Identifying ovarian cancer with machine learning DNA methylation pattern analysis.

Journal: Scientific reports
Published Date: Jul 1, 2025

Abstract

The majority of patients with epithelial ovarian cancer (EOC) continue to be diagnosed at an advanced stage despite great advances in this disease treatment. To impact overall survival, we need better methods of EOC early diagnosis. We performed a case control study to predict high-grade serous cancer (HGSC) using artificial intelligence methodology and methylated DNA from surgical specimens. Initial prediction models with MethylNet were accurate but complex (AUC = 100%). We optimized these models by selecting the most informative probes with univariate ANOVA analyses first, and then multivariate lasso regression modelling. This step-wise approach resulted in 9 methylated probes predicting HGSC with an AUC of 100%. These models were validated with different analytics and with an independent DNA-methylation experiment with excellent performances.

Authors

  • Jesus Gonzalez Bosquet
    Department of Obstetrics and Gynecology, Gynecologic Oncology, University of Iowa, Iowa City, IA.
  • Vincent M Wagner
    Department of Obstetrics and Gynecology, Gynecologic Oncology, University of Iowa, Iowa City, IA.
  • Douglas Russo
    Division of Urogynecology and Reconstructive Pelvic Surgery, Department of Obstetrics and Gynecology, University of Chicago, Chicago, IL, USA.
  • Henry D Reyes
    Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA.
  • Andreea M Newtson
    Endeavor Health, Evanston, IL, 68198, USA.
  • David P Bender
    Department of Obstetrics and Gynecology, University of Iowa, 200 Hawkins Dr., Iowa City, IA, 52242, USA.
  • Michael J Goodheart
    Department of Obstetrics and Gynecology, University of Iowa Hospitals and Clinics, Iowa City, IA.

Keywords

External Resources

Popular Topics
Recent Journals