Refine
Document Type
- Article (1)
- Doctoral Thesis (1)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- periodontal disease (2) (remove)
Institute
Publisher
Prediction models learn patterns from available data (training) and are then validated on new data (testing). Prediction modeling is increasingly common in dental research. We aimed to evaluate how different model development and validation steps affect the predictive performance of tooth loss prediction models of patients with periodontitis. Two independent cohorts (627 patients, 11,651 teeth) were followed over a mean ± SD 18.2 ± 5.6 y (Kiel cohort) and 6.6 ± 2.9 y (Greifswald cohort). Tooth loss and 10 patient- and tooth-level predictors were recorded. The impact of different model development and validation steps was evaluated: 1) model complexity (logistic regression, recursive partitioning, random forest, extreme gradient boosting), 2) sample size (full data set or 10%, 25%, or 75% of cases dropped at random), 3) prediction periods (maximum 10, 15, or 20 y or uncensored), and 4) validation schemes (internal or external by centers/time). Tooth loss was generally a rare event (880 teeth were lost). All models showed limited sensitivity but high specificity. Patients’ age and tooth loss at baseline as well as probing pocket depths showed high variable importance. More complex models (random forest, extreme gradient boosting) had no consistent advantages over simpler ones (logistic regression, recursive partitioning). Internal validation (in sample) overestimated the predictive power (area under the curve up to 0.90), while external validation (out of sample) found lower areas under the curve (range 0.62 to 0.82). Reducing the sample size decreased the predictive power, particularly for more complex models. Censoring the prediction period had only limited impact. When the model was trained in one period and tested in another, model outcomes were similar to the base case, indicating temporal validation as a valid option. No model showed higher accuracy than the no-information rate. In conclusion, none of the developed models would be useful in a clinical setting, despite high accuracy. During modeling, rigorous development and external validation should be applied and reported accordingly.
Chronic infections, including periodontal infections, may reduce lung function. To date, there are hardly any population-based studies evaluating the association between periodontitis and lung function. However, there are some studies that used variables associated with obstructive pulmonary diseases (FEV1, FEV1/FVC). Thus, we aimed to assess the potential association of periodontal diseases with lung volumes and airflow limitation in the population-based Study of Health in Pomerania (SHIP). Of 3300 participants aged 25-85 years of the 5-year follow-up (SHIP-1), 1809 subjects participated in lung function examinations. 1465 subjects were included in the analyses. Lung function was measured using spirometry, body plethysmography, helium dilution, and diffusing capacity for carbon monoxide. Periodontal status was assessed by clinical attachment loss, probing depth, and number of missing teeth. Linear regression models using fractional polynomials were used to assess linear and non-linear associations between periodontal disease and lung function adjusting for confounders. Adjusting for age, sex, waist circumference, physical activity, diabetes, asthma, and time between core and pulmonary examination, mean attachment loss was significantly associated with variables of dynamic and static lung volumes, airflow limitation and hyperinflation. Total lung capacity and diffusing capacity for carbon monoxide were not associated with mean attachment loss. Adjustment for smoking and height considerably changed coefficients indicating profound confounding. Including fibrinogen and high sensitive CRP into fully adjusted models did not change coefficients of mean attachment loss. Restricted to never smokers, mean attachment loss was significantly associated with FEV1, FVC, and RV/TLC. Relations with lung function were confirmed for mean probing depth, extent measures of attachment loss/probing depth, and number of missing teeth. Periodontal disease was significantly associated with decreased lung function. Systemic inflammation did not provide a mechanism linking both diseases. However, cohort studies evaluating lung function in the current manner are needed to confirm results from this study and to assess a causal relationship. Furthermore, it needs to be investigated with the help of randomized clinical trials whether prevention or treatment of periodontitis might have a beneficial impact on lung function.