022) · New England Journal of Medicine · doi:10.1056/nejmoa2203690 · Cited by 2,871 · cited 1×
“Various studies like the Destiny Breast 04 Study published beneficial data on Her2low BC treatment [24].”
Backgroundvon Minckwitz, G., Untch, M., Blohmer, J.-U., Costa, S. D., Eidtmann, H., Fasching, P. A., Gerber, B., Eiermann, W., Hilfrich, J., Huober, J., et al. (2012) · Journal of Clinical Oncology · doi:10.1200/jco.2011.38.8595 · Cited by 2,659 · cited 1×
“The German Breast Group could describe the differences in survival parameters in subtypes of breast cancer after neoadjuvant chemotherapy, whereby the pathological complete remission was a strong predictor of disease-free survival [21].”
BackgroundBreast Cancer Risk Genes — Association Analysis in More than 113,000 Women
Breast Cancer Association Consortium (2021) · New England Journal of Medicine · doi:10.1056/nejmoa1913948 · Cited by 1,181 · cited 1×
“Carriers of PALB2, BARD1, RAD51C, RAD51D, ATM, and CHEK2 are at higher risk of breast cancer as well [20].”
BackgroundGao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2022) · doi:10.1101/2022.12.23.521610 · Cited by 1,099 · cited 2×
“It possesses the ability to write high-quality scientific papers [8].”
BackgroundGao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00819-6 · Cited by 1,099
Rao, A. S., Kim, J., Kamineni, M., Pang, M., Lie, W., Dreyer, K. J., & Succi, M. D. (2023) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2023.05.003 · Cited by 509
Artificial intelligence-based multi-omics analysis fuels cancer precision medicine
He, X., Liu, X., Zuo, F., Shi, H., & Jing, J. (2022) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2022.12.009 · Cited by 494 · cited 1×
“1 3 support establishing a more precise medicine, particularly in the days when a huge amount of data is available[17, 18].”
Background
Research works printed but not linked: 1
- Lukac S, Friedl TWP, Leinert E (2023) Age of the patient as a prognosis and therapy-relevant factor in early breast cancer. University of Ulm, Ulm
Cited by
Sorted by citations
Items 101–130 of 130
From Evidence to Recommendations With Large Language Models: A Feasibility Study
Zhao, W., Xia, D., Ye, Z., Lai, H., Sun, M., Huang, J., Liu, J., Liu, J., & Ge, L. (2025) · Journal of Evidence-Based Medicine · doi:10.1111/jebm.70067 · Cited by 1
AI Clinical Decision Tools in Multidisciplinary Team Discussions for Colorectal Cancer
Horesh, N., Wignakumar, A., & Emile, S. H. (2025) · Clinics in Colon and Rectal Surgery · doi:10.1055/a-2769-1363 · Cited by 1
“Nonetheless, successful implementation hinges on careful management of identi fi ed risks and thorough consideration of medi-colegal and ethical dimensions, reinforcing AI as an adjunct to — not a replacement for — human clinical expertise.”
Tsujimoto, Y., Shiraishi, M., Yamanaka, H., Lee, H., Okazaki, M., & Morimoto, N. (2026) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2026.111391 · Cited by 1
Meixner, B. J., Tristram, C., Schranner, M., Kenner, A., Serwe-Pandrick, E., Sperlich, B., & Düking, P. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1765699 · Cited by 1
Tokoçn, M., Pehlivan, T., Cin, S., Toksöz, B., Tokoçin, O., Cingöz, E., Erkoç, N., Özen, A., Arıkan, N. S., Bedir, Ş., et al. (2026) · European Journal of Breast Health · doi:10.4274/ejbh.galenos.2026.2025-10-4 · Cited by 1
“The substantial agreement between ChatGPT-4 and human experts for primary treatments (weighted Cohen’s kappa = 0.712, p <0.001) reflects a remarkable alignment with St. Gallen, ESMO, NCCN, and ASCO guidelines in standard cases, and was similar to the findings reported by Lukac et al. (7).”
InfluentialElkefi, S., Scheinmann, R., Hao, D., Bhar, S., Tounsi, A., & Feiner, S. (2026) · BMC Artificial Intelligence · doi:10.1186/s44398-026-00024-x · Cited by 1
Sümbüllü, M., Adam, E. O., ALTUN, E. A., & Arslan, H. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08327-1 · Cited by 1
“Inaccurate or misleading responses may negatively impact treatment adherence, physician–patient communication, and overall trust in healthcare systems [17].”
Li, M., Yu, Y., Li, G., Zhang, X., Shi, Y., & Su, R. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1862730 · Cited by 1
“Many studies have explored the application of LLMs in breast cancer care, particularly in text generation and providing guideline-based responses (5, 6).”
Wu, F., Aseem, R., Armes, J., Rockall, T., Frampton, A. E., & Pakzad, F. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1804004 · Cited by 1
Alamrain, A. A., Adewunmi, M. A., Amrain, M. A. A., Wong, M. C., & Yee, K. C. (2023) · doi:10.2196/preprints.51444
Ye, Z., Lai, H., Sun, M., Huang, J., Liu, J., Xia, D., Zhao, W., Liu, J., & Ge, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4756038
Alamrain, A. A., Adewunmi, M. A., Amrain, M. A. A., Wong, M. C., & Yee, K. C. (2023) · JMIR Cancer · doi:10.2196/51444
Chatgpt-Assisted Decision-Making: An In-Depth Exploration of the Human-Ai InteractionPreprint
Mustata, M. A., Iliescu, D., Mavriș, E., Jude, C.-R., Bojor, L., Tudorache, P., Cîrdei, A., Hrab, D.-E., Covaci, B., Răpan, I., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4870176
Masur, L., Driller, M. W., Suppiah, H. T., Matzka, M., & Düking, P. (2025) · doi:10.2196/preprints.71358
Cakir, E., Bekçi, T., Aslan, S., Oǧuz, U., Öğreden, E., Demirelli, E., Tok, D. S., Tok, B., Yaslıkaya, Ş., Zorlu, Ş., et al. (2025) · European Journal of Cancer Care · doi:10.1155/ecc/9029196
“Similarly, Lukac et al. [5] reported ChatGPT’s utility as an adjunct in breast cancer tumor boards, noting its strength in providing guideline-based recommendations—a fnding consistent with our models’ performance in prostate cancer, where treatment pathways are well established.”
Idrees, M., Rahmeh, S., Ng, K., Blanco‐Colino, R., Mcallister, J., & Farid, S. G. (2025) · HPB · doi:10.1016/j.hpb.2025.12.032
Sun, M., Reiter, E., Murchie, P., Kiltie, A. E., Ramsay, G., Duncan, L., & Adam, R. (2026) · medRxiv · doi:10.64898/2026.02.02.26345346
Buonaiuto, R., Caltavituro, A., Rienzo, R. D., Grieco, A., Mangiacotti, F. P., Longobardi, A., Cantile, V., Molinaro, V., Pagliuca, M., Buono, G., et al. (2026) · JCO Clinical Cancer Informatics · doi:10.1200/cci-25-00230
“21,22 ChatGPT showed to provide appropriate breast cancer screening recommendations 23 and demonstrated substantial accuracy and reliability in answering questions raised by patients with breast cancer about surgical treatment.”
Navigating the utility of generative artificial intelligence in healthcare delivery
Kulkarni, M., Sheth, M., & Chaudhary, P. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45252-9.00015-3
Schmidl, B., Walter, R., Hoch, C. C., Hütten, T., Pigorsch, S. U., Stögbauer, F., Hussain, T., Wollenberg, B., & Wirth, M. (2026) · European Annals of Otorhinolaryngology Head and Neck Diseases · doi:10.1016/j.anorl.2026.02.012
Leveraging AI chatbots in supporting breast and ovarian cancer patients: A scoping review
Hui, V. C. C., Tian, L., Feng, X., Yuan, X., Yorke, J., & Lee, Y. J. (2026) · Digital Health · doi:10.1177/20552076261451390
“High concordance was demonstrated in genetic counseling applications 36,50 and screening assessments, 22 while treatment planning applications showed variable results with congruence rates ranging from 70% 42 to 16.05% 49 when compared with professional team recommendations.”
InfluentialStalp, J. L., Schneider, J. A., STEINKASSERER, L., Hachenberg, J., Jentschke, M., Hillemanns, P., Wolff, D., & Denecke, A. (2026) · Archives of Gynecology and Obstetrics · doi:10.1007/s00404-026-08498-w
Freudenberg, J., Knitza, J., Gremke, N., Amann, N., Deutsch, T. M., Tauber, N., Muras, K., Oftring, Z. S., Engler, T., Englisch, A., et al. (2026) · Journal of Medical Systems · doi:10.1007/s10916-026-02434-w · Cited by 1
Ammo, T., Englich, M., Adrego, F. D. S., Jacobi, M., Wilckens, A., Kruppa, P., Bonaventura, B., Niemuth, S. S., Weiler, S. M., Wachenfeld-Teschner, V., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-10035573/v1
The Rise of Generalist Foundation Models and Quantum Computing in Oncology
Kakar, M. (2026) · Technology in Cancer Research & Treatment · doi:10.1177/15330338261476208
“…for training, Large Language Models ( LLMs) 33 for communication with patient and clinicians, and digital twins reproducing individual’s unique characteristic, they are not mature and are prone to errors, bias, 18,34 misinformation, 35 inaccuracies and hallucinations, 36 ethical and legal concerns.”
Zhao, W., Chen, L., Pu, W., Liu, L., Tan, X., Li, S., Qiu, X., Fan, J., Zhu, M., & Wang, Z. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134108
Beyond one-size-fits-all: mapping information-seeking and decision-making pathways in cancer care
Levit, N. S., & Saban, M. (2026) · Supportive Care in Cancer · doi:10.1007/s00520-026-11250-4
Schmidl, B., Walter, R., Hoch, C. C., Hütten, T., Pigorsch, S. U., Stögbauer, F., Hussain, T., Wollenberg, B., & Wirth, M. (2026) · Annales françaises d Oto-rhino-laryngologie et de Pathologie Cervico-faciale · doi:10.1016/j.aforl.2026.08.001
Lombardo, R., Stagliano, M. G., Santioni, M., Pagliarulo, V., Gallo, G., Secco, S., Dell’Oglio, P., Antonio Galfano, A., Olivero, A., Cillis, S. D., et al. (2026) · International Urology and Nephrology · doi:10.1007/s11255-026-05389-6
Ammo, T., Englich, M., Adrego, F. D. S., Jacobi, M., Wilckens, A., Kruppa, P., Bonaventura, B., Niemuth, S., Weiler, S. M., Wachenfeld-Teschner, V., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-74868-8
“5 as an adjunct to the multidisciplinary tumor board in primary breast cancer, similarly described moderate, case-dependent performance and emphasized that LLMs are not yet reliable enough for autonomous tumor-board use 20 .”
Metadata
- Authors
- Lukac, S., Dayan, D., Fink, V., Leinert, E., Hartkopf, A., Veselinovic, K., Janni, W., Rack, B., Pfister, K., Heitmeir, B., & Ebner, F.
- Affiliations
- University Hospital Ulm (DE)
- Corresponding author
- Lukac, Stefan
- ORCID
- Venue
- Archives of Gynecology and Obstetrics
- Published
- 2023-07-17
- Volume
- 308
- Issue
- 6
- Pages
- 1831-1844
- ISSN
- 0003-9128 (ISSN-L)
- 1432-0711
- PMC
- PMC10579162
- OpenAlex
- W4384558920
- Cited by
- 130
- References
- 23
- Citations by year
- 2026: 32 · 2025: 44 · 2024: 45 · 2023: 9
- FWCI
- 5.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Archives of Gynecology and Obstetrics (publishedVersion, cc-by)
- Research Square (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Universitätsklinikum Ulm
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
- Keywords
- ChatGPT, large language models, multidisciplinary tumor board, primary breast cancer, early breast cancer, treatment decision-making, clinical implementation of AI, HER2-positive breast cancer, endocrine therapy, personalized treatment
- MeSH terms
- Aged, Antibodies, Artificial Intelligence, Breast Neoplasms, Female, Humans, Oncogenes, Pilot Projects
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
