A prediction model for urological tumor metastasis using liquid biopsy-derived biomarkers - Takeaways - MDSpire

A prediction model for urological tumor metastasis using liquid biopsy-derived biomarkers

  • By

  • Jiandong Qu

  • Jing Zhang

  • Xiaoli Huang

  • July 3, 2026

  • 0 min

Share

  • 1

    A predictive model for tumor metastasis in urological tumors was developed using liquid biopsy biomarkers and clinical characteristics.

  • 2

    The study included 360 patients with urological tumors, divided into a training set of 252 and a validation set of 108.

  • 3

    Independent predictors for tumor metastasis identified were C-reactive protein, neutrophil count, platelet count, and white blood cell count.

  • 4

    The random forest model achieved the highest predictive efficacy with an area under the curve (AUC) of 0.891.

  • 5

    Machine learning methods were employed to integrate multi-dimensional data for improved prediction accuracy of metastasis.

Original Source(s)

A prediction model for urological tumor metastasis using liquid biopsy-derived biomarkers

  • by Jiandong Qu, Jing Zhang, Xiaoli Huang

  • July 3, 2026

Related Content

Case Report: Melanoma of the hard palate presenting initially with gastrointestinal symptoms: the diagnostic pivotal role of 18F-FDG PET/CT

TREM1 unleashes immunosuppression in glioma: targeting macrophage polarization as a new therapeutic vulnerability

Optimizing the Stupp protocol for treatment of glioblastoma: eliminating age bias, enhancing treatment timing, use of stereotactically-guided sequential boost, and dexamethasone dosing