Ovarian Cancer Diagnosis and Chemoresistance Prediction Model Based on cfRNA Molecular Signature.

Authors

Qinhao Guo, Yangyang Zhang, Yongcheng Jin, Siwei Deng, Yongqi Chen, Zheng Feng, Hao Wen, Liu Wang, Yilin Li, Fanghong Ou, Yong Shen, Haiming Li, Tianyao Zhou, Xingzhu Ju, Xiaohua Wu

Published in

Advanced science (Weinheim, Baden-Wurttemberg, Germany). Pages e76274. Jul 17, 2026. Epub Jul 17, 2026.

Abstract

Ovarian cancer (OVCA) is a common and highly aggressive gynecologic malignancy often diagnosed at advanced stages. Approximately 30% of patients develop platinum resistance, resulting in disease recurrence and progression. Currently, no diagnostic or chemoresistance prediction model based on plasma cell-free RNA (cfRNA) profiling exists.
We recruited 304 participants and performed plasma cfRNA sequencing. After quality control, 172 OVCA patients and 70 healthy controls were assigned to the training set, and 44 OVCA patients with 18 controls to the test set. A DenseNet-based deep learning model was developed to analyze cfRNA features.
The model distinguished OVCA patients from healthy controls with AUCs of 0.9997 in the training set and 0.9747 (95% CI: 0.9437-0.9963) in the test set. For chemoresistance prediction, it yielded AUCs of 0.9442 and 0.8421 (95% CI: 0.7504-0.9147), respectively. Our model outperformed comparative models across both tasks, though the performance advantage in the chemoresistance prediction task should be interpreted cautiously given the limited sample size. Interpretability analyses combined with bioinformatics identified FLOT1, IFITM3, and IFITM2 as putative diagnostic cfRNA biomarkers.
This plasma cfRNA-based deep learning model identifies OVCA patients and predicts chemoresistance, offering a non-invasive tool for early diagnosis and treatment stratification.
This study was registered in the Chinese Clinical Trial Registry under registration number ChiCTR2500099940.

PMID:
42467997
Bibliographic data and abstract were imported from PubMed on 18 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.