Development and validation of a machine learning-based early warning model for bone metastasis in newly diagnosed prostate cancer - Takeaways - MDSpire

Development and validation of a machine learning-based early warning model for bone metastasis in newly diagnosed prostate cancer

  • By

  • Leibo Wang

  • Wei He

  • Changyong Zhao

  • Qi lv

  • Tao Qiu

  • Jianpo Zhai

  • Kaiyi Mao

  • Daobing Li

  • Xian Wen

  • July 9, 2026

  • 0 min

Share

  • 1

    A machine learning model was developed to predict bone metastasis in newly diagnosed prostate cancer patients using data from 327 individuals.

  • 2

    The Boruta algorithm identified six significant predictors for bone metastasis, including clinical T stage and Gleason score.

  • 3

    The random forest model demonstrated the best performance with an area under the curve of 0.902 in the training set and 0.906 in the validation set.

  • 4

    An interactive online prediction tool was created for individualized risk estimation of bone metastasis in prostate cancer patients.

  • 5

    Prospective multicenter studies are needed to confirm the generalizability of the developed predictive model for clinical use.

Original Source(s)

Development and validation of a machine learning-based early warning model for bone metastasis in newly diagnosed prostate cancer

  • by Leibo Wang, Wei He, Changyong Zhao, Qi lv, Tao Qiu, Jianpo Zhai, Kaiyi Mao, Daobing Li, Xian Wen

  • July 9, 2026

Related Content

Regression of retinal capillary hemangioblastoma with systemic belzutifan in von Hippel–Lindau disease: a case report

Efficacy and safety of PARP inhibitors in older patients with advanced ovarian cancer: a systematic review and network meta-analysis

Long-term outcomes of definitive chemoradiotherapy with docetaxel, cisplatin, and 5-fluorouracil for postoperative locoregional recurrent esophageal cancer: a prospective phase II study