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

mSystems, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Bacterial vaginosis (BV) is an abnormal gynecological condition caused by the overgrowth of specific bacteria in vagina. This study aims to develop a novel method for BV detection integrating surface-enhanced Raman scattering (SERS) with machine learning (ML) algorithms. Vaginal fluid samples were classified as positive or negative using BVBlue Test and clinical microscopy, followed SERS spectral acquisition construct data set. Preliminary analysis revealed notable disparities characteristic peak features. Multiple ML models constructed optimized, convolutional neural network (CNN) model achieving highest prediction accuracy at 99%. Gradient-weighted class activation mapping (Grad-CAM) was used highlight important regions images prediction. Moreover, CNN blindly tested on spectra vaginal collected from 40 participants unknown infection status, 90.75% compared results combined microscopy. technique simple, cheap, rapid accurately diagnosing bacterial vaginosis, potentially complementing current diagnostic methods laboratories.

Language: Английский

---

Controllable Construction of Aptamer-Modified Fe3O4@SiO2-Au Core-Shell-Satellite Nanocomposites with Surface-Enhanced Raman Scattering and Photothermal Properties and Their Effective Capture, Detection, and Elimination of Staphylococcus aureus

Molecules, Journal Year: 2024, Volume and Issue: 29(15), P. 3593 - 3593

Published: July 30, 2024

The early monitoring and inactivation of bacteria are crucial importance in preventing the further spread foodborne pathogens.

Language: Английский

---

Comparative study of machine-and deep-learning based classification algorithms for biomedical Raman spectroscopy (RS): case study of RS based pathogenic microbe identification

Analytical Sciences, Journal Year: 2024, Volume and Issue: 40(12), P. 2101 - 2109

Published: Aug. 29, 2024

One key aspect pushing the frontiers of biomedical RS is dedicated machine- or deep- learning (ML DL) algorithms. Yet, systematic comparative study between ML and DL algorithms has not been conducted for RS, largely due to limited availability open-source large Raman spectra dataset. Therefore we compared typical partial least square-discriminant analysis (PLS-DA) one dimensional convolution neural network (1D-CNN) based pathogenic microbe identification on 12,000 from six species (i.e., K. aerogenes (Klebsiella aerogenes), C. albicans (Candida albicans), glabrata glabrata), Group A Strep. (Group Streptococcus), E. coli1 (Escherichia coli1), coli2 coli2)) when 100%, 75%, 50% 25% were retained. The total dataset was analyzed with 80% split training 20% testing. 100% retained testing accuracy, area under curve (AUC) receiver operating characteristic (ROC) 95.25% 0.997 1D-CNN, which are higher than those (89.42% 0.979) PLS-DA. PLS-DA outperforms 1D-CNN resultant accuracies AUCs demonstrated performance reliance number. Besides, both loadings latent variables saliency maps captured peaks arising DNA proteins comparable interpretability. results current work indicated that should be explored application-wise select whichever AUCs.

Language: Английский

---

Au@Ag hollow nanoshells-based SERS integrated microfluidic chip as a sample-to-answer platform for the ultra-sensitive detection of geosmin

Analytica Chimica Acta, Journal Year: 2024, Volume and Issue: 1335, P. 343471 - 343471

Published: Nov. 23, 2024

Language: Английский

---

Activated silver nanoparticle-based platform for specific capture of Porphyromonas gingivalis in human saliva

Sensors and Actuators B Chemical, Journal Year: 2023, Volume and Issue: 403, P. 135171 - 135171

Published: Dec. 19, 2023

Language: Английский

---

SERS microfluidic chip integrated with double amplified signal off-on strategy for detection of microRNA in NSCLC

Biomedical Optics Express, Journal Year: 2023, Volume and Issue: 15(2), P. 594 - 594

Published: Dec. 22, 2023

In this work, based on Fe 3 O 4 @AuNPs and double amplified signal Off-On strategy, a simple sensitive SERS microfluidic chip was constructed to detect microRNA associated with non-small cell lung cancer (NSCLC). have two advantages of enhanced magnetic adsorption, the introduction can realize amplification signal. First, binding complementary ssDNA hpDNA moved Raman signaling molecule away from @AuNPs, at which point turned off. Second, in presence target microRNA, they were captured by bound them. HpDNA restored hairpin conformation, closer @AuNPs. At time, strong generated. And last, through component chip, could be enriched secondary enhancement way, proposed high sensitivity specificity. The corresponding detection limit (LOD) for miR-21 versus miR-125b 6.38 aM 7.94 aM, respectively. This promising field early NSCLC.

Language: Английский

---

Au@Ag Hollow Nanoshells-Based Sers Integrated Microfluidic Chip as a Sample-to-Answer Platform for the Ultra-Sensitive Detection of Geosmin

Published: Jan. 1, 2024

Language: Английский

---

Signal “on-off” photoelectrochemical biosensor for gram-positive bacteria quick detection based on vancomycin functionalized BiVO4/Au photoelectrode

Microchemical Journal, Journal Year: 2024, Volume and Issue: 207, P. 112096 - 112096

Published: Nov. 6, 2024

Language: Английский

---