{"title":"Predicting breast cancer pathological complete response with clinical and imaging data.","authors":"Xinlong Tao, Yongxin Li, Yinyin Ye, Xiao Liang, Xingchang Qiu, Jiuda Zhao","doi":"10.1080/14796694.2026.2706356","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Pathological complete response (pCR) is a key prognostic indicator in breast cancer (BC) patients receiving neoadjuvant chemotherapy (NAC). Unimodal prediction models are limited, underscoring the need for multimodal machine learning approaches.</p><p><strong>Methods: </strong>This retrospective study included 211 BC patients. A radiomics score (Radscore) was developed from multiparametric MRI, and integrated with clinical predictors using machine learning to build three models: clinical, radiomics, and a combined clinical-radiomics model. Their performance was systematically compared.</p><p><strong>Results: </strong>The combined clinical-radiomics model significantly outperformed unimodal models, with an AUC of 0.937 in the training cohort and 0.853 in the validation cohort. Decision curve and calibration analyses suggested potential clinical utility and accuracy.</p><p><strong>Conclusion: </strong>The clinical-radiomics model accurately predicts pCR to NAC in BC, surpassing unimodal methods. Its dynamic nomogram aids in personalizing treatment decisions.</p>","PeriodicalId":12672,"journal":{"name":"Future oncology","volume":" ","pages":"2261-2270"},"PeriodicalIF":3.1000,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13540178/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Future oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/14796694.2026.2706356","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/7/18 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Introduction: Pathological complete response (pCR) is a key prognostic indicator in breast cancer (BC) patients receiving neoadjuvant chemotherapy (NAC). Unimodal prediction models are limited, underscoring the need for multimodal machine learning approaches.
Methods: This retrospective study included 211 BC patients. A radiomics score (Radscore) was developed from multiparametric MRI, and integrated with clinical predictors using machine learning to build three models: clinical, radiomics, and a combined clinical-radiomics model. Their performance was systematically compared.
Results: The combined clinical-radiomics model significantly outperformed unimodal models, with an AUC of 0.937 in the training cohort and 0.853 in the validation cohort. Decision curve and calibration analyses suggested potential clinical utility and accuracy.
Conclusion: The clinical-radiomics model accurately predicts pCR to NAC in BC, surpassing unimodal methods. Its dynamic nomogram aids in personalizing treatment decisions.
期刊介绍：
Future Oncology (ISSN 1479-6694) provides a forum for a new era of cancer care. The journal focuses on the most important advances and highlights their relevance in the clinical setting. Furthermore, Future Oncology delivers essential information in concise, at-a-glance article formats - vital in delivering information to an increasingly time-constrained community.
The journal takes a forward-looking stance toward the scientific and clinical issues, together with the economic and policy issues that confront us in this new era of cancer care. The journal includes literature awareness such as the latest developments in radiotherapy and immunotherapy, concise commentary and analysis, and full review articles all of which provide key findings, translational to the clinical setting.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
