Skip to main content

ORIGINAL RESEARCH article

Front. Immunol.
Sec. Cancer Immunity and Immunotherapy
Volume 15 - 2024 | doi: 10.3389/fimmu.2024.1493377
This article is part of the Research Topic Immunological Precision Therapeutics: Integrating Multi-Omics Technologies and Comprehensive Approaches for Personalized Immune Intervention View all 25 articles

Integrating Omics data and Machine Learning Techniques for Precision Detection of Oral Squamous Cell Carcinoma: Evaluating Single Biomarkers

Provisionally accepted
Yilan Sun Yilan Sun 1,2Guozhen Cheng Guozhen Cheng 3Dongliang Wei Dongliang Wei 1,2Jiacheng Luo Jiacheng Luo 4Jiannan Liu Jiannan Liu 1,2*
  • 1 Department of Oral Maxillofacial-Head and Neck Oncology, Shanghai Ninth People’s Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
  • 2 Shanghai Research Institute of Stomatology, Shanghai, China, Shanghai, China
  • 3 College of Mechanical and Electronic Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian Province, China
  • 4 College of Stomatology, School of Medicine, Shanghai Jiao Tong University, Pudong, Shanghai Municipality, China

The final, formatted version of the article will be published soon.

    The early detection of oral squamous cell carcinoma (OSCC) through precision diagnostics has the potential to significantly improve clinical outcomes. In this study, we integrated metabolomics with advanced machine learning models using a multicenter public dataset. Plasma-based metabolomics provides a non-invasive method to identify tumor-derived biomarkers, which are crucial for the early screening of OSCC. We processed data from 61 OSCC patients and 61 healthy controls, identifying 29 numerical and 47 ratio features that significantly differentiate between cases and controls. Using the Extra Trees (ET) algorithm for feature selection and the TabPFN model for classification and prediction, we achieved an AUC of 93%, with an overall accuracy of 76.6% when utilizing topranked individual biomarkers. Our findings demonstrate the utility of integrating omics data and machine learning techniques for developing highly accurate, non-invasive diagnostics in OSCC, advancing personalized therapeutics by identifying actionable metabolic signatures for early intervention.

    Keywords: machine learning, oral squamous cell carcinoma, Precision Metabolomics, Feature Selection, personalized therapy

    Received: 09 Sep 2024; Accepted: 18 Nov 2024.

    Copyright: © 2024 Sun, Cheng, Wei, Luo and Liu. 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) or licensor 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.

    * Correspondence: Jiannan Liu, Department of Oral Maxillofacial-Head and Neck Oncology, Shanghai Ninth People’s Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.