Automated Machine Learning to Develop Predictive Models of Metabolic Syndrome in Patients with Periodontal Disease

Metabolic syndrome is experiencing a concerning and escalating rise in prevalence today. The link between metabolic syndrome and periodontal disease is a highly relevant area of research. Some studies have suggested a bidirectional relationship between metabolic syndrome and periodontal disease, where one condition may exacerbate the other. Furthermore, the existence of periodontal disease among these individuals significantly impacts overall health management. This research focuses on the relationship between periodontal disease and metabolic syndrome, while also incorporating data on general health status and overall well-being. We aimed to develop advanced machine learning models that efficiently identify key predictors of metabolic syndrome, a significant emphasis being placed on thoroughly explaining the predictions generated by the models. We studied a group of 296 patients, hospitalized in SCJU Sibiu, aged between 45-79 years, of which 57% had metabolic syndrome. The patients underwent dental consultations and subsequently responded to a dedicated questionnaire, along with a standard EuroQol 5-Dimensions 5-Levels (EQ-5D-5L) questionnaire. The following data were recorded: DMFT (Decayed, Missing due to caries, and Filled Teeth), CPI (Community Periodontal Index), periodontal pockets depth, loss of epithelial insertion, bleeding after probing, frequency of tooth brushing, regular dental control, cardiovascular risk, carotid atherosclerosis, and EQ-5D-5L score. We used Automated Machine Learning (AutoML) frameworks to build predictive models in order to determine which of these risk factors exhibits the most robust association with metabolic syndrome. To gain confidence in the results provided by the machine learning models provided by the AutoML pipelines, we used SHapley Additive exPlanations (SHAP) values for the interpretability of these models, from a global and local perspective. The obtained results confirm that the severity of periodontal disease, high cardiovascular risk, and low EQ-5D-5L score have the greatest impact in the occurrence of metabolic syndrome.

Saliva pH and Flow Rate in Patients with Periodontal Disease and Associated Cardiovascular Disease

BACKGROUND Periodontal disease, a frequent oral health problem, is connected with cardiovascular morbidity and mortality. This study aimed to assess the unstimulated saliva flow rate and saliva pH as markers of the severity of periodontal disease in patients with cardiovascular disease. MATERIAL AND METHODS A cohort of 155 patients (78 men and 77 women, aged 30-92 years) was included, and a structured questionnaire obtained information about their health status, oral healthcare behaviors, and eating habits. An oral examination was performed to assess periodontal status and presence of dental calculus. The unstimulated whole salivary flow rate and salivary pH were measured. An oral hygienization was performed, and 3 months later, salivary flow rate and pH were reevaluated. RESULTS A severe form of periodontal disease was found in 22.4% of patients. Disease severity was strongly correlated with low pH values (6.25 in stage IV periodontal disease), lower salivary flow rate (0.28 mL/min), smoking, poor oral hygiene habits and obesity, with no significant differences by sex. We observed a significant increase of pH (up to 6.30±0.17) in patients with severe periodontal disease (P=0.001) and salivary flow rate values (0.29±0.07 mL/min; P=0.014) 3 months after oral hygienization. There was a strong association between the severity of periodontal disease and presence of cardiovascular disease (P=0.001). CONCLUSIONS Our study suggests that the decrease of salivary flow rate and pH level might be associated with the severity of periodontal disease.

Lovastatin and fluvastatin reduce viremia and the pro-inflammatory cytokines in the patients with chronic hepatitis C

BACKGROUNDS/AIMS

Certain statins interfere with the mechanism of the hepatitis C virus replication. We aimed at studying the effect of statins on the level of viremia and of the pro-and anti-inflammatory cytokines in the patients with chronic hepatitis C.

METHODOLOGY

We took in our study all the patients with chronic hepatitis C placed in the evidence of the clinics of internal medicine of the Emergency County Clinical Hospitals of Braşov, Oradea and Sibiu, who had been identified with viremias. The patients were treated with fluvastatin 40 mg/day or lovastatin 20 mg/day for 28 days. The level of viremia, hemoleukogram, hepatic biochemical tests and the pro and anti-inflammatory hepatic cytokines were analysed before and after the treatment. The final results were compared with the initial ones, as well as between the 2 groups.

RESULTS

Regarding those 99 analysed patients, the initial average viremia was of 2376074 +/- 3427596 UI/ml, while the final one was of 1321136 +/- 1343570 UI/ml (p = 0.000987). Both, in the group treated with lovastatin, as well as in that treated with fluvastatin, the decrease of viremia was significant from the statistics point of view (p = 0.032, respectively p = 0.00092). Lovastatin administration resulted in the significant decrease of the pro-inflammatory cytokines IL-6 and TNF-alfa, while that of fluvastatin brought about the significant decrease of the serum levels of IL-6, IL-8 and TNF-alfa. There were no significant differences, statistically speaking, between the 2 determinations, regarding the levels of IL-10 (anti-inflammatory cytokine) and those of erythropoietin. Transaminases average level did not vary significantly after those 4 weeks of statins treatment.

CONCLUSIONS

Lovastatin and fluvastatin, significantly decrease the level of viremia, of IL-6 and TNF-alpha in the patients with chronic hepatitis C.