Detection of Helicobacter pylori Infection in Human Gastric Fluid Through Surface-Enhanced Raman Spectroscopy Coupled With Machine Learning Algorithms

• Published in: Laboratory investigation Vol. 104; no. 2; p. 100310
• Main Authors: Tang, Jia-Wei, Li, Fen, Liu, Xin, Wang, Jin-Ting, Xiong, Xue-Song, Lu, Xiang-Yu, Zhang, Xin-Yu, Si, Yu-Ting, Umar, Zeeshan, Tay, Alfred Chin Yen, Marshall, Barry J., Yang, Wei-Xuan, Gu, Bing, Wang, Liang
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.02.2024
• Subjects: gastric fluid; Helicobacter pylori; machine learning; string test; surface-enhanced Raman spectroscopy; gastric fluid; string test; Helicobacter pylori; machine learning; surface-enhanced Raman spectroscopy
• ISSN: 0023-6837; 1530-0307; 1530-0307
• DOI: 10.1016/j.labinv.2023.100310

Diagnostic methods for Helicobacter pylori infection include, but are not limited to, urea breath test, serum antibody test, fecal antigen test, and rapid urease test. However, these methods suffer drawbacks such as low accuracy, high false-positive rate, complex operations, invasiveness, etc. Therefore, there is a need to develop simple, rapid, and noninvasive detection methods for H. pylori diagnosis. In this study, we propose a novel technique for accurately detecting H. pylori infection through machine learning analysis of surface-enhanced Raman scattering (SERS) spectra of gastric fluid samples that were noninvasively collected from human stomachs via the string test. One hundred participants were recruited to collect gastric fluid samples noninvasively. Therefore, 12,000 SERS spectra (n = 120 spectra/participant) were generated for building machine learning models evaluated by standard metrics in model performance assessment. According to the results, the Light Gradient Boosting Machine algorithm exhibited the best prediction capacity and time efficiency (accuracy = 99.54% and time = 2.61 seconds). Moreover, the Light Gradient Boosting Machine model was blindly tested on 2,000 SERS spectra collected from 100 participants with unknown H. pylori infection status, achieving a prediction accuracy of 82.15% compared with qPCR results. This novel technique is simple and rapid in diagnosing H. pylori infection, potentially complementing current H. pylori diagnostic methods.