Using Machine Learning and Silver Nanoparticle-Based Surface-Enhanced Raman Spectroscopy for Classification of Cardiovascular Disease Biomarkers.

Characterizing complex biofluids using surface-enhanced Raman spectroscopy (SERS) coupled with machine learning (ML) has been proposed as a powerful tool for point-of-care detection of clinical disease. ML is well-suited to categorizing otherwise uninterpretable, patient-derived SERS spectra that contain a multitude of low concentration, disease-specific molecular biomarkers among a dense spectral background of biological molecules. However, ML can generate false, non-generalizable models when data sets used for model training are inadequate. It is thus critical to determine how different SERS experimental methodologies and workflow parameters can potentially impact ML disease classification of clinical samples. In this study, a label-free, broadband, Ag nanoparticle-based SERS platform was coupled with ML to assess simulated clinical samples for cardiovascular disease (CVD), containing randomized combinations of five key CVD biomarkers at clinically relevant concentrations in serum. Raman spectra obtained at 532, 633, and 785 nm from up to 300 unique samples were classified into physiological and pathological categories using two standard ML models. Label-free SERS and ML could correctly classify randomized CVD samples with high accuracies of up to 90.0% at 532 nm using as few as 200 training samples. Spectra obtained at 532 nm produced the highest accuracies with no significant increase achieved using multiwavelength SERS. Sample preparation and measurement methodologies (e.g., different SERS substrate lots, sample volumes, sample sizes, and known variations in randomization and experimental handling) were shown to strongly influence the ML classification and could artificially increase classification accuracies by as much as 27%. This detailed investigation into the proper application of ML techniques for CVD classification can lead to improved data set acquisition required for the SERS community, such that ML on labeled and robust SERS data sets can be practically applied for future point-of-care testing in patients.

Publication Trends in Exosomes Nanoparticles for Cancer Detection.

BACKGROUND: Exosomes are small vesicles produced by almost all cells in the body and found in all biofluids. Cancer cell-derived exosomes are known to have distinct, measurable signatures, applicable for early cancer diagnosis. Despite the present bibliometric studies on "Cancer detection" and "Nanoparticles", no single study exists to deal with "Exosome" bibliometric study. METHODS: This bibliometric work investigated the publication trends of "Exosomes" nanoparticles and its application in cancer detection, for the literature from 2008 to July 2019. The data were collected from the Web of Science Core Collection. There were variant visual maps generated to show annual publication, most- relevant authors, sources, countries, topics and keywords. The network analysis of these studies was investigated to evaluate the research trends in the field of exosomes. In addition, the data were qualitatively analyzed according to 22 top-cited articles, illustrating the frequently used subjects and methods in exosomes research area. RESULTS: The results showed that the documents in this field have improved the citation rate. The top-relevant papers are mostly published in Scientific Reports journal which has lost its popularity after 2017, while today, Analytical Chemistry is leading in publishing the most articles related to exosomes. The documents containing keywords of plasma, cells, cancer, biomarkers, and vesicles as keywords plus, are more likely to be published in PLoS One journal. The clustering of the keywords network showed that the keyword theme of "extracellular vesicles" has the highest centrality rate. In global research, USA is the most corresponding country, followed by China, Korea and Australia. Based on the qualitative analysis, the published documents with at least 50 citations have used exosome release, cargo, detection, purification and secretion, as their targets and applied cell culture or isolation as their methods. CONCLUSION: The bibliometric study on exosomes nanoparticles for cancer detection provides a clear vision of the future research direction and identifies the potential opportunities and challenges. This may lead new researchers to select the proper subfields in exosome-related research fields.

Publication Trends in Drug Delivery and Magnetic Nanoparticles.

This bibliometric study investigated the public trends in the fields of nanoparticles which is limited to drug delivery and magnetic nanoparticles' literature published from 1980 to October 2017. The data were collected from the Web of Science Core Collections, and a network analysis of research outputs was carried out to analyse the research trends in the nanoparticles literature. Nanoparticles and its applications are progressing in recent years. The results show that documents in the field of nanoparticles in chemistry and material science have improved in citation rate, as the authors were researching in multidisciplinary zones. Top-cited documents are mainly focusing on drug delivery, magnetic nanoparticles and iron oxide nanoparticles which are also the top research keywords in all papers published. Top-cited papers are mostly published in Biomaterials journal which so far has published 12% of top-cited articles. Although research areas such as contrast agents, quantum dots, and nanocrystals are not considered as the top-ranked keywords in all documents, these keywords received noticeable citations. The trends of publications on drug delivery and magnetic nanoparticles give a general view on future research and identify potential opportunities and challenges.