Impact of poor dental health on pneumonia

Identifying oral disease variables associated with pneumonia emergence by application of machine learning to integrated medical and dental big data to inform eHealth approaches

Background

The objective of this study was to build models that define variables contributing to pneumonia risk by applying supervised Machine Learning-(ML) to medical and oral disease data to define key risk variables contributing to pneumonia emergence for any pneumonia/pneumonia subtypes.

Methods

Retrospective medical and dental data were retrieved from Marshfield Clinic Health System's data warehouse and integrated electronic medical-dental health records (iEHR). Retrieved data were pre-processed prior to conducting analyses and included matching of cases to controls by (a) race/ethnicity and (b) 1:1 Case: Control ratio. Variables with >30% missing data were excluded from analysis. Datasets were divided into four subsets: (1) All Pneumonia (all cases and controls); (2) community (CAP)/healthcare associated (HCAP) pneumonias; (3) ventilator-associated (VAP)/hospital-acquired (HAP) pneumonias and (4) aspiration pneumonia (AP). Performance of five algorithms were compared across the four subsets: Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests. Feature (input variables) selection and ten-fold cross validation was performed on all the datasets. An evaluation set (10%) was extracted from the subsets for further validation. Model performance was evaluated in terms of total accuracy, sensitivity, specificity, F-measure, Mathews-correlation-coefficient and area under receiver operating characteristic curve (AUC).

Results

In total, 6,034 records (cases and controls) met eligibility for inclusion in the main dataset. After feature selection, the variables retained in the subsets were: All Pneumonia (n = 29 variables), CAP-HCAP (n = 26 variables); VAP-HAP (n = 40 variables) and AP (n = 37 variables), respectively. Variables retained (n = 22) were common across all four pneumonia subsets. Of these, the number of missing teeth, periodontal status, periodontal pocket depth more than 5 mm and number of restored teeth contributed to all the subsets and were retained in the model. MLP outperformed other predictive models for All Pneumonia, CAP-HCAP and AP subsets, while SVM outperformed other models in VAP-HAP subset.

Conclusion

This study validates previously described associations between poor oral health and pneumonia. Benefits of an integrated medical-dental record and care delivery environment for modeling pneumonia risk are highlighted. Based on findings, risk score development could inform referrals and follow-up in integrated healthcare delivery environment and coordinated patient management.

Improving oral health in people with severe mental illness (SMI): A systematic review

BACKGROUND

Those with severe mental illness (SMI) are at greater risk of having poor oral health, which can have an impact on daily activities such as eating, socialising and working. There is currently a lack of evidence to suggest which oral health interventions are effective for improving oral health outcomes for people with SMI.

AIMS

This systematic review aims to examine the effectiveness of oral health interventions in improving oral health outcomes for those with SMI.

METHODS

The review protocol was registered with PROSPERO (ID CRD42020187663). Medline, EMBASE, PsycINFO, AMED, HMIC, CINAHL, Scopus and the Cochrane Library were searched for studies, along with conference proceedings and grey literature sources. Titles and abstracts were dual screened by two reviewers. Two reviewers also independently performed full text screening, data extraction and risk of bias assessments. Due to heterogeneity between studies, a narrative synthesis was undertaken.

RESULTS

In total, 1462 abstracts from the database search and three abstracts from grey literature sources were identified. Following screening, 12 studies were included in the review. Five broad categories of intervention were identified: dental education, motivational interviewing, dental checklist, dietary change and incentives. Despite statistically significant changes in plaque indices and oral health behaviours as a result of interventions using dental education, motivational interviewing and incentives, it is unclear if these changes are clinically significant.

CONCLUSION

Although some positive results in this review demonstrate that dental education shows promise as an intervention for those with SMI, the quality of evidence was graded as very low to moderate quality. Further research is in this area is required to provide more conclusive evidence.

Is dental caries associated with lower respiratory tract infections?

Design This study comprised an analysis of data from a cohort, born in the Finnish city of Espoo between January 1 1984 and March 31 1990.Objectives The objective of the study was to investigate the effect of dental caries on the risk of lower respiratory tract infections (LRTI) in participants aged 20-27, using data collected during the 20-year follow-up conducted in 2010-2011.Data Dental caries experience was determined by asking study participants 'Estimate, how many teeth with a filling you have?' LRTI was defined as at least one occurrence in the 12 months prior to the administration of the 20-year questionnaire. LTRI data were obtained by asking participants if they had suffered from influenza or pneumonia, bronchitis, bronchiolitis or unspecified lower respiratory tract infection. In addition, data were obtained from the National Hospital Discharge Register. Risk ratios were determined using Poisson regression models.Results Having a high number of filled teeth was associated with an increased number of LRTIs (adjusted relative risk 1.24) and was not modified by the family's socioeconomic status or by smoking.Conclusions The authors suggest that dental caries increases the risk of LRTIs, but concede that common risk factors might explain at least partly the observed relation between filled teeth and LRTIs.

Association between oral health and incidence of pneumonia: a population-based cohort study from Korea

Pneumonia is related to oral health of the elderly and intensive care unit patients. However, studies on the relationship between overall oral health and pneumonia in the general population have been limited. The purpose of this study was to investigate the association between oral health and pneumonia using a nationwide population-based Korean cohort database. Data from 122,251 participants who underwent health screening and oral examinations in 2004 or 2005 were analyzed. Cox proportional hazard regression analysis was performed to evaluate the association between oral health and pneumonia. The risk of pneumonia increased significantly in groups with a higher number of dental caries and missing teeth, with respective adjusted hazard ratios (HRs) and 95% confidence interval (CI) of 1.265 (1.086–1.473; p = 0.0025) and 1.218 (1.113–1.332; p < 0.0001), and decreased significantly in frequent tooth brushing and regular professional dental cleaning groups, with respective adjusted HRs and 95% CI of 0.853 (0.786–0.926; p = 0.0001) and 0.920 (0.855–0.990; p = 0.0255). In addition, regardless of age and comorbidities, oral health status and oral hygiene behaviors were associated with pneumonia. The results indicate that improved oral health may reduce the risk of pneumonia in the general population.