An integrated serum peptidomics and multi-algorithm machine learning approach for early diagnosis of lung cancer
Abstract
BackgroundLung cancer is one of the leading causes of cancer-related mortality worldwide. Due to the lack of specific symptoms at early stages, most patients are diagnosed at advanced stages, underscoring the need for reliable non-invasive early detection strategies beyond invasive biopsy and non-specific imaging.MethodsWe integrated serum proteomics with multi-algorithm machine learning to establish an artificial intelligence–based workflow for early lung cancer diagnosis. Serum samples from 774 participants were analyzed using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) to generate peptidomic profiles. After data preprocessing and normalization, eight machine learning algorithms were applied for model construction, and model performance was systematically evaluated using the receiver operating characteristic (ROC) curve.ResultsMost machine learning models showed strong diagnostic performance in independent test sets. By combining feature importance, Shapley additive explanations (SHAP), and local interpretable model-agnostic explanations (LIME), nine lung cancer–associated peptide peaks were identified. Multidimensional models based on these peptide signatures achieved AUC values approaching 1, significantly outperforming single markers derived from the PRIDE database. Candidate proteins were further validated through integrative transcriptomic and proteomic analyses, supporting their biological relevance.ConclusionsOur findings indicate that serum proteomics combined with multi-algorithm machine learning enables accurate and non-invasive early detection of lung cancer, providing a promising framework for clinical translation.
Related
- Beyond Binary Diagnosis: A Genetic Algorithm Optimized Hybrid Machine Learning Model for PCOS Phenotype Prediction
- Evaluation of an Artificial Intelligence and Machine Learning Algorithm to Enhance Angiographic Coronary Visibility in Morbid Obesity: A Retrospective Observational Study
- Predicting the Risk of Unplanned Hospital Encounters in Hemodialysis Patients: A Comparison Between Clinicians and a Machine Learning Prediction Algorithm
- Machine Learning Based on Routine Hematological Parameters and Derived Inflammatory Indices for the Diagnosis of Schizophrenia
- Machine learning prediction model for distant metastasis at diagnosis in pediatric neuroblastoma: development, interpretation, and temporal validation
BibTeX
@article{cao2026integrated,
title = {{An integrated serum peptidomics and multi-algorithm machine learning approach for early diagnosis of lung cancer}},
author = {Li Cao and Jie Ding and Aihong Guo and Lihong Zhao and Bingju Wang and Zefeng Liu and Jiajing Zhao and Lin Han and Wen Li and Wei Zhang and Jiangbo Ding and Huange Zhu},
journal = {Frontiers in Oncology},
year = {2026},
month = nov,
doi = {10.3389/fonc.2026.1799622},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1799622},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - An integrated serum peptidomics and multi-algorithm machine learning approach for early diagnosis of lung cancer
AU - Li Cao
AU - Jie Ding
AU - Aihong Guo
AU - Lihong Zhao
AU - Bingju Wang
AU - Zefeng Liu
AU - Jiajing Zhao
AU - Lin Han
AU - Wen Li
AU - Wei Zhang
AU - Jiangbo Ding
AU - Huange Zhu
PY - 2026
DA - 2026/11/06
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1799622
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1799622
AB - BackgroundLung cancer is one of the leading causes of cancer-related mortality worldwide. Due to the lack of specific symptoms at early stages, most patients are diagnosed at advanced stages, underscoring the need for reliable non-invasive early detection strategies beyond invasive biopsy and non-specific imaging.MethodsWe integrated serum proteomics with multi-algorithm machine learning to establish an artificial intelligence–based workflow for early lung cancer diagnosis. Serum samples from 774 participants were analyzed using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) to generate peptidomic profiles. After data preprocessing and normalization, eight machine learning algorithms were applied for model construction, and model performance was systematically evaluated using the receiver operating characteristic (ROC) curve.ResultsMost machine learning models showed strong diagnostic performance in independent test sets. By combining feature importance, Shapley additive explanations (SHAP), and local interpretable model-agnostic explanations (LIME), nine lung cancer–associated peptide peaks were identified. Multidimensional models based on these peptide signatures achieved AUC values approaching 1, significantly outperforming single markers derived from the PRIDE database. Candidate proteins were further validated through integrative transcriptomic and proteomic analyses, supporting their biological relevance.ConclusionsOur findings indicate that serum proteomics combined with multi-algorithm machine learning enables accurate and non-invasive early detection of lung cancer, providing a promising framework for clinical translation.
SN - 2234-943X
ER -