Machine-learning algorithms predict breast cancer patient survival from UK Biobank whole-exome sequencing data.

Journal: Biomarkers in medicine
PMID:

Abstract

We tested whether machine-learning algorithm could find biomarkers predicting overall survival in breast cancer patients using blood-based whole-exome sequencing data. Whole-exome sequencing data derived from 1181 female breast cancer patients within the UK Biobank was collected. We found feature genes (n = 50) regarding total mutation burden using the long short-term memory model. Then, we developed the XGBoost survival model with selected feature genes. The XGBoost survival model performed acceptably, with a concordance index of 0.75 and a scaled Brier score of 0.146 in terms of overall survival prediction. The high-mutation group exhibited inferior overall survival compared with the low-mutation group in patients ≥56 years (log-rank test, p = 0.042). We showed that machine-learning algorithms can be used to predict overall survival in breast cancer patients from blood-based whole-exome sequencing data.

Authors

  • Bum-Sup Jang
    Department of Radiation Oncology, Seoul National University Hospital, Seoul, Korea.
  • In Ah Kim
    Department of Radiation Oncology, Seoul National University Bundang Hospital, Seongnam, 13620, Korea.