Artificial Neural Networks for the Diagnosis of Aggressive Periodontitis Trained by Immunologic Parameters

Abstract

There is neither a single clinical, microbiological, histopathological or genetic test, nor combinations of them, to discriminate aggressive periodontitis (AgP) from chronic periodontitis (CP) patients. We aimed to estimate probability density functions of clinical and immunologic datasets derived from periodontitis patients and construct artificial neural networks (ANNs) to correctly classify patients into AgP or CP class. The fit of probability distributions on the datasets was tested by the Akaike information criterion (AIC). ANNs were trained by cross entropy (CE) values estimated between probabilities of showing certain levels of immunologic parameters and a reference mode probability proposed by kernel density estimation (KDE). The weight decay regularization parameter of the ANNs was determined by 10-fold cross-validation. Possible evidence for 2 clusters of patients on cross-sectional and longitudinal bone loss measurements were revealed by KDE. Two to 7 clusters were shown on datasets of CD4/CD8 ratio, CD3, monocyte, eosinophil, neutrophil and lymphocyte counts, IL-1, IL-2, IL-4, INF-γ and TNF-α level from monocytes, antibody levels against A. actinomycetemcomitans (A.a.) and P.gingivalis (P.g.). ANNs gave 90%–98% accuracy in classifying patients into either AgP or CP. The best overall prediction was given by an ANN with CE of monocyte, eosinophil, neutrophil counts and CD4/CD8 ratio as inputs. ANNs can be powerful in classifying periodontitis patients into AgP or CP, when fed by CE values based on KDE. Therefore ANNs can be employed for accurate diagnosis of AgP or CP by using relatively simple and conveniently obtained parameters, like leukocyte counts in peripheral blood. This will allow clinicians to better adapt specific treatment protocols for their AgP and CP patients.

P. gingivalis lipopolysaccharide intensifies inflammation post-myocardial infarction through matrix metalloproteinase-9

“…There are four main causal risk factors: 1) the subgingival microbiota, 2) individual genetic variations, 3) life style, and 4) systemic factors [5]. The link between periodontitis and CVD are thought to be caused by inflammatory mechanisms initiated by bacteria, associated with periodontal lesions [6].…”

Artificial intelligence: A dentist's perspective

“…[14] ANN can also effectively be used in classifying patients into aggressive periodontitis and chronic periodontitis group based on their immune response profile. [15] When it comes down to implementing ANN in clinical practice, it has sufficient precision for the design and chairside manufacturing of dental prostheses, based on digital image acquisition following tooth cusps assessment. [16] It can have a great potential in investigating the properties of dental materials such as chemical stability, wear resistance, and flexural strength.…”

Decision support systems for adoption in dental clinics: A survey

“…ANN attempts to simulate the non-linear processing pattern of the human brain and is a very powerful tool for generalising acquired knowledge and data analysis by interweaving artificial neurons across input, hidden and output layers. For example, Papantonopoulos et al (2014) used ANN for periodontal disease diagnosis and to classify patients according to their immune responses. ANN was also applied to support decisions on implant placements, where the system mimicked choices made by implant experts (Sadighpour et al, 2014).…”