@article{Zheng2025, 
author = {Zefeng Zheng and Ying Cui and Boyou Zhang and Yang Li and Yongjie Liu and Jiaying Ye and Feng Yuan and Khek-yu HO and Jing Liu and Lijia Wang},
title = {Recent research progress in the integration of Raman spectroscopy with machine learning algorithms for disease diagnosis},
year = {2025},
journal = {Nano Research},
volume = {18},
number = {11},
pages = {94907834},
keywords = {artificial intelligence, machine learning, Raman spectroscopy, disease diagnosis},
url = {https://www.sciopen.com/article/10.26599/NR.2025.94907834},
doi = {10.26599/NR.2025.94907834},
abstract = {Disease diagnosis involves multiple complex factors, and Raman spectroscopy has great potential to aid in diagnosis. While traditional Raman spectroscopy technology offers abundant chemical information, it may face challenges in highly complex pattern recognition tasks. As an emerging technology, artificial intelligence enhances multi-dimensional data processing via its learning and feature extraction capabilities while simulating human intelligence to achieve self-learning, self-optimization, self-adaptation, and autonomous decision-making. This enables automation, intelligent operation, and high-efficiency tasks. This review expounds on recent progress (over the past several years) in disease detection via the integration of Raman spectroscopy and machine learning, particularly in diagnosing cancers (e.g., gastrointestinal, urogenital, respiratory, and nervous systems) along with viral, bacterial, and fungal infections. This review demonstrates cross-disciplinary cooperation among fields like Raman spectroscopy, nanotechnology, and artificial intelligence, which has promoted biomedical detection technology. These technological advancements have not only refined diagnostic accuracy but also opened new avenues for research.}
}