Developing a periodontal disease antibody array for the prediction of severe periodontal disease using machine learning classifiers
Journal of Periodontology Aug 16, 2019
Huang W, Wu J, Mao Y, et al. - Using machine learning classifiers, researchers simultaneously and quantitatively evaluated the expression levels of 20 periodontal disease-related proteins in gingival crevicular fluid (GCF) from normal controls (NOR) and severe periodontitis (SP) individuals with an antibody array. To create a periodontal disease antibody array, antibodies against 20 periodontal disease-related proteins were spotted onto a glass slide. The array was then incubated from 25 NOR and 25 SP patients with GCF samples collected. According to results, seven proteins (CRP, IL-1α, IL-1β, IL-8, MMP-13, Osteoprotegerin, Osteoactivin) in patients with SP were significantly upregulated compared with NOR, whereas RANK was significantly downregulated. For IL-1β with an area under the curve of 0.984, the highest diagnostic accuracy was observed using a receiver operator characteristic curve. As important classification characteristics, five of the proteins (IL-1β, IL-8, MMP-13, Osteoprotegerin, Osteoactivin) have been identified. In the five classification models that were tested, Linear Discriminant Analysis had the highest classification accuracy. This research shows the potential for diagnosing periodontal disease of antibody arrays.
Go to Original
Only Doctors with an M3 India account can read this article. Sign up for free or login with your existing account.
4 reasons why Doctors love M3 India
-
Exclusive Write-ups & Webinars by KOLs
-
Daily Quiz by specialty
-
Paid Market Research Surveys
-
Case discussions, News & Journals' summaries