Diabetes mellitus is a chronic disease characterized by hyperglycemia. It may cause many complications. According to the growing morbidity in recent years, in 2040, the world's diabetic patients will reach 642 million, which means that one of the ten adults in the future is suffering from diabetes. There is no doubt that this alarming figure needs great attention. With the rapid development of machine learning, machine learning has been applied to many aspects of medical health. In this study, we used decision tree, random forest and neural network to predict diabetes mellitus. The dataset is the hospital physical examination data in Luzhou, China. It contains 14 attributes. In this study, five-fold cross validation was used to examine the models. In order to verity the universal applicability of the methods, we chose some methods that have the better performance to conduct independent test experiments. We randomly selected 68994 healthy people and diabetic patients' data, respectively as training set. Due to the data unbalance, we randomly extracted 5 times data. And the result is the average of these five experiments. In this study, we used principal component analysis (PCA) and minimum redundancy maximum relevance (mRMR) to reduce the dimensionality. The results showed that prediction with random forest could reach the highest accuracy (ACC = 0.8084) when all the attributes were used.

/pdf/predicting-diabetes-mellitus-with-machine-learning-1nnh9wy811.pdf

Predicting Diabetes Mellitus With Machine Learning Techniques.

Diabetes is a chronic disease characterized by high blood sugar. It may cause many complicated disease like stroke, kidney failure, heart attack, etc. About 422 million people were affected by diabetes disease in worldwide in 2014. The figure will be reached 642 million in 2040. The main objective of this study is to develop a machine learning (ML)-based system for predicting diabetic patients. Logistic regression (LR) is used to identify the risk factors for diabetes disease based on p value and odds ratio (OR). We have adopted four classifiers like naive Bayes (NB), decision tree (DT), Adaboost (AB), and random forest (RF) to predict the diabetic patients. Three types of partition protocols (K2, K5, and K10) have also adopted and repeated these protocols into 20 trails. Performances of these classifiers are evaluated using accuracy (ACC) and area under the curve (AUC). We have used diabetes dataset, conducted in 2009–2012, derived from the National Health and Nutrition Examination Survey. The dataset consists of 6561 respondents with 657 diabetic and 5904 controls. LR model demonstrates that 7 factors out of 14 as age, education, BMI, systolic BP, diastolic BP, direct cholesterol, and total cholesterol are the risk factors for diabetes. The overall ACC of ML-based system is 90.62%. The combination of LR-based feature selection and RF-based classifier gives 94.25% ACC and 0.95 AUC for K10 protocol. The combination of LR and RF-based classifier performs better. This combination will be very helpful for predicting diabetic patients.

Classification and prediction of diabetes disease using machine learning paradigm

During the last two to three decades our understanding of the immunobiology of periodontal disease has increased exponentially, both with respect to the microbial agents triggering the disease process and the molecular mechanisms of the host engagement maintaining homeostasis or leading to collateral tissue damage. These foundational scientific findings have laid the groundwork for translating cell phenotype, receptor engagement, intracellular signaling pathways and effector functions into a 'picture' of the periodontium as the host responds to the 'danger signals' of the microbial ecology to maintain homeostasis or succumb to a disease process. These findings implicate the chronicity of the local response in attempting to manage the microbial challenge, creating a 'Double Indemnity' in some patients that does not 'insure' health for the periodontium. As importantly, in reflecting the title of this volume of Periodontology 2000, this review attempts to inform the community of how the science of periodontal immunology gestated, how continual probing of the biology of the disease has led to an evolution in our knowledge base and how more recent studies in the postgenomic era are revolutionizing our understanding of disease initiation, progression and resolution. Thus, there has been substantial progress in our understanding of the molecular mechanisms of host-bacteria interactions that result in the clinical presentation and outcomes of destructive periodontitis. The science has embarked from observations of variations in responses related to disease expression with a focus for utilization of the responses in diagnosis and therapeutic outcomes, to current investigations using cutting-edge fundamental biological processes to attempt to model the initiation and progression of soft- and hard-tissue destruction of the periodontium. As importantly, the next era in the immunobiology of periodontal disease will need to engage more sophisticated experimental designs for clinical studies to enable robust translation of basic biologic processes that are in action early in the transition from health to disease, those which stimulate microenvironmental changes that select for a more pathogenic microbial ecology and those that represent a rebalancing of the complex host responses and a resolution of inflammatory tissue destruction.

Periodontal disease immunology: 'double indemnity' in protecting the host.

For decades, Aggregatibacter actinomycetemcomitans has been considered the most likely etiologic agent in aggressive periodontitis. Implementation of DNA-based microbiologic methodologies has considerably improved our understanding of the composition of subgingival biofilms, and advanced open-ended molecular techniques even allow for genome mapping of the whole bacterial spectrum in a sample and characterization of both the cultivable and not-yet-cultivable microbiota associated with periodontal health and disease. Currently, A. actinomycetemcomitans is regarded as a minor component of the resident oral microbiota and as an opportunistic pathogen in some individuals. Its specific JP2 clone, however, shows properties of a true exogenous pathogen and has an important role in the development of aggressive periodontitis in certain populations. Still, limited data exist on the impact of other microbes specifically in aggressive periodontitis. Despite a wide heterogeneity of bacteria, especially in subgingival samples collected from patients, bacteria of the red complex in particular, and those of the orange complex, are considered as potential pathogens in generalized aggressive periodontitis. These types of bacterial findings closely resemble those found for chronic periodontitis, representing a mixed polymicrobial infection without a clear association with any specific microorganism. In aggressive periodontitis, the role of novel and not-yet-cultivable bacteria has not yet been elucidated. There are geographic and ethnic differences in the carriage of periodontitis-associated microorganisms, and they need to be taken into account when comparing study reports on periodontal microbiology in different study populations. In the present review, we provide an overview on the colonization of potential periodontal pathogens in childhood and adolescence, and on specific microorganisms that have been suspected for their role in the initiation and progression of aggressive forms of periodontal disease.

Microbiology of aggressive periodontitis

Periodontal diseases constitute one of the major global oral health burdens, and periodontitis remains a major cause of tooth loss in adults worldwide. The World Health Organization recently reported that severe periodontitis exists in 5-20% of adult populations, and most children and adolescents exhibit signs of gingivitis. Likely reasons to account for these prevalent diseases include genetic, epigenetic, and environmental risk factors, as well as individual and socio-economic determinants. Currently, there are fundamental gaps in knowledge of such fundamental issues as the mechanisms of initiation and progression of periodontal diseases, which are undefined; inability to identify high-risk forms of gingivitis that progress to periodontitis; lack of evidence on how to prevent the diseases effectively; inability to detect disease activity and predict treatment efficacy; and limited information on the effects of integration of periodontal health as a part of the health care program designed to promote general health and prevent chronic diseases. In the present report, 12 basic, translational, and applied research areas have been proposed to address the issue of global periodontal health inequality. We believe that the oral health burden caused by periodontal diseases could be relieved significantly in the near future through an effective global collaboration.

/pdf/global-oral-health-inequalities-task-group-periodontal-b11bg7janu.pdf

Global Oral Health Inequalities: Task Group—Periodontal Disease

Periodontal diseases are inflammatory and destructive diseases of the dentogingival complex associated with specific periodontal pathogens inhabiting periodontal pockets. Periodontal diseases lead to damage of the periodontal tissues supporting the teeth (bone and connective tissue) and affect the quality of life of the affected individuals: poor alimentation, tooth loss, social and financial problems. Although it is generally considered that the disease has multifactorial etiology, data show that some specific Gram-negative microorganisms in the subgingival plaque biofilm play a major role in the initiation and progression of periodontitis. Porphyromonas gingivalis, Treponema denticola and Tannerella forsythia form a consortium in the subgingival biofilm and are regarded as the principal periodontopathogenic bacteria. Other microorganisms that have been implicated as predominant species in the disease process are: Aggregatibacter actinomycetemcomitans, Fusobacterium nucleatum, Prevotella intermed...

Microbiology of Periodontal Diseases. A Review

This review examines literature data concerning the bacterial findings in chronic periodontitis depending on pocket depth, and presents the latest published information on the presence of proinflammatory factors in periodontal environment. It has been found that chronic periodontitis affects as much as 80% of the middle-aged population; by comparison, the prevalence of aggressive periodontitis reaches up to 1-1.5%. It is accepted that this social disease is multifactorial in etiology, but the evidence in the literature suggests that the levels of specific Gram-negative organisms in subgingival plaque biofilm play a major role in the initiation and progression of the disease. Of the many bacterial species inhabiting the periodontal environment, three types--Porphyromonas gingivalis (PG), Treponema denticola (TD), Tannerella forsythia (TF)--are strongly associated with the initiation and progression of periodontitis. Microbiological studies suggest that Porphyromonas gingivalis should be considered a major etiologic agent. Currently, Porphyromonas gingivalis is strongly associated with the pathogenesis of chronic periodontitis. On the other hand, the presence of Aggregatibacter actinomycetemeomitans in patients with chronic periodontitis may be related to the severity of the disease and thus modify the therapeutic plan. The increased amount of periodontal pathogens in the subgingival area can activate a cascade of defense mechanisms of the body associated with the production of factors causing inflammation and destruction, which suggests a correlation between the bacterial findings and the body response implemented by enhancing the local cytokine expression. Studies in the literature show that the presence of certain micro-organisms in the periodontal environment is associated to increased levels of proinflammatory cytokines in the gingival fluid and gingival tissue. These levels have been associated with destructive tissues response. There is little evidence in the literature on the correlation of the levels of periodontal pathogens of sites with different pocket depth with periodontal disease activity defined by the degree of the proinflammatory cytokine expression such as tumor necrosis factor alpha (TNF-α) and interleukin 6 (IL-6).

Subgingival microbial profile and production of proinflammatory cytokines in chronic periodontitis.

The aim of this paper is to perform optimization of photopolymerization process of dental composites in order to obtain maximum hardness. Samples (5 mm diameter; 2, 3 and 4 mm thickness) were made of Universal Composite (UC), Bulk fill Composite (BC) and Flowable Composite (FC). Light curing of specimens was performed with 600, 1000 and 1500 mW/cm2 light intensity and an irradiation time of 20, 40 and 60 s. Vickers microhardness on the top and bottom surfaces of samples was measured. Optimization was carried out via regression analysis using QStatLab software. Photopolymerization process parameters were calculated using a specially designed MatLab software-based algorithm. For all composites, regression models for hardness on top and bottom surfaces of composite layer were established. Layer thickness as well as hardness on top and bottom surfaces of each composite was calculated for 21 curing modes varying with light intensity and irradiation time. It was established that photopolymerization guidelines only of FC manufacturer guarantee the required hardness, while recommended regimes for UC and BC did not satisfy this requirement. Tables, containing recommended light curing regimes, were developed for three composite types, guaranteeing high hardness of composite restoration. They were designed to facilitate work of dentists in dental offices.

https://www.mdpi.com/2227-9717/9/5/779/pdf

Optimization of Photopolymerization Process of Dental Composites

Diabetes mellitus (DM) is a metabolic disease which affects many organs. Often in the oral cavity undergo changes that are associated with diabetes. Many dental practitioners are often not aware of the attendant oral manifestations in diabetic patients, which results in prescription of a non-accurate treatment. The aim of the review is to focus on main oral manifestations related to diabetes in order that the proper solution for treatment is to be taken. Untreated oral infections can adversely affect metabolic control. Patients may present with oral conditions that suggest undiagnosed diabetes: progressing severe periodontitis, enlarged gums which bleed easily, multiple periodontal abscesses. Diabetic patients with poor oral hygiene, a history of smoking, rare visits to dentists, high carbohydrate intake are more likely to present caries and periodontitis and to respond poorly to dental treatment. If the doctor suspects undiagnosed diabetes, the patient should be examined to reveal the history of polydipsia, polyuria, polyphagia, unexplained weight loss, and family history of diabetes.

/pdf/oral-cavity-and-systemic-diseases-diabetes-mellitus-18xcvsfazi.pdf

Oral Cavity and Systemic Diseases—Diabetes Mellitus

SUMMARY Viral hepatitis is a major public health problem, occurring endemically in all areas of the world. The prevalence of the disease is influenced by numerous factors which may be able to modulate its onset. The presence of HCV-RNA in saliva provides a biological basis for saliva as a possible source of HCV infection, although it does not necessarily imply transmission. Lock and coworkers (2006) demonstrates a contamination with HCV-RNA of a considerable portion of toothbrushes used by hepatitis C patients. Dentists were in a high risk of contracting this disease due to the procedures and instruments of dental treatment. Patients with liver disorders are of significant interest to the dentist because liver plays a vital role in metabolitic function, including the secretion of bile needed to fat absorption, conversion of sugar to glycogen, excretion of bilirubin, a waste product of hemoglobin metabolism. Impairment of liver function can lead to abnormalities of the metabolism of amino acid, protein, carbohydrates and lipid. Many biochemical function performed by the liver, such as synthesis of coagulation factors and drug metabolism, may be adversely affected. Viral hepatitis is the most common liver disorder and is a major public health problem, occurring endemically in all areas of the world. The prevalence of the disease is influenced by numerous factors which may be able to modulate its onset.

/pdf/hepatitis-b-and-c-in-dentistry-44ksgs1btm.pdf

Vladimir Panov

Papers

Microbiology of Periodontal Diseases. A Review

Subgingival microbial profile and production of proinflammatory cytokines in chronic periodontitis.

Optimization of Photopolymerization Process of Dental Composites

Oral Cavity and Systemic Diseases—Diabetes Mellitus

Hepatitis b and c in dentistry