Development and validation of a machine learning-based risk prediction model for cancer-related fatigue in ovarian cancer patients - Takeaways - MDSpire

Development and validation of a machine learning-based risk prediction model for cancer-related fatigue in ovarian cancer patients

  • By

  • Ru Feng

  • Zexuan Fan

  • Yuanyuan Pang

  • Qifan Ding

  • Qian Yue

  • Siqi Wei

  • June 4, 2026

  • 0 min

Share

  • 1

    A machine learning model was developed to predict cancer-related fatigue (CRF) in ovarian cancer patients, addressing inadequate early detection tools.

  • 2

    The study involved 407 ovarian cancer patients, with data split into training and testing sets for model evaluation.

  • 3

    The Support Vector Machine (SVM) achieved the best predictive performance, with an AUC of 0.884 and high accuracy and sensitivity.

  • 4

    Key predictive features identified included serum calcium level, anxiety-depression status, and cancer stage, among others.

  • 5

    The SVM model's robust efficacy supports its use for CRF risk stratification, enabling targeted interventions to improve patient outcomes.

Original Source(s)

Development and validation of a machine learning-based risk prediction model for cancer-related fatigue in ovarian cancer patients

  • by Ru Feng, Zexuan Fan, Yuanyuan Pang, Qifan Ding, Qian Yue, Siqi Wei

  • June 4, 2026

Related Content

Interaction of CD99 and its ligands regulates immunoregulatory pathways in NK cells

Baseline 18F-FDG PET/CT habitat radiomics versus dual-channel deep learning for predicting interim PET early metabolic response in diffuse large B-cell lymphoma: a comparative study

Identification, design, and in vivo proof of concept of a shared APC neoantigen delivered via a self-amplifying RNA containing virus-like nanoparticle for cancer vaccination