Rapid diagnosis of bacterial vaginosis using machine-learning-assisted surface-enhanced Raman spectroscopy of human vaginal fluids

• Published in: mSystems Vol. 10; no. 1; p. e0105824
• Main Authors: Wen, Xin-Ru, Tang, Jia-Wei, Chen, Jie, Chen, Hui-Min, Usman, Muhammad, Yuan, Quan, Tang, Yu-Rong, Zhang, Yu-Dong, Chen, Hui-Jin, Wang, Liang
• Format: Journal Article
• Language: English
• Published: United States American Society for Microbiology 21.01.2025
• Subjects: Accuracy; Adult; Algorithms; bacterial vaginosis; Body Fluids - chemistry; Body Fluids - microbiology; Computational Biology; deep learning; Diagnosis; Electrons; Female; Humans; Learning algorithms; Machine Learning; Medical laboratories; Microscopy; Nanoparticles; Neural networks; Neural Networks, Computer; Particle size; Potassium; Predictions; Raman spectroscopy; rapid identification; Research Article; SERS; Silver; Spectrum analysis; Spectrum Analysis, Raman - methods; Support vector machines; Vagina; Vagina - microbiology; Vaginosis; Vaginosis, Bacterial - diagnosis; Vaginosis, Bacterial - microbiology; Young Adult; deep learning; machine learning; SERS; bacterial vaginosis; rapid identification
• ISSN: 2379-5077; 2379-5077
• DOI: 10.1128/msystems.01058-24

The accurate and rapid diagnosis of bacterial vaginosis (BV) is crucial due to its high prevalence and association with serious health complications, including increased risk of sexually transmitted infections and adverse pregnancy outcomes. Although widely used, traditional diagnostic methods have significant limitations in subjectivity, complexity, and cost. The development of a novel diagnostic approach that integrates SERS with ML offers a promising solution. The CNN model’s high prediction accuracy, cost-effectiveness, and extraordinary rapidity underscore its significant potential to enhance the diagnosis of BV in clinical settings. This method not only addresses the limitations of current diagnostic tools but also provides a more accessible and reliable option for healthcare providers, ultimately enhancing patient care and health outcomes.