Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 55 min ago
Peer-reviewedCC BY-NC-NDJournal of translational medicine

Interpretable machine learning model for brain metastasis in breast cancer: a large-scale, multi-center study.

  • Quan Yuan1
  • Yupeng Sha2
  • Rui Yu3
  • Hao Yu4
  • Rongjie Ye5
  • Yi Du6
  • Hanqing Deng7
  • Liqun Wang8
  • Zhihao Lei9
  • Kaizhou Chen10
  • Jian Cai10
  • Xiaoming Li2
31 more authors
  • Yixin Liu2
  • Yige Lu2
  • Hui Pang2
  • Shuiliang Wang11
  • Taozhu Ye3
  • Youzhuang Wu3
  • Xiaofeng Li12
  • Zhengda Chen5
  • Junjing Li5
  • Shuqi Yang13
  • Kangni Chen8
  • Qinpei Ke8
  • Yongxuan Yuan8
  • Lierui Chen8
  • Fan Wang8
  • Yuxin Cheng8
  • Boqian Yu2
  • Yuancong Jiang14
  • Pengfei He15
  • Kejie Zhang16
  • Fei Gao17
  • Zhichuan He18
  • Zhiyang Li19
  • Wenxin Chen20
  • Zheng Wang21
  • Chunhong Xiao22
  • Yonghui Su23
  • Naiqian Zhang24
  • Debo Chen25
  • Ming Niu26
  • Jiguang Han27
27 affiliations
  1. 1Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, 150000, China. [email protected].
  2. 2Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, 150000, China.
  3. 3Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, Fujian, 350025, China.
  4. 4The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, 361000, China.
  5. 5Department of Breast Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian, 362000, China.
  6. 6Nanyang Central Hospital, Nanyang, Henan, 473000, China.
  7. 7Department of Breast Surgery, Sanming First Hospital Affiliated to Fujian Medical University, Sanming, Fujian, 365001, China.
  8. 8Department of Thyroid, Breast and Hernia Surgery, General Surgery, The Second Affiliated Hospital of Shantou University Medical College, Shantou, Guangdong, 515000, China.
  9. 9Department of Statistics and Data Science, Cornell University, Ithaca, NY, USA.
  10. 10The First Hospital of Putian City, Putian, Fujian, 351100, China.
  11. 11Fujian Key Laboratory of Aptamers Technology, Affiliated Dongfang Hospital of School of Medicine (the 900th Hospital), Xiamen University, Fuzhou, Fujian, 350025, China.
  12. 12Department of Medical Oncology, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian, 362000, China.
  13. 13Department of Infection Disease, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian, 362000, China.
  14. 14Department of Breast and Thyroid Surgery, Shaoxing People's Hospital, Shaoxing, China.
  15. 15Department of Breast Surgery, Nanyang Second People's Hospital, Nanyang, Henan, 473000, China.
  16. 16Department of Breast Surgery, Peking University Shougang Hospital, Beijing, China.
  17. 17Daqing Oilfield General Hospital, Daqing, Heilongjiang, China.
  18. 18The First Hospital of Putian City, Putian, Fujian, 351100, China. [email protected].
  19. 19Department of Thyroid, Breast and Hernia Surgery, General Surgery, The Second Affiliated Hospital of Shantou University Medical College, Shantou, Guangdong, 515000, China. [email protected].
  20. 20Department of Breast Surgery, Sanming First Hospital Affiliated to Fujian Medical University, Sanming, Fujian, 365001, China. [email protected].
  21. 21Nanyang Central Hospital, Nanyang, Henan, 473000, China. [email protected].
  22. 22Department of General Surgery, The 900th Hospital of Joint Logistic Support Force, Fuzhou, Fujian, 350025, China. [email protected].
  23. 23The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, 361000, China. [email protected].
  24. 24Jilin Cancer Hospital, Changchun, Jilin Province, China. [email protected].
  25. 25Department of Breast Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian, 362000, China. [email protected].
  26. 26Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, 150000, China. [email protected].
  27. 27Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang, 150000, China. [email protected].
Read full textPDFDOICite

Abstract

Background

Brain metastasis (BM) is a devastating complication of breast cancer (BC) with a poor prognosis. Early identification of high-risk patients is essential but currently lacks accurate predictive tools. This study aimed to develop a stable machine learning model for predicting BM in a large, diverse patient population.Methods

We conducted a retrospective cohort study of 186,351 primary BC patients from the SEER program, the National Cancer Database, and a multi-center Chinese cohort. Patients were split into training and validation sets. Candidate predictors included demographic, clinicopathological, biomarker, and treatment-related variables, including surgery, chemotherapy, endocrine therapy, neoadjuvant therapy, and radiotherapy. LASSO regression was used for feature selection. Nine machine learning models were developed and compared using area under the curve (AUC) and decision curve analysis. The optimal model was deployed as an online tool.Results

Among 186,351 patients, 2,982 (1.6%) developed BM. In baseline comparisons, patients who developed BM more frequently exhibited advanced disease characteristics and different treatment patterns, likely reflecting more aggressive disease presentation. Key predictors retained in the final parsimonious model included AJCC N/M/T stage, age, and surgery status. The LASSO-regularized Logistic Regression model achieved superior discrimination in the validation set, with an AUC of 0.907 (95% CI: 0.857-0.958). The model demonstrated good calibration, clinical net benefit, and interpretability, with SHAP analysis confirming the contribution of each retained predictor to individual risk estimates. Survival analysis confirmed the poor prognosis associated with BM (p < 0.001). An interactive online tool was developed for real-time risk estimation.Conclusion

We developed and internally validated a accurate, clinically translatable model for predicting BM in BC using over 186,000 patients from North American and Asian cohorts. This web-based tool can assist clinicians in identifying high-risk individuals, enabling personalized management and potentially improving patient outcomes.

Related

  1. An interpretable machine-learning signature predicts early triple-negative breast cancer recurrence but adds no prognostic value beyond clinicopathological factors in external validation
    Haocheng Nan, Rong Di, Xiaorong Kou +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textOncologyCrossref
  2. Predicting lymph node metastasis in non-small cell lung cancer using clinical and PET/CT-derived morphological features: An interpretable machine-learning study
    Yunchao Xu, Jiajun Hao, Yujiao Dou +1
    PLOS OnePeer-reviewedCC BY 4.0Full textMedical imaging & radiologyOncologyPLOS
  3. Machine learning-based prediction of lymph node metastasis in papillary thyroid carcinoma: an interpretable multidimensional model
    Xiaoqing Yuan, Yahui Wu, Yixiang Xing +4
    Frontiers in endocrinologyPeer-reviewedCC BYFull textEndocrinology & metabolismEurope PMC
  4. An interpretable machine-learning model to predict moderate-to-severe acute radiation esophagitis following regional nodal irradiation for breast cancer.
    Bin He, Zhongchun Qi, Hengdi Zhang +6
    Oncology lettersPeer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaEurope PMCPMC
  5. Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
    S. Zhang, F. Xue
    medRxivPreprintAll rights reservedFull textEpidemiology & public healthmedRxiv

Cite

BibTeXRIS
BibTeX
@article{yuan2026interpretable,
  title = {{Interpretable machine learning model for brain metastasis in breast cancer: a large-scale, multi-center study.}},
  author = {Quan Yuan and Yupeng Sha and Rui Yu and Hao Yu and Rongjie Ye and Yi Du and Hanqing Deng and Liqun Wang and Zhihao Lei and Kaizhou Chen and Jian Cai and Xiaoming Li and Yixin Liu and Yige Lu and Hui Pang and Shuiliang Wang and Taozhu Ye and Youzhuang Wu and Xiaofeng Li and Zhengda Chen and Junjing Li and Shuqi Yang and Kangni Chen and Qinpei Ke and Yongxuan Yuan and Lierui Chen and Fan Wang and Yuxin Cheng and Boqian Yu and Yuancong Jiang and Pengfei He and Kejie Zhang and Fei Gao and Zhichuan He and Zhiyang Li and Wenxin Chen and Zheng Wang and Chunhong Xiao and Yonghui Su and Naiqian Zhang and Debo Chen and Ming Niu and Jiguang Han},
  journal = {Journal of translational medicine},
  year = {2026},
  month = jul,
  doi = {10.1186/s12967-026-08675-0},
  url = {https://europepmc.org/article/MED/42902382},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Interpretable machine learning model for brain metastasis in breast cancer: a large-scale, multi-center study.
AU  - Quan Yuan
AU  - Yupeng Sha
AU  - Rui Yu
AU  - Hao Yu
AU  - Rongjie Ye
AU  - Yi Du
AU  - Hanqing Deng
AU  - Liqun Wang
AU  - Zhihao Lei
AU  - Kaizhou Chen
AU  - Jian Cai
AU  - Xiaoming Li
AU  - Yixin Liu
AU  - Yige Lu
AU  - Hui Pang
AU  - Shuiliang Wang
AU  - Taozhu Ye
AU  - Youzhuang Wu
AU  - Xiaofeng Li
AU  - Zhengda Chen
AU  - Junjing Li
AU  - Shuqi Yang
AU  - Kangni Chen
AU  - Qinpei Ke
AU  - Yongxuan Yuan
AU  - Lierui Chen
AU  - Fan Wang
AU  - Yuxin Cheng
AU  - Boqian Yu
AU  - Yuancong Jiang
AU  - Pengfei He
AU  - Kejie Zhang
AU  - Fei Gao
AU  - Zhichuan He
AU  - Zhiyang Li
AU  - Wenxin Chen
AU  - Zheng Wang
AU  - Chunhong Xiao
AU  - Yonghui Su
AU  - Naiqian Zhang
AU  - Debo Chen
AU  - Ming Niu
AU  - Jiguang Han
PY  - 2026
DA  - 2026/07/01
JO  - Journal of translational medicine
DO  - 10.1186/s12967-026-08675-0
UR  - https://europepmc.org/article/MED/42902382
AB  - Background  Brain metastasis (BM) is a devastating complication of breast cancer (BC) with a poor prognosis. Early identification of high-risk patients is essential but currently lacks accurate predictive tools. This study aimed to develop a stable machine learning model for predicting BM in a large, diverse patient population.Methods  We conducted a retrospective cohort study of 186,351 primary BC patients from the SEER program, the National Cancer Database, and a multi-center Chinese cohort. Patients were split into training and validation sets. Candidate predictors included demographic, clinicopathological, biomarker, and treatment-related variables, including surgery, chemotherapy, endocrine therapy, neoadjuvant therapy, and radiotherapy. LASSO regression was used for feature selection. Nine machine learning models were developed and compared using area under the curve (AUC) and decision curve analysis. The optimal model was deployed as an online tool.Results  Among 186,351 patients, 2,982 (1.6%) developed BM. In baseline comparisons, patients who developed BM more frequently exhibited advanced disease characteristics and different treatment patterns, likely reflecting more aggressive disease presentation. Key predictors retained in the final parsimonious model included AJCC N/M/T stage, age, and surgery status. The LASSO-regularized Logistic Regression model achieved superior discrimination in the validation set, with an AUC of 0.907 (95% CI: 0.857-0.958). The model demonstrated good calibration, clinical net benefit, and interpretability, with SHAP analysis confirming the contribution of each retained predictor to individual risk estimates. Survival analysis confirmed the poor prognosis associated with BM (p < 0.001). An interactive online tool was developed for real-time risk estimation.Conclusion  We developed and internally validated a accurate, clinically translatable model for predicting BM in BC using over 186,000 patients from North American and Asian cohorts. This web-based tool can assist clinicians in identifying high-risk individuals, enabling personalized management and potentially improving patient outcomes.
SN  - 1479-5876
ER  -