Transformer-based AI technology improves early ovarian cancer diagnosis using cfDNA methylation markers

Cell Rep Med. 2024 Aug 20;5(8):101666. doi: 10.1016/j.xcrm.2024.101666. Epub 2024 Aug 1.

Abstract

Epithelial ovarian cancer (EOC) is the deadliest women's cancer and has a poor prognosis. Early detection is the key for improving survival (a 5-year survival rate in stage I/II is over 70% compared to that of 25% in stage III/IV) and can be achieved through methylation markers from circulating cell-free DNA (cfDNA) using a liquid biopsy. In this study, we first identify top 500 EOC markers differentiating EOC from healthy female controls from 3.3 million methylome-wide CpG sites and validated them in 1,800 independent cfDNA samples. We then utilize a pretrained AI transformer system called MethylBERT to develop an EOC diagnostic model which achieves 80% sensitivity and 95% specificity in early-stage EOC diagnosis. We next develop a simple digital droplet PCR (ddPCR) assay which archives good performance, facilitating early EOC detection.

Keywords: cfDNA; early cancer detection; liquid biopsy; methylation; neuronal network; ovarian cancer; transformer.

MeSH terms

  • Artificial Intelligence
  • Biomarkers, Tumor* / genetics
  • Carcinoma, Ovarian Epithelial / diagnosis
  • Carcinoma, Ovarian Epithelial / genetics
  • Carcinoma, Ovarian Epithelial / pathology
  • Cell-Free Nucleic Acids* / blood
  • Cell-Free Nucleic Acids* / genetics
  • CpG Islands / genetics
  • DNA Methylation* / genetics
  • Early Detection of Cancer* / methods
  • Female
  • Humans
  • Liquid Biopsy / methods
  • Middle Aged
  • Ovarian Neoplasms* / blood
  • Ovarian Neoplasms* / diagnosis
  • Ovarian Neoplasms* / genetics

Substances

  • Biomarkers, Tumor
  • Cell-Free Nucleic Acids