Proposing new early detection indicators for pancreatic cancer - Combining machine learning and neural networks for serum miRNA-based diagnostic model

Aug 5, 2026

Upload by Patrick

Pancreatic cancer remains a highly lethal malignancy with persistently low five-year survival, creating urgent demand for dependable early detection. This study analyzes serum miRNA expression profiles from three independent GEO datasets and uses SVM-RFE, LASSO, and Random Forest to identify pancreatic cancer–associated serum miRNAs. An artificial neural network model with a nomogram evaluates diagnostic performance and is validated by qPCR, while consensus clustering defines optimal subtypes and expression analyses assess clinical relevance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Background

Methods

Results

Conclusion

Keywords

TYPE Original Research PUBLISHED 03 August 2023 DOI 10.3389/fonc.2023.1244578 OPEN ACCESS EDITED BY Zhendong Jin, Second Military Medical University, China REVIEWED BY Feng Zhu, Jincheng People’s Hospital, China Xiaying Han, Zhejiang Chinese Medical University, China *CORRESPONDENCE Yunfei Liu [Yunfei.Liu@med.uni-muenchen.de](Yunfei.Liu@med.uni-muenchen.de)[ ](Yunfei.Liu@med.uni-muenchen.de)Qinhong Zhang [zhangqh0451@163.com](zhangqh0451@163.com)[ ](zhangqh0451@163.com)Guanhu Yang [guanhuyang@gmail.com](guanhuyang@gmail.com) †These authors have contributed equally to this work RECEIVED 22 June 2023 ACCEPTED 18 July 2023 PUBLISHED 03 August 2023 CITATION Chi H, Chen H, Wang R, Zhang J, Jiang L, Zhang S, Jiang C, Huang J, Quan X, Liu Y, Zhang Q and Yang G (2023) Proposing new early detection indicators for pancreatic cancer: Combining machine learning and neural networks for serum miRNA-based diagnostic model. Front. Oncol. 13:1244578 . doi: 10.3389/fonc.2023.1244578 COPYRIGHT © 2023 Chi, Chen, Wang, Zhang, Jiang, Zhang, Jiang, Huang, Quan, Liu, Zhang and Yang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Proposing new early detection indicators for pancreatic cancer: Combining machine learning and neural networks for serum miRNA-based diagnostic model Hao Chi 1†, Haiqing Chen 1†, Rui Wang 2,3,4†, Jieying Zhang 5,6†, Lai Jiang 1, Shengke Zhang 1, Chenglu Jiang 1, Jinbang Huang 1, Xiaomin Quan 7,8, Yunfei Liu 9*, Qinhong Zhang 10* and Guanhu Yang 11* 1Clinical Medical College, Southwest Medical University, Luzhou, China, 2 Department of General Surgery (Hepatobiliary Surgery), The Afﬁliated Hospital of Southwest Medical University, Luzhou, China, 3 Nuclear Medicine and Molecular Imaging Key Laboratory of Sichuan Province, Luzhou, China, 4Academician (Expert) Workstation of Sichuan Province, Luzhou, China, 5 First Teaching Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin, China, 6 National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, Tianjin, China, 7 Beijing University of Chinese Medicine, Beijing, China, 8 Beijing University of Chinese Medicine Second Afﬁliated DongFang Hospital, Beijing, China, 9 Department of General, Visceral, and Transplant Surgery, Ludwig-Maximilians-University Munich, Munich, Germany, 10Shenzhen Frontiers in Chinese Medicine Research Co., Ltd., Shenzhen, China, 11 Department of Specialty Medicine, Ohio University, Athens, OH, United States Background: Pancreatic cancer (PC) is a lethal malignancy that ranks seventh in terms of global cancer-related mortality. Despite advancements in treatment, the ﬁve-year survival rate remains low, emphasizing the urgent need for reliable early detection methods. MicroRNAs (miRNAs), a group of non-coding RNAs involved in critical gene regulatory mechanisms, have garnered signiﬁcant attention as potential diagnostic and prognostic biomarkers for pancreatic cancer (PC) . Their suitability stems from their accessibility and stability in blood, making them particularly appealing for clinical applications. Methods: In this study, we analyzed serum miRNA expression proﬁles from three independent PC datasets obtained from the Gene Expression Omnibus (GEO) database. To identify serum miRNAs associated with PC incidence, we employed three machine learning algorithms: Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest. We developed an artiﬁcial neural network model to assess the accurac

FAQs

How was the diagnostic model built and validated?

An artificial neural network model with a nomogram was developed to assess diagnostic accuracy using the identified miRNAs, and findings were further validated with qPCR experiments.

Aug 5, 2026

Upload by Patrick