A machine learning-based prognostic model for de novo metastatic HR-positive breast cancer: SEER cohort with external validation - Takeaways - MDSpire

A machine learning-based prognostic model for de novo metastatic HR-positive breast cancer: SEER cohort with external validation

  • By

  • Sihang Lin

  • Wanwan Wang

  • Lixia Liu

  • Jiayu Guan

  • Chuanrong Cen

  • Huawei Yang

  • July 17, 2026

Share

  • 1

    The study analyzed 2,266 patients with de novo metastatic HR-positive breast cancer from the SEER database to evaluate postoperative radiotherapy's impact on overall survival.

  • 2

    Kaplan–Meier analysis showed significantly better overall survival in the postoperative radiotherapy group compared to the non-radiotherapy group.

  • 3

    Logistic regression emerged as the most effective machine learning model for predicting 3-year overall survival, achieving an AUC of 0.721.

  • 4

    Postoperative radiotherapy was confirmed as an independent protective factor for overall survival in both the training and external validation cohorts.

  • 5

    The study emphasizes the need for accurate prognostic risk stratification in patients with metastatic HR-positive breast cancer under current treatment strategies.

Original Source(s)

A machine learning-based prognostic model for de novo metastatic HR-positive breast cancer: SEER cohort with external validation

  • by Sihang Lin, Wanwan Wang, Lixia Liu, Jiayu Guan, Chuanrong Cen, Huawei Yang

  • July 17, 2026

Related Content

Intratumoral and intracranial hemorrhage associated with MAPK-pathway targeted therapy: a systematic review and mechanistic synthesis

From associations to clinical practice: translating inflammatory-nutritional indices into a machine learning-driven model for breast cancer risk stratification with cross-ethnic validation

Quantitative assessment of inter-observer consistency in target volume delineation following breast-conserving surgery and mastectomy