{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T06:15:01Z","timestamp":1783318501566,"version":"3.54.6"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Breast cancer chemotherapy decision-making remains challenging due to biological heterogeneity and variability in clinical practice. This study proposes a hybrid framework integrating machine learning (ML), causal reasoning, and large language models (LLMs) to improve treatment recommendations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the METABRIC dataset, eleven pre-treatment clinicopathologic variables were selected. A Random Forest classifier was developed and compared with baseline ML models. Individualized treatment benefit was estimated through inverse probability-weighted causal survival analysis, while GPT-4 was employed using few-shot prompting to generate clinical rationales.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The Random Forest achieved an AUC of 0.91, outperforming benchmark models. Causal analysis identified heterogeneous treatment benefits and patient groups where chemotherapy could potentially be deprioritized. GPT-4 showed moderate agreement with the Random Forest (Cohen's \u03ba\u2009=\u20090.13) while consistently highlighting clinically relevant factors. Uplift-based ML policies outperformed treat-all and treat-none strategies, and GPT-4 improved interpretability through rationale-driven explanations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>By combining predictive ML, causal survival modeling, and LLM-based rationale generation, the proposed framework provides a promising approach for personalized and transparent chemotherapy decision support in oncology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1738346","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:40Z","timestamp":1783316200000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning for chemotherapy decision-making in breast cancer using large language model"],"prefix":"10.3389","volume":"8","author":[{"given":"Md Serajun","family":"Nabi","sequence":"first","affiliation":[{"name":"Faculty of Artificial Intelligence and Engineering, Multimedia University","place":["Cyberjaya, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dema","family":"Yuden","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, Albukhary International University","place":["Alor Setar, Kedah, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thinley Yeshey","family":"Choden","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, Albukhary International University","place":["Alor Setar, Kedah, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. M.","family":"Asiful Islam Saky","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, Albukhary International University","place":["Alor Setar, Kedah, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hasanul","family":"Bannah","sequence":"additional","affiliation":[{"name":"Faculty of Artificial Intelligence and Engineering, Multimedia University","place":["Cyberjaya, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Sabbir","family":"Hossen","sequence":"additional","affiliation":[{"name":"Faculty of Artificial Intelligence and Engineering, Multimedia University","place":["Cyberjaya, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Faizal Ahmad","family":"Fauzi","sequence":"additional","affiliation":[{"name":"Faculty of Artificial Intelligence and Engineering, Multimedia University","place":["Cyberjaya, Malaysia"]},{"name":"School of Digital Health, KPJU Healthcare University","place":["Nilai, Negeri Sembilan, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hezerul Bin Abdul","family":"Karim","sequence":"additional","affiliation":[{"name":"Faculty of Artificial Intelligence and Engineering, Multimedia University","place":["Cyberjaya, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"102793","DOI":"10.1016\/j.amsu.2021.102793","article-title":"Breast cancer resistance to chemotherapy: when should we suspect it and how can we prevent it?","volume":"70","author":"Faruk","year":"2021","journal-title":"Ann Med Surg"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1053125","DOI":"10.3389\/fonc.2023.1053125","article-title":"Expression changes of ER, PR, HER2, and Ki-67 in primary and metastatic breast cancer and its clinical significance","volume":"13","author":"Hu","year":"2023","journal-title":"Front Oncol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.3390\/diagnostics16091295","article-title":"AI-driven breast cancer nuclei segmentation, classification, and scoring in PR-IHC images","volume":"16","author":"Bannah","year":"2026","journal-title":"Diagnostics"},{"key":"B4","doi-asserted-by":"publisher","first-page":"101700","DOI":"10.1016\/j.imu.2025.101700","article-title":"Explainable deep learning models for HER2 IHC scoring in breast cancer diagnosis","volume":"58","author":"Nabi","year":"","journal-title":"Inf Med Unlock"},{"key":"B5","author":"Nabi","year":""},{"key":"B6","author":"Nabi","year":""},{"key":"B7","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1016\/j.gendis.2020.12.005","article-title":"Role of hormone receptors and HER2 as prospective molecular markers for breast cancer: an update","volume":"9","author":"Mohanty","year":"2022","journal-title":"Genes Dis"},{"key":"B8","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1186\/s40001-023-01361-7","article-title":"Development and testing of a random forest-based machine learning model for predicting events among breast cancer patients with a poor response to neoadjuvant chemotherapy","volume":"28","author":"Jin","year":"2023","journal-title":"Eur J Med Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"110247","DOI":"10.1016\/j.ejrad.2022.110247","article-title":"Machine learning with magnetic resonance imaging for prediction of response to neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis","volume":"150","author":"Liang","year":"2022","journal-title":"Eur J Radiol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/s43681-022-00141-z","article-title":"Explainable machine learning practices: opening another black box for reliable medical AI","volume":"2","author":"Ratti","year":"2022","journal-title":"AI Ethics"},{"key":"B11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B12","doi-asserted-by":"crossref","first-page":"22199","DOI":"10.52202\/068431-1613","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"B13","author":"Nori","year":""},{"key":"B14","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"B15","doi-asserted-by":"crossref","first-page":"11809","DOI":"10.52202\/075280-0517","article-title":"Tree of thoughts: deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"B16","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/j.surg.2023.12.014","article-title":"Evaluating capabilities of large language models: performance of GPT-4 on surgical knowledge assessments","volume":"175","author":"Beaulieu-Jones","year":"2024","journal-title":"Surgery"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e2343689","DOI":"10.1001\/jamanetworkopen.2023.43689","article-title":"Leveraging large language models for decision support in personalized oncology","volume":"6","author":"Benary","year":"2023","journal-title":"JAMA Netw Open"},{"key":"B18","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"B19","author":"Ferber","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"8236","DOI":"10.1038\/s41467-024-52415-1","article-title":"Evaluating the use of large language models to provide clinical recommendations in the emergency department","volume":"15","author":"Williams","year":"2024","journal-title":"Nat Commun"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.5644\/ama2006-124.239","article-title":"Prospective validation of a genomic assay in breast cancer: the 70-gene MammaPrint assay and the MINDACT trial","volume":"48","author":"Audeh","year":"2019","journal-title":"Acta Med Acad"},{"key":"B22","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1016\/S1470-2045(21)00007-3","article-title":"70-gene signature as an aid for treatment decisions in early breast cancer: updated results of the phase 3 randomised MINDACT trial with an exploratory analysis by age","volume":"22","author":"Piccart","year":"2021","journal-title":"Lancet Oncol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1056\/NEJMoa1804710","article-title":"Adjuvant chemotherapy guided by a 21-gene expression assay in breast cancer","volume":"379","author":"Sparano","year":"2018","journal-title":"N Engl J Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.breast.2021.04.011","article-title":"Towards population-based genetic screenings for breast and ovarian cancer: a comprehensive review from economic evaluations to patient perspectives","volume":"58","author":"Ficarazzi","year":"2021","journal-title":"Breast"},{"key":"B25","article-title":"Deep learning-based approaches using medical imaging for therapy response prediction in breast cancer: a systematic literature review","volume":"20","author":"El Jiani","year":"2024","journal-title":"Int J Online Biomed Eng"},{"key":"B26","doi-asserted-by":"publisher","first-page":"111538","DOI":"10.1016\/j.jclinepi.2024.111538","article-title":"Machine learning approaches to evaluate heterogeneous treatment effects in randomized controlled trials: a scoping review","volume":"176","author":"Inoue","year":"2024","journal-title":"J Clin Epidemiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2634","DOI":"10.1038\/s41598-024-52976-7","article-title":"Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation","volume":"14","author":"Sato","year":"2024","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","first-page":"4554","DOI":"10.1002\/sim.9525","article-title":"Targeted maximum likelihood estimation of causal effects with interference: a simulation study","volume":"41","author":"Zivich","year":"2022","journal-title":"Stat Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"J Am Stat Assoc"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e70011","DOI":"10.1002\/mpr.70011","article-title":"Application of causal forest model to examine treatment effect heterogeneity in substance use disorder psychosocial treatments","volume":"34","author":"Susukida","year":"2025","journal-title":"Int J Methods Psychiatr Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1038\/nature10983","article-title":"The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups","volume":"486","author":"Curtis","year":"2012","journal-title":"Nature"},{"key":"B32","doi-asserted-by":"publisher","first-page":"4192","DOI":"10.1200\/JCO.22.02511","article-title":"Supervised risk predictor of breast cancer based on intrinsic subtypes","volume":"41","author":"Parker","year":"2023","journal-title":"J Clin Oncol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.1073\/pnas.1804597116","article-title":"Metalearners for estimating heterogeneous treatment effects using machine learning","volume":"116","author":"K\u00fcnzel","year":"2019","journal-title":"Proc Natl Acad Sci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3083","DOI":"10.1002\/sim.3697","article-title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples","volume":"28","author":"Austin","year":"2009","journal-title":"Stat Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1080\/01621459.2020.1713792","article-title":"Regression models and multivariate life tables","volume":"116","author":"Prentice","year":"2021","journal-title":"J Am Stat Assoc"},{"key":"B36","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1093\/ajcp\/aqw045","article-title":"Biomarkers predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer","volume":"145","author":"Li","year":"2016","journal-title":"Am J Clin Pathol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.3390\/cancers16244163","article-title":"ChatGPT\u2019s agreement with the recommendations from the 18th St. Gallen international consensus conference on the treatment of early breast cancer","volume":"16","author":"Nabieva","year":"2024","journal-title":"Cancers"},{"key":"B38","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.3390\/curroncol31070284","article-title":"Quality of ChatGPT-generated therapy recommendations for breast cancer treatment in gynecology","volume":"31","author":"Stalp","year":"2024","journal-title":"Curr Oncol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/s10488-023-01303-9","article-title":"A tutorial introduction to heterogeneous treatment effect estimation with meta-learners","volume":"51","author":"Salditt","year":"2024","journal-title":"Adm Policy Ment Health Ment Health Serv Res"},{"key":"B40","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/s00432-024-05964-3","article-title":"Proof-of-concept study of a small language model chatbot for breast cancer decision support\u2014a transparent, source-controlled, explainable and data-secure approach","volume":"150","author":"Griewing","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"key":"B41","author":"Evit\u00e2n","year":""},{"key":"B42","first-page":"1","article-title":"A review of random forest-based feature selection methods for data science education and applications","author":"Iranzad","year":"2024","journal-title":"Int J Data Sci Anal"},{"key":"B43","author":"Kwon","year":""},{"key":"B44","author":"Schroeder","year":""},{"key":"B45","article-title":"Evaluation of ChatGPT-4\u2019s performance in therapeutic decision-making during multidisciplinary oncology meetings for head and neck squamous cell carcinoma","volume":"16","author":"Alami","year":"2024","journal-title":"Cureus"},{"key":"B46","doi-asserted-by":"publisher","first-page":"3793","DOI":"10.1007\/s12094-025-03905-1","article-title":"Assessing the accuracy of the GPT-4 model in multidisciplinary tumor board decision prediction","volume":"27","author":"Erdat","year":"2025","journal-title":"Clin Transl Oncol"},{"key":"B47","doi-asserted-by":"publisher","first-page":"3535","DOI":"10.3390\/jcm14103535","article-title":"The role of artificial intelligence (ChatGPT-4o) in supporting tumor board decisions","volume":"14","author":"Karabu\u011fa","year":"2025","journal-title":"J Clin Med"},{"key":"B48","doi-asserted-by":"publisher","first-page":"oyaf293","DOI":"10.1093\/oncolo\/oyaf293","article-title":"Large language model processing capabilities of ChatGPT 4.0 to generate molecular tumor board recommendations\u2014a critical evaluation on real world data","volume":"30","author":"Schmutz","year":"2025","journal-title":"Oncologist"},{"key":"B49","first-page":"9029196","article-title":"Exploring the utility of ChatGPT-4o and DeepSeek-R1 for multidisciplinary uro-oncology tumor boards: a tumor type\u2013specific analysis","volume":"2025","author":"Cakir","year":"2025","journal-title":"Eur J Cancer Care (Engl)"},{"key":"B50","author":"Kenaston","year":""},{"key":"B51","doi-asserted-by":"publisher","first-page":"155002","DOI":"10.1088\/1361-6560\/adf02c","article-title":"Automated radiotherapy treatment planning guided by GPT-4Vision","volume":"70","author":"Liu","year":"2025","journal-title":"Phys Med Biol"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1738346\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:41Z","timestamp":1783316201000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1738346\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":51,"alternative-id":["10.3389\/fdgth.2026.1738346"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1738346","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"1738346"}}