This study aims to demonstrate the use of the tree-based machine learning algorithms to predict the 3- and 5-year disease-specific survival of oral and pharyngeal cancers (OPCs) and compare their performance with the traditional Cox regression. A total of 21,154 individuals diagnosed with OPCs between 2004 and 2009 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Three tree-based machine learning algorithms (survival tree (ST), random forest (RF) and conditional inference forest (CF)), together with a reference technique (Cox proportional hazard models (Cox)), were used to develop the survival prediction models. To handle the missing values in predictors, we applied the substantive model compatible version of the fully conditional specification imputation approach to the Cox model, whereas we used RF to impute missing data for the ST, RF and CF models. For internal validation, we used 10-fold cross-validation with 50 iterations in the model development datasets. Following this, model performance was evaluated using the C-index, integrated Brier score (IBS) and calibration curves in the test datasets. For predicting the 3-year survival of OPCs with the complete cases, the C-index in the development sets were 0.77 (0.77, 0.77), 0.70 (0.70, 0.70), 0.83 (0.83, 0.84) and 0.83 (0.83, 0.86) for Cox, ST, RF and CF, respectively. Similar results were observed in the 5-year survival prediction models, with C-index for Cox, ST, RF and CF being 0.76 (0.76, 0.76), 0.69 (0.69, 0.70), 0.83 (0.83, 0.83) and 0.85 (0.84, 0.86), respectively, in development datasets. The prediction error curves based on IBS showed a similar pattern for these models. The predictive performance remained unchanged in the analyses with imputed data. Additionally, a free web-based calculator was developed for potential clinical use. In conclusion, compared to Cox regression, ST had a lower and RF and CF had a higher predictive accuracy in predicting the 3- and 5-year OPCs survival using SEER data. The RF and CF algorithms provide non-parametric alternatives to Cox regression to be of clinical use for estimating the survival probability of OPCs patients.

Background: Increased attention has been focused on the associations of periodontal disease with the onset and progression of cognitive impairment. Although the associations are likely to be multifactorial, few studies have explored the role of mitochondrial dysfunction in the periodontitis‐dementia link.Methods: Cross‐sectional data of 1,883 participants aged ≥60 years in the National Health and Nutrition Examination Survey 2011‒2014 were analyzed. The following data were collected: 1) general information on sociodemographic, behavioral, and health‐related factors; 2) periodontal status (mean attachment loss [AL] and mean probing depth [PD]); 3) mitochondrion‐derived biomarker of mitochondrial dysfunction (blood sample concentration of methylmalonic acid [MMA]); 4) cognitive function (Consortium to Establish a Registry for Alzheimer's disease immediate recall [CERAD‐IR] and delay recall [CERAD‐DR], animal fluency test, and digit symbol substitution test [DSST]). Mediation analysis weighted for complex survey design was used to assess the effect of MMA on the association of periodontal status with cognitive function after adjusting for potential confounders.Results: Participants with Stage III and IV periodontitis had lower scores on cognitive performance and higher MMA levels than those with Stages I/II periodontitis. Circulating MMA was significantly associated with CERAD‐DR (weighted β [SE] = −0.076 [0.011]) and DSST (weighted β [SE] = −0.039 [0.009]), which mediated 9.9% and 6.0% of the total association of mean PD with cognitive function. Moreover, MMA mediated 11.7% and 5.8% of the association of mean AL with CERAD‐DR and DSST, respectively.Conclusion: The findings suggest that MMA, a biomarker of mitochondrial dysfunction, plays a mediating role in the link between periodontitis and cognitive impairment in older adults aged ≥60 years.

The relationship between periodontitis and cardiovascular disease (CVD) has been extensively studied, but the role of biological aging in this relationship remains poorly understood. This study is dedicated to investigating the effect of periodontitis on the incidence of CVD and to elucidating the potential mediating role of biological aging. Furthermore, this study will seek to elucidate the causal association between periodontitis, CVD, and biological aging. We included 3269 participants from the National Health and Nutrition Examination Survey (2009–2014) with diagnostic information on periodontitis and composite CVD events. Biological aging was evaluated by utilizing both the Klemera–Doubal method’s calculated biological age (KDMAge) and phenotypic age (PhenoAge). Logistic regression, restricted cubic spline (RCS) analysis, and subgroup analysis were used for data analysis. Mediation analysis was employed to explore the mediating role of biological aging. Subsequently, Mendelian randomization (MR) analyses were performed using genome-wide association study databases to explore potential causal relationships between periodontitis, CVD, and biological aging. Periodontitis was associated with a higher risk of CVD. Participants with periodontitis were found to have increased levels of biological aging, and elevated levels of biological aging were associated with increased CVD risk. Mediation analyses showed a partial mediating effect of biological aging (PhenoAge: 44.6%; KDMAge: 22.9%) between periodontitis and CVD risk. MR analysis showed that periodontitis played a causal role in increasing the risk of small vessel stroke, while myocardial infarction was found to increase the risk of periodontitis. In addition, reverse MR analysis showed that phenotypic aging can increase the risk of periodontitis, and there is a two-way causal relationship between CVD and biological aging. Periodontitis is associated with an increased CVD risk, partially mediated by biological aging, with a complex causal interrelationship. Targeted interventions for periodontal health may slow the biological aging processes and reduce CVD risk.

The prevalence of periodontitis is increasing with the aging of the global population. Periodontitis has been suggested to accelerate aging and increase mortality. The present nationwide prospective cohort study aimed to determine whether periodontitis could modify the association of biological aging with all-cause and cause-specific mortality in middle-aged and older adults. Participants ≥40 y of age from the Third National Health and Nutrition Examination Survey (NHANES III) were included ( n = 6,272). Phenotypic age acceleration (PhenoAgeAccel) was used to evaluate the biological aging process. Moderate/severe periodontitis was defined using a half-reduced Centers for Disease Control and Prevention and American Academy of Periodontology case definition. Multivariable Cox proportional hazard regression was conducted to estimate the association between PhenoAgeAccel and mortality risk, followed by effect modification analysis to test whether periodontitis modified the association. During a median follow-up of 24.5 y, 3,600 (57.4%) deaths occurred. The positive relationships between PhenoAgeAccel and all-cause and cause-specific mortality were nonlinear. After adjusting for potential confounders, the highest quartile of PhenoAgeAccel was associated with increased all-cause mortality in individuals with no/mild periodontitis (hazard ratio for Q4 vs. Q1 [HR _Q4vs.Q1 ] = 1.789; 95% confidence interval [CI], 1.541–2.076). In contrast, the association was enhanced in patients with moderate/severe periodontitis (HR _Q4vs.Q1 = 2.446 [2.100–2.850]). Periodontal status significantly modified the association between PhenoAgeAccel and all-cause mortality ( P for interaction = 0.012). In subgroup analyses, the modifying effect of periodontitis was observed in middle-aged adults (40–59 y), females, and non-Hispanic Whites. Although cause-specific mortality showed a similar trend, the PhenoAgeAccel × periodontitis interaction did not reach statistical significance. In conclusion, periodontitis might enhance the association of biological aging with all-cause mortality in middle-aged and older adults. Hence, maintaining and enhancing periodontal health is expected to become an intervention to slow aging and extend life span.

Recent efforts to improve the reliability and efficiency of scientific research have caught the attention of researchers conducting prediction modeling studies (PMSs). Use of prediction models in oral health has become more common over the past decades for predicting the risk of diseases and treatment outcomes. Risk of bias and insufficient reporting present challenges to the reproducibility and implementation of these models. A recent tool for bias assessment and a reporting guideline—PROBAST (Prediction Model Risk of Bias Assessment Tool) and TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis)—have been proposed to guide researchers in the development and reporting of PMSs, but their application has been limited. Following the standards proposed in these tools and a systematic review approach, a literature search was carried out in PubMed to identify oral health PMSs published in dental, epidemiologic, and biostatistical journals. Risk of bias and transparency of reporting were assessed with PROBAST and TRIPOD. Among 2,881 papers identified, 34 studies containing 58 models were included. The most investigated outcomes were periodontal diseases (42%) and oral cancers (30%). Seventy-five percent of the studies were susceptible to at least 4 of 20 sources of bias, including measurement error in predictors (n = 12) and/or outcome (n = 7), omitting samples with missing data (n = 10), selecting variables based on univariate analyses (n = 9), overfitting (n = 13), and lack of model performance assessment (n = 24). Based on TRIPOD, at least 5 of 31 items were inadequately reported in 95% of the studies. These items included sampling approaches (n = 15), participant eligibility criteria (n = 6), and model-building procedures (n = 16). There was a general lack of transparent reporting and identification of bias across the studies. Application of the recommendations proposed in PROBAST and TRIPOD can benefit future research and improve the reproducibility and applicability of prediction models in oral health.