journal article·2026-02-18

Explainable Artificial Intelligence-Driven Salivary Exosome Spectroscopic Profiling for Clinical Diagnosis and Metastasis Detection of Oral Cancer

Wenqian Tian, Yangcenzi Xie, Hua Su, Chao Zheng, Ming Li

Nano Letters· Volume 26· Issue 6
Publisher page

Abstract

Oral squamous cell carcinoma (OSCC), the most common oral malignancy, requires accurate diagnostic methods for patient stratification and treatment guidance. Exosome-based liquid biopsy represents a promising minimally invasive approach to cancer detection. This study develops an explainable artificial intelligence (xAI)-assisted label-free surface-enhanced Raman spectroscopy (SERS) platform for profiling salivary exosomes to enable noninvasive OSCC diagnosis and metastatic stratification. A fully connected artificial neural network is designed to extract discriminative features from complex SERS data. Trained on cellular exosome SERS data sets, the model achieves 90.63% accuracy in distinguishing OSCC patients from healthy subjects and 86.63% accuracy in differentiating nonmetastatic and metastatic OSCC cases. Importantly, Shapley additive explanation-based xAI interpretation identifies tryptophan residues in transmembrane proteins as regulators of carcinogenesis, while genetic mutations are linked to metastatic progression, thereby bridging diagnostic outcomes with molecular mechanisms. This work establishes a biochemically interpretable SERS-xAI framework for cancer diagnosis, advancing precision oncology through mechanistic insights.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Spectroscopy Techniques in Biomedical and Chemical Research · Extracellular vesicles in disease · Gold and Silver Nanoparticles Synthesis and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Materials Science and Engineering

Central South University

Department of Breast Surgery, The Second Qilu Hospital

Shandong University

Funding

Department of Science and Technology of Hunan Province · National Natural Science Foundation of China

References (50)

Show source-provided references
1. 10.3322/caac.2183410.3322/caac.21834 ↗
2. 10.1016/S0140-6736(21)01550-610.1016/S0140-6736(21)01550-6 ↗
3. 10.1016/j.ejca.2015.07.04310.1016/j.ejca.2015.07.043 ↗
4. World Cancer Research Fund · 2022
5. International Agency for Research on Cancer. Cancer Today. World Health Organization. https://gco.iarc.who.int/media/globocan/factsheets/populations/900-world-fact-sheet.pdf (accessed 2025-Dec-08).
6. American Cancer Society · 2025
7. 10.3390/jcm1209326410.3390/jcm12093264 ↗
8. 10.1007/s40496-014-0014-y10.1007/s40496-014-0014-y ↗
9. 10.1016/j.oraloncology.2014.03.00910.1016/j.oraloncology.2014.03.009 ↗
10. 10.1038/nrc298210.1038/nrc2982 ↗
11. 10.1039/D3NR02662K10.1039/D3NR02662K ↗
12. 10.1126/sciadv.160027410.1126/sciadv.1600274 ↗
13. 10.1016/j.ccr.2021.21411110.1016/j.ccr.2021.214111 ↗
14. 10.1039/D3CS00793F10.1039/D3CS00793F ↗
15. 10.1038/s41591-024-02869-z10.1038/s41591-024-02869-z ↗
16. 10.1126/science.aau697710.1126/science.aau6977 ↗
17. 10.1021/acsabm.3c0124310.1021/acsabm.3c01243 ↗
18. 10.1021/acsnano.3c0044910.1021/acsnano.3c00449 ↗
19. 10.1126/sciadv.aba255610.1126/sciadv.aba2556 ↗
20. 10.1021/acsnano.7b0819910.1021/acsnano.7b08199 ↗
21. 10.1002/adma.20197031810.1002/adma.201970318 ↗
22. 10.1021/acsnano.4c0066610.1021/acsnano.4c00666 ↗
23. 10.1016/j.ccr.2018.05.00710.1016/j.ccr.2018.05.007 ↗
24. 10.1021/jacs.2c0451410.1021/jacs.2c04514 ↗
25. 10.1002/adfm.20230709110.1002/adfm.202307091 ↗
26. 10.1021/acs.nanolett.4c0289010.1021/acs.nanolett.4c02890 ↗
27. 10.1039/D4CS00883A10.1039/D4CS00883A ↗
28. 10.1038/s43586-021-00083-610.1038/s43586-021-00083-6 ↗
29. 10.1039/D4CS00090K10.1039/D4CS00090K ↗
30. 10.1021/acssensors.3c0267010.1021/acssensors.3c02670 ↗
31. 10.1038/s41576-019-0122-610.1038/s41576-019-0122-6 ↗
32. 10.1021/acs.nanolett.2c0292810.1021/acs.nanolett.2c02928 ↗
33. 10.1016/0277-5379(88)90335-510.1016/0277-5379(88)90335-5 ↗
34. 10.1038/bjc.1981.11510.1038/bjc.1981.115 ↗
35. 10.1111/j.1600-0714.1989.tb01570.x10.1111/j.1600-0714.1989.tb01570.x ↗
36. 10.1021/nn400188510.1021/nn4001885 ↗
37. 10.1016/j.cej.2025.16562810.1016/j.cej.2025.165628 ↗
38. 10.1002/anie.20140931410.1002/anie.201409314 ↗
39. 10.1039/D1TC02083H10.1039/D1TC02083H ↗
40. 10.1021/acs.jpcc.2c0869310.1021/acs.jpcc.2c08693 ↗
41. 10.1021/jp068790810.1021/jp0687908 ↗
42. 10.3390/ijms2118646610.3390/ijms21186466 ↗
43. 10.1080/20013078.2020.181664110.1080/20013078.2020.1816641 ↗
44. 10.3390/molecules2521520910.3390/molecules25215209 ↗
45. 10.1016/j.trac.2022.11680410.1016/j.trac.2022.116804 ↗
46. 10.1080/05704928.2014.92390210.1080/05704928.2014.923902 ↗
47. 10.1039/C8NR04677H10.1039/C8NR04677H ↗
48. 10.1186/s12943-024-02193-710.1186/s12943-024-02193-7 ↗
49. 10.1038/s41573-019-0016-510.1038/s41573-019-0016-5 ↗
50. 10.1038/s41368-023-00249-w10.1038/s41368-023-00249-w ↗