An Extracellular Vesicle Protein-Based Machine Learning Framework for Early Detection of Oesophageal Squamous Cell Carcinoma - A Multicentre, Prospective Study

Sep 23, 2026

Early detection of oesophageal squamous cell carcinoma (ESCC) is critical for improving survival, yet current screening is limited by the lack of effective, non-invasive methods. An extracellular vesicle (EV) protein-based blood test was prospectively developed and validated for preclinical ESCC detection. A high-sensitivity EV protein analysis platform (BarFlare) enabled identification of a biomarker panel integrating EV-associated SCC and MMP13, fused with clinical factors in an interpretable multi-criteria decision-making classification (MCF) framework. The model achieved strong discrimination across prospective multicentre diagnostic cohorts and external validations, including early-stage disease, and predicted future ESCC development with substantial lead time in a longitudinal population-based cohort.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Journal of Extracellular Vesicles RESEARCH ARTICLE An Extracellular Vesicle Protein-Based Machine Learning Framework for Early Detection of Oesophageal Squamous Cell Carcinoma: A Multicentre, Prospective Study Yu Wang1, 2 Shan Xing1, 2 Ya-Xian Wu1, 2 Ning Xue3 Pei-Min Chen4 Run-Xian Jin5 Yi-Wei Xu6 Ming-Fang Ji7 Yu-Hui Peng6 Yuan-Tao Liu1, 8 Li-Na Chen1, 8 Meng Wu1, 2 Zi-Ying Jiang1, 8 Shang-Hang Xie1, 9 Yi-Ling Luo1, 8 Biao Zhang6 Xin-Yuan Ou1, 2 Qi Huang1, 2 Bo-Yu Tian1, 2 Li Ling10 Su-Mei Cao1, 9 Wan-Li Liu1, 2 Mu-Sheng Zeng1, 8 Qian Zhong1, 8 1 State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China 2 Department of Clinical Laboratory, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China 3 Department of Clinical Laboratory, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China 4 Centre for Disease Control and Prevention of Liwan District of Guangzhou, Guangzhou, China 5Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China 6 Department of Clinical Laboratory Medicine, Cancer Hospital of Shantou University Medical College, Shantou, China 7 Cancer Research Institute of Zhongshan City, Zhongshan City People’s Hospital, Zhongshan, China 8 Department of Experimental Research, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China 9 Department of Cancer Prevention Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China 10 Department of Medical Statistics and Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China Correspondence: Su-Mei Cao ([caosm@sysucc.org.cn](caosm@sysucc.org.cn)) Wan-Li Liu (liuwl@sysucc.org.cn) Mu-Sheng Zeng (zengmsh@sysucc.org.cn) Qian Zhong ([zhongqian@sysucc.org.cn](zhongqian@sysucc.org.cn)) Received: 26 August 2025 Revised: 11 December 2025 Accepted: 6 February 2026 Keywords: biomarkers | early detection | extracellular vesicles | liquid biopsy | oesophageal squamous cell carcinoma ABSTRACT Early detection of oesophageal squamous cell carcinoma (ESCC) is critical for improving survival, yet current screening is hampered by the lack of effective, non-invasive methods. Here, we developed and prospectively validated an extracellular vesicle (EV) protein-based blood test for the preclinical detection of ESCC. We first engineered BarFlare, a high-sensitivity platform for serum EV protein analysis, and identified a novel biomarker panel that includes EV-associated squamous cell carcinoma antigen (SCC) and matrix metalloproteinase-13 (MMP13) . These biomarkers were integrated with clinical factors into an interpretable multi-criteria decision-making classification fusion (MCF) machine-learning framework. The MCF model was trained and validated in prospective, multicentre diagnostic cohorts (n = 1018), and its preclinical detection capability was assessed in a prospective, population-based longitudinal cohort. TheMCF framework accurately distinguished patients with ESCC from healthy controls in a test set (AUC, 0.987) and two external validation cohorts (AUCs, 0.926 and 0.960), including those with early-stage disease (AUCs, 0.901–0.980). Critically, in the longitudinal cohort, the framework identified individuals who would later develop ESCC from their baseline blood samples with a median lead time of 34.9 months (range, 0.4–72.5) before clinical diagnosis (AUC, 0.864; sensitivity, 73.3%; specificity, 82.2%). The risk score of the model correlated with time to diagnosis, and its dynamic increase significantly outperformed that of traditi

FAQs

Why is early detection of oesophageal squamous cell carcinoma (ESCC) challenging?

Early detection is critical but current screening is hindered by the lack of effective non-invasive methods, and conventional approaches like endoscopy are invasive and unsuitable for large-scale screening.

What did the study develop for preclinical ESCC detection?

The study developed a blood test based on extracellular vesicle (EV) proteins, using BarFlare for high-sensitivity EV protein analysis and a biomarker panel including EV-associated SCC and MMP13.

How well did the machine-learning framework perform in prospective and external validations?

The multicentre MCF framework distinguished ESCC patients from healthy controls with high AUC values in test and external cohorts, and it also identified individuals who later developed ESCC using baseline blood samples with a median lead time of 34.9 months.

Sep 23, 2026

Upload by Sophia Brooks