{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:20:29Z","timestamp":1791937229656,"version":"4.3.4"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Hormone receptor (HR)-positive, human epidermal growth factor receptor 2 (HER2)-negative breast cancer is the most prevalent subtype among women but has a modest response to neoadjuvant chemotherapy (NAC). Accurately predicting NAC efficacy and recurrence risk remains challenging, as conventional clinical and molecular markers have limited predictive power. Advances in digital pathology and artificial intelligence now enable quantitative pathomics analysis, offering new opportunities for precise prediction and prognostic assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective study, 162 HR-positive, HER2-negative breast cancer patients treated with NAC between 2014 and 2021 were included. Hematoxylin and eosin (H&amp;amp;E)-stained pretreatment biopsy slides were digitized and analyzed using Vision Transformer (ViT) and Unified Network for Image (UNI) deep learning models to extract pathomic features. Thirteen clinical variables were collected. After least absolute shrinkage and selection operator (LASSO)-based feature selection, multiple machine learning models were developed for both response prediction and prognostic evaluation of recurrence, with performance evaluated by receiver operating characteristic (ROC) curves, area under the curve (AUC), sensitivity, specificity, confusion matrix, calibration curves, and decision curve analysis (DCA). Furthermore, SHapley Additive exPlanations (SHAP) was used to rank the importance of features for each model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The CatBoost model achieved the best predictive performance (AUC = 0.900 in training and 0.848 in validation) when a combination of clinical and pathomics-derived variables was used. Key predictive factors included Ki-67 expression, age, histological grade, PR status, and prominent pathomic features. A Kaplan\u2013Meier survival plot indicated that regardless of stratification by MP grade or pCR status, there was no significant difference in recurrence status or survival outcomes between the two groups in this cohort. Furthermore, the recurrence models developed mainly using pathomics were strongly accurate for predicting 1-year recurrence (AUC = 0.907 in training and 0.769 in validation).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Integrating pathomic features with clinical variables via machine learning enables robust pretreatment prediction of NAC efficacy and short-term recurrence in HR-positive, HER2-negative breast cancer. This approach has the potential to offer a clinically practical tool to optimize individualized therapy and improve patient management, highlighting the translational value of AI-powered digital pathology in breast cancer care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1770037","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T05:27:46Z","timestamp":1771824466000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Development and validation of a pathomics-driven machine learning model for individualized prediction of neoadjuvant chemotherapy response and early recurrence in HR-positive, HER2-negative breast cancer"],"prefix":"10.3389","volume":"16","author":[{"given":"Jiaxian","family":"Yue","sequence":"first","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University","place":["Beijing, China"]},{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyu","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Pathology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Thorough Lab, Thorough Future","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Shang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyao","family":"Shang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xubin","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongmin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Thorough Lab, Thorough Future","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Ying","sequence":"additional","affiliation":[{"name":"Department of Pathology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgical Oncology, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3322\/caac.21871","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA A Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21863","article-title":"Breast cancer statistics 2024","volume":"74","author":"Giaquinto","year":"2024","journal-title":"CA A Cancer J Clin"},{"key":"B3","doi-asserted-by":"publisher","first-page":"480","DOI":"10.3322\/caac.21777","article-title":"Systemic therapy for hormone receptor-positive\/human epidermal growth factor receptor 2-negative early stage and metastatic breast cancer","volume":"73","author":"Huppert","year":"2023","journal-title":"CA A Cancer J Clin"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdz201","article-title":"The ESMO clinical practise guidelines for early breast cancer: diagnosis, treatment and follow-up: on the winding road to personalized medicine","volume":"30","author":"Loi","year":"2019","journal-title":"Ann Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdx308","article-title":"De-escalating and escalating treatments for early-stage breast cancer: the St. Gallen International Expert Consensus Conference on the Primary Therapy of Early Breast Cancer 2017","volume":"28","author":"Curigliano","year":"2017","journal-title":"Ann Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.24876","article-title":"Immunohistochemical surrogate markers of breast cancer molecular classes predicts response to neoadjuvant chemotherapy: A single institutional experience with 359 cases","volume":"116","author":"Bhargava","year":"2010","journal-title":"Cancer"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-011-1488-0","article-title":"Neoadjuvant chemotherapy in ER+ HER2\u2013 breast cancer: response prediction based on immunohistochemical and molecular characteristics","volume":"131","author":"Lips","year":"2012","journal-title":"Breast Cancer Res Treat"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1186\/s13058-025-01960-8","article-title":"Prediction of pathological complete response after neoadjuvant chemotherapy for HER2-negative breast cancer patients with routine immunohistochemical markers","volume":"27","author":"H\u00e4berle","year":"2025","journal-title":"Breast Cancer Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s41523-025-00727-w","article-title":"Accessible model predicts response in hormone receptor positive HER2 negative breast cancer receiving neoadjuvant chemotherapy","volume":"11","author":"Mastrantoni","year":"2025","journal-title":"NPJ Breast Cancer"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(13)62422-8","article-title":"Pathological complete response and long-term clinical benefit in breast cancer: the CTNeoBC pooled analysis","volume":"384","author":"Cortazar","year":"2014","journal-title":"Lancet"},{"key":"B11","doi-asserted-by":"publisher","first-page":"e066381","DOI":"10.1136\/bmj-2021-066381","article-title":"Evaluation of pathological complete response as surrogate endpoint in neoadjuvant randomised clinical trials of early stage breast cancer: systematic review and meta-analysis","volume":"375","author":"Conforti","year":"2021","journal-title":"BMJ"},{"key":"B12","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13058-023-01752-y","article-title":"Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer","volume":"26","author":"Fisher","year":"2024","journal-title":"Breast Cancer Res"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.7150\/thno.49864","article-title":"Development and interpretation of a pathomics-based model for the prediction of microsatellite instability in Colorectal Cancer","volume":"10","author":"Cao","year":"2020","journal-title":"Theranostics"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.6437","article-title":"6.Identification of lymph node metastasis in pre-operation cervical cancer patients by weakly supervised deep learning from histopathological whole-slide biopsy images","volume":"12","author":"Liu","year":"2023","journal-title":"Cancer Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103311","article-title":"Evaluating axillary lymph node metastasis risks in breast cancer patients via Semi-ALNP: a multicenter study","volume":"85","author":"Qu","year":"2025","journal-title":"eClinicalMedicine"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.5114\/aoms\/188006","article-title":"Development and validation of a pathological model predicting the efficacy of neoadjuvant therapy for breast cancer based on RCB scoring","volume":"21","author":"Li","year":"2024","journal-title":"Arch Med Sci"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/S0960-9776(03)00106-1","article-title":"A new histological grading system to assess response of breast cancers to primary chemotherapy: prognostic significance and survival","volume":"12","author":"Ogston","year":"2003","journal-title":"Breast"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-3190","article-title":"Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer: A multicenter study","volume":"25","author":"Liu","year":"2019","journal-title":"Clin Can-cer Res"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1539644","article-title":"Using baseline MRI radiomics to predict the tumor shrinkage patterns in HR-Positive, HER2-Negative Breast Cancer","volume":"15","author":"Wang","year":"2025","journal-title":"Front Oncol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-018-4801-3","article-title":"Response rates and pathologic complete response by breast cancer molecular subtype following neoadjuvant chemotherapy","volume":"170","author":"Haque","year":"2018","journal-title":"Breast Cancer Res Treat"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2021.103280","article-title":"Neoadjuvant chemotherapy in hormone receptor-positive\/HER2-negative early breast cancer: When, why and what","volume":"160","author":"Torrisi","year":"2021","journal-title":"Crit Rev Oncol\/Hematol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2020.12.016","article-title":"Reconstructing tumor history in breast cancer: signatures of mutational processes and response to neoadjuvant chemotherapy\u2606","volume":"32","author":"Denkert","year":"2021","journal-title":"Ann Oncol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctrv.2023.102669","article-title":"Neoadjuvant therapy in hormone Receptor-Positive\/HER2-Negative breast cancer","volume":"123","author":"Cantini","year":"2024","journal-title":"Cancer Treat Rev"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2021.12.019","article-title":"Neoadjuvant approach in patients with early breast cancer: patient assessment, staging, and planning","volume":"62","author":"Rubio","year":"2022","journal-title":"Breast"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-010-1008-1","article-title":"The relevance of breast cancer subtypes in the outcome of neoadjuvant chemotherapy","volume":"17","author":"Straver","year":"2010","journal-title":"Ann Surg Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000000924","article-title":"Tumor biology correlates with rates of breast-conserving surgery and pathologic complete response after neoadjuvant chemotherapy for breast cancer: findings from the ACOSOG Z1071 (Alliance) prospective multicenter clinical trial","volume":"260","author":"Boughey","year":"2014","journal-title":"Ann Surg"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/jso.24721","article-title":"Impact of neoadjuvant chemotherapy on surgical outcomes among patients with hormone receptor positive breast cancer","volume":"116","author":"Hage","year":"2017","journal-title":"J Surg Oncol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-017-5898-z","article-title":"Standard pathologic features can be used to identify a subset of estrogen receptor-positive, HER2 negative patients likely to benefit from neoadjuvant chemotherapy","volume":"24","author":"Petruolo","year":"2017","journal-title":"Ann Surg Oncol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"412","DOI":"10.4048\/jbc.2019.22.e35","article-title":"Potential benefits of neoadjuvant chemotherapy in clinically node-positive luminal subtype\u2013 breast cancer","volume":"22","author":"Kim","year":"2019","journal-title":"J Breast Cancer"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2022.834","article-title":"Androgen receptor as a predictive marker for pathologic complete response in hormone receptor\u2013positive and HER-2\u2013negative breast cancer with neoadjuvant chemotherapy","volume":"55","author":"Lee","year":"2023","journal-title":"Cancer Res Treat"},{"key":"B31","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1186\/s12885-023-10817-2","article-title":"Development and validation of a radiopathomic model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer patients","volume":"23","author":"Zhang","year":"2023","journal-title":"BMC Cancer"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/s40537-020-00369-8","article-title":"CatBoost for big data: an interdisciplinary review","volume":"7","author":"Hancock","year":"2020","journal-title":"J Big Data"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109504","article-title":"Artificial intelligence for identification of candidates for device-aided therapy in Parkinson\u2019s disease: DELIST-PD study","volume":"185","author":"Freire-\u00c1lvarez","year":"2025","journal-title":"Comput Biol Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijsu.2022.106638","article-title":"Machine learning algorithms as early diagnostic tools for pancreatic fistula following pancreaticoduodenectomy and guide drain removal: A retrospective cohort study","volume":"102","author":"Shen","year":"2022","journal-title":"Int J Surg"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2024.103858","article-title":"Novel models based on machine learning to predict the prognosis of metaplastic breast cancer","volume":"79","author":"Zhang","year":"2025","journal-title":"Breast"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.35425","article-title":"Long-term efficacy of neoadjuvant\u2013adjuvant targeted therapy in borderline resectable stage IIIB\u2013D and IV melanoma","volume":"130","author":"Czarnecka","year":"2024","journal-title":"Cancer"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djae034","article-title":"Neoadjuvant platinum-based chemotherapy and lymphadenectomy for penile cancer: an international, multi-institutional, real-world study","volume":"116","author":"Rose","year":"2024","journal-title":"JNCI: J Natl Cancer Inst"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2021.05.027","article-title":"Utility of the CPS + EG scoring system in triple-negative breast cancer treated with neoadjuvant chemotherapy","volume":"153","author":"Marm\u00e9","year":"2021","journal-title":"Eur J Cancer"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.06.014","article-title":"Meta-analysis confirms achieving pathological complete response after neoadjuvant chemotherapy predicts favourable prognosis for breast cancer patients","volume":"47","author":"Kong","year":"2011","journal-title":"Eur J Cancer"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2020.11.053","article-title":"Neoadjuvant chemotherapy for luminal a breast cancer: Factors predictive of histopathologic response and oncologic outcome","volume":"222","author":"Collins","year":"2021","journal-title":"Am J Surg"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.clbc.2017.09.013","article-title":"The prognostic effect of changes in tumor stage and nodal status after neoadjuvant chemotherapy in each primary breast cancer subtype","volume":"18","author":"Hayashi","year":"2018","journal-title":"Clin Breast Cancer"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103456","article-title":"When multiple instance learning meets foundation models: Advancing histological whole slide image analysis","volume":"101","author":"Xu","year":"2025","journal-title":"Med Img Anal"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1770037\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T05:27:47Z","timestamp":1771824467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1770037\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":43,"alternative-id":["10.3389\/fonc.2026.1770037"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1770037","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"article-number":"1770037"}}