Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG DOI Creative Commons
Thais de Andrade Silva, Gabriel F. S. dos Santos,

Adilson Ribeiro Prado

et al.

Biosensors, Journal Year: 2024, Volume and Issue: 14(11), P. 523 - 523

Published: Oct. 29, 2024

This work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated spike protein were used human identify anti-SARS-CoV-2 antibodies. The comprehensive database utilized Raman spectra from all 594 serum samples. Machine investigations carried out using the Scikit-Learn library and implemented Python, characteristics of positive negative extracted Uniform Manifold Approximation Projection (UMAP) technique. models k-Nearest Neighbors (kNN), Support Vector (SVM), Decision Trees (DTs), logistic regression (LR), Light Gradient Boosting (LightGBM). kNN model led sensitivity 0.943, specificity 0.9275, accuracy 0.9377. study showed that combining spectroscopy algorithm can be effective diagnostic method. Furthermore, we highlighted advantages disadvantages each algorithm, providing valuable information for future research.

Language: Английский

Application of machine learning-assisted surface-enhanced Raman spectroscopy in medical laboratories: principles, opportunities, and challenges DOI

Jia-Wei Tang,

Quan Yuan, Li Zhang

et al.

TrAC Trends in Analytical Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 118135 - 118135

Published: Jan. 1, 2025

Language: Английский

Citations

7
Machine Learning-Driven Multidomain Nanomaterial Design: From Bibliometric Analysis to Applications DOI
Hong Wang,

Hengyu Cao,

Liang Yang

et al.

ACS Applied Nano Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 21, 2024

Machine learning (ML), as an advanced data analysis tool, simulates the process of human brain, enabling extraction features, discovery patterns, and making accurate predictions or decisions from complex data. In field nanomaterial design, application ML technology not only accelerates performance optimization nanomaterials but also promotes innovation materials science research methods. Bibliometrics, a method based on quantitative analysis, provides us with macro perspective to observe understand in design by statistically analyzing various indicators scientific literature. This paper quantitatively analyzes literature related ML-driven seven dimensions, revealing importance necessity design. It systematically diversified applications combination suitable algorithms being key enhancing nanomaterials. addition, this discusses current challenges future development directions, including quality set construction, algorithm optimization, deepening interdisciplinary cooperation. review researchers state trends ideas suggestions for research. is significant value promoting progress fostering in-depth research, accelerating innovative material technologies.

Language: Английский

Citations

15
Artificial Intelligence-Powered Surface-Enhanced Raman Spectroscopy for Biomedical Applications DOI

Xinyuan Bi,

X. Ai, Zongyu Wu

et al.

Analytical Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: March 27, 2025

Language: Английский

Citations

0
IDMap: Leveraging AI and Data Technologies for Early Cancer Detection DOI Open Access

Sabira Arefin

International Journal of Scientific Research and Management (IJSRM), Journal Year: 2024, Volume and Issue: 12(08), P. 1138 - 1145

Published: Aug. 4, 2024

Cancer screening is vital in cutting mortality rates, and containing the impact of cancer a worldwide basis. The current conventional detection techniques including imaging biopsy though efficient are also characterized with drawbacks like; invasive, expensive, inaccurate. This abstract will describe new AI data solution fight against early detection, which presents massive opportunity to improve accuracy, cut down time that it takes deliver diagnosis, bring quality health care possibly millions patients. ML and, particular, DL prospective terms decision making upon medical imaging, genomic sequences, electronic records detect biomarkers stages. statistics show AI-driven systems capable provide better diagnostic outcomes than methods some fields mammography for breast CT lung. Moreover, AI’s integration studies helps determining related genes hence supporting precision medicine adapts treatment specific genetic information patient. Apart from having outlets AI, big analytics, cloud computing, IoT equally important as well. Big analysis enables large complicated sets aid one may identify inklings point towards possible development cancer. use computing mainly provides meaningful platforms storage management volumes way allows improved efficiency high levels security. Wearable sensors collect on different throughout patient’s body, convey real-time regarding whether biomarkers’ approaching cancerous state. Despite this great promise, there various issues have be solved: protection, privacy, security, problems algorithms’ biases, into practice. Ethical questions generally tackle uncertainty surrounding decision-making clinical using A I systems. future trends diagnostics involve deeper approaches technology, enable more precise prevention treatment. applicability approach can extend identification cancer, but its occurrence through proper intervention. In conclusion, conversing technologies useful enhancing why perspectives patients’ recovery further decrease rates connected rather promising. area remain informative developing likely integrated work leading organizational models oncology preventive health.

Language: Английский

Citations

3
Electrochemical deposition of HSA on Ag electrode for its quantitative determination using SERS and machine learning DOI
I. A. Boginskaya, E. A. Slipchenko, Robert R. Safiullin

et al.

Sensors and Actuators A Physical, Journal Year: 2024, Volume and Issue: 377, P. 115700 - 115700

Published: Oct. 1, 2024

Language: Английский

Citations

1
Surface-Enhanced Raman Scattering Combined with Machine Learning for Rapid and Sensitive Detection of Anti-SARS-CoV-2 IgG DOI Creative Commons
Thais de Andrade Silva, Gabriel F. S. dos Santos,

Adilson Ribeiro Prado

et al.

Biosensors, Journal Year: 2024, Volume and Issue: 14(11), P. 523 - 523

Published: Oct. 29, 2024

This work reports an efficient method to detect SARS-CoV-2 antibodies in blood samples based on SERS combined with a machine learning tool. For this purpose, gold nanoparticles directly conjugated spike protein were used human identify anti-SARS-CoV-2 antibodies. The comprehensive database utilized Raman spectra from all 594 serum samples. Machine investigations carried out using the Scikit-Learn library and implemented Python, characteristics of positive negative extracted Uniform Manifold Approximation Projection (UMAP) technique. models k-Nearest Neighbors (kNN), Support Vector (SVM), Decision Trees (DTs), logistic regression (LR), Light Gradient Boosting (LightGBM). kNN model led sensitivity 0.943, specificity 0.9275, accuracy 0.9377. study showed that combining spectroscopy algorithm can be effective diagnostic method. Furthermore, we highlighted advantages disadvantages each algorithm, providing valuable information for future research.

Language: Английский

Citations

0