Early Tooth Loss after Periodontal Diagnosis: Development and Validation of a Clinical Decision Model

Abstract

The aim of this study was to develop and validate a predictive early tooth loss multivariable model for periodontitis patients before periodontal treatment. A total of 544 patients seeking periodontal care at the university dental hospital were enrolled in the study. Teeth extracted after periodontal diagnosis and due to periodontal reasons were recorded. Clinical and sociodemographic variables were analyzed, considering the risk of short-term tooth loss. This study followed the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines for development and validation, with two cohorts considered as follows: 455 patients in the development phase and 99 in the validation phase. As a result, it was possible to compute a predictive model based on tooth type and clinical attachment loss. The model explained 25.3% of the total variability and correctly ranked 98.9% of the cases. The final reduced model area under the curve (AUC) was 0.809 (95% confidence interval (95% CI): 0.629–0.989) for the validation sample and 0.920 (95% CI: 0.891–0.950) for the development cohort. The established model presented adequate prediction potential of early tooth loss due to periodontitis. This model may have clinical and epidemiologic relevance towards the prediction of tooth loss burden.

Systematic Review of Prognosis Models in Predicting Tooth Loss in Periodontitis

“…Among the studies focusing on model development, 21 did not report any correction for model overfitting or optimism, 5 used cross-validation (Schwendicke et al 2021; Dukka et al 2022; El Sayed et al 2022; Rahim-Wöstefeld et al 2022; Troiano et al 2022), 2 used bootstrapping (Ravidà et al 2020; Shi et al 2020), and 1 used temporal split sample validation (Santos et al 2021).…”

Deep learning improves prediction of periodontal therapy effectiveness in Chinese patients

“…Emerging scientific evidence has inspired the development of various periodontal risk assessment tools in calculating the probability of periodontitis progression 9,10 and tooth survival after therapy. 3,5,7,11 Most of these tools calculate the risk of tooth loss as either a continuous or an ordinal (categorical) variable. 16 The use of descriptive words like good, fair, or questionable can be perceived subjectively by clinicians due to heterogeneity in how definitions are interpreted and applied.…”

“…Emerging scientific evidence has inspired the development of various periodontal risk assessment tools in calculating the probability of periodontitis progression 9,10 and tooth survival after therapy 3,5,7,11 . Most of these tools calculate the risk of tooth loss as either a continuous or an ordinal (categorical) variable 16 .…”

“…Since the last century, a number of prognostic models and risk assessment tools 2,5–8 based on the abovementioned factors have been developed to calculate the probability of periodontitis progression 9,10 and to predict tooth survival after therapy 3,5,7,11 . However, the existing models have the following limitations: (1) most qualitative models 1,6,8,12 are empirically specified and grouped with no specific evidence of division 13 ; (2) the models were developed based on small samples and traditional statistical methods such as the COX proportional‐hazards model or logistic regression, which may lead to possible bias contributed from both sample selection and the multicollinearity between multiple factors at different levels 14 ; (3) and no model can predict the treatment outcome at a given time point after periodontal therapy.…”

“…4 Since the last century, a number of prognostic models and risk assessment tools 2,5-8 based on the abovementioned factors have been developed to calculate the probability of periodontitis progression 9,10 and to predict tooth survival after therapy. 3,5,7,11 However,…”