Quantitative Analysis of Multiple Serum Tumor Biomarkers by an Interpretable Stacked Ensemble Model
values exceeding 0.9 for all biomarkers. Crucially, based on the quantitative results, we provided molecular-level interpretability for structure-spectrum correlations using Shapley additive explanations (SHAP), revealing how glycosylation reactions, matrix interference, and spectral overlap influence prediction accuracy. Furthermore, the capability of ISEM to quantify multiple biomarkers in unseen samples was confirmed through validation of its generalizability. Our study establishes an ensemble-driven, interpretable framework for quantitative biomarker analysis in a complex biological matrix, demonstrating significant potential for early cancer diagnosis and screening.
Authors
- Liangbao Yang (ORCID: https://orcid.org/0000-0002-6559-6947)
- Qingmei Deng
- Yanheng Huang
- Ronglu Dong
- Pan Li
- Boyu Wu (ORCID: https://orcid.org/0000-0002-7585-4997)
- Jiawei Chen
Institutions
- University of Science and Technology of China (CN)
- Anhui Medical University (CN)
- Chinese Academy of Sciences (CN)
- Hefei Institutes of Physical Science (CN)
- National Cancer Center (US)
- Hefei Institute of Technology Innovation (CN)
- First Affiliated Hospital of Anhui Medical University (CN)
Publication Details
- Journal
- Analytical Chemistry
- Published
- 2026-04-21
- DOI
- https://doi.org/10.1021/acs.analchem.5c04589
- Primary Topic
- Spectroscopy Techniques in Biomedical and Chemical Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Anhui Postdoctoral Science Foundation
- Anhui Provincial Key Research and Development Plan