Modeling longitudinal oral health status and pneumonia risk: secondary data analyses of an integrated dental-medical cohort.

BACKGROUND: Mounting evidence indicates potential associations between poor oral health status (OHS) and increased pneumonia risk. Relative pneumonia risk was assessed in the context of longitudinally documented OHS. METHODS: Electronic medical/dental patient data captured from 2007 through 2019 were retrieved from the integrated health records of Marshfield Clinic Health Systems. Participant eligibility initiated with an assessment of OHS, stratified into the best, moderate, or worst OHS groups, with the additional criterion of 'no pneumonia diagnosis in the past 90 days'. Pneumonia incidence was longitudinally monitored for up to 1 year from each qualifying dental visit. Models were assessed, with and without adjustment for prior pneumonia incidence, adjusted for smoking and subjected to confounding mitigation attributable to known pneumonia risk factors by applying propensity score analysis. Time-to-event analysis and proportional hazard modeling were applied to investigate relative pneumonia risk over time among the OHS groups. RESULTS: Modeling identified associations between any incident pneumonia subtype and 'number of missing teeth' (p < 0.001) and 'clinically assessed periodontal status' (p < 0.01), which remained significant following adjustment for prior pneumonia incidence and smoking. The hazard ratio (HR) for 'any incident pneumonia' in the best OHS group for 'number of missing teeth' was 0.65, 95% confidence interval (CI) [0.54 - 0.79] (unadjusted) and 0.744, 95% CI [0.61 - 0.91] (adjusted). The HR for 'any incident pneumonia' in the best 'clinically assessed periodontal status' group was 0.72, 95% CI [0.58 - 0.90] (unadjusted) and 0.78, 95% CI [0.62 - 0.97] (adjusted). CONCLUSION/CLINICAL RELEVANCE: Poor OHS increased pneumonia risk. Proactive attention of medical providers to patient OHS and health literacy surrounding oral-systemic disease association is vital, especially in high-risk populations.

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.