Using machine learning algorithms to investigate factors associated with complete edentulism among older adults in the United States.

AIMS: Edentulism is an incapacitating condition, and its prevalence is unequal among different population groups in the United States (US) despite its declining prevalence. This study aimed to investigate the current prevalence, apply Machine Learning (ML) Algorithms to investigate factors associated with complete tooth loss among older US adults, and compare the performance of the models. METHODS: The cross-sectional 2020 Behavioral Risk Factor Surveillance System (BRFSS) data was used to evaluate the prevalence and factors associated with edentulism. ML models were developed to identify factors associated with edentulism utilizing seven ML algorithms. The performance of these models was compared using the area under the receiver operating characteristic curve (AUC). RESULTS: An overall prevalence of 11.9% was reported. The AdaBoost algorithm (AUC = 84.9%) showed the best performance. Analysis showed that the last dental visit, educational attainment, smoking, difficulty walking, and general health status were among the top factors associated with complete edentulism. CONCLUSION: Findings from our study support the declining prevalence of complete edentulism in older adults in the US and show that it is possible to develop a high-performing ML model to investigate the most important factors associated with edentulism using nationally representative data.

Investigating the relationship between cancer and orofacial clefts using GWAS significant loci for cancers: A case-control and case-triad study.

Background: Several population-based case-control studies have reported concurrent presentation of cancer and congenital malformations. Many associations have been made between oral clefting and cancers, though some of these results are conflicting. Some studies have reported an increased risk of cancer among 1st-degree relatives of cleft cases and vice versa, and also an excess risk of cancers of the breast, lung, and brain among those with oral clefts. This study aimed to determine if the genetic polymorphisms found in some cancers are also associated with orofacial cleft in an African cohort. Methods: The study was a case-control and case-triad study in which cases were 400 individuals clinically diagnosed with non-syndromic cleft lip and/or palate (CL/P), while controls were 450 individuals without CL/P. Samples were obtained from three African countries while DNA extraction, PCR, and genotyping were carried out at the University of Iowa, US. Eleven SNPs in genes coding for SWI/SNF subunits and 13 GWAS significant SNPs for cancers associated with orofacial cleft were selected. Case-control analysis, transmission disequilibrium test (TDT), and DFAM to combine the parent-offspring trio data and unrelated case/control data in a single analysis were carried out using PLINK. Results: For the case-control analyses that included all the clefts and for the CLP subtype, none of the SNPs were statistically significant. Statistically increased risk for the following SNPs rs34775372 (p = 0.02; OR = 1.54, CI:1.07-2.22), rs55658222 (p = 0.009; OR = 2.64, CI:1.28-5.45) and rs72728755 (p = 0.02; OR=2.27, CI:1.17-4.45) was observed with the CL only sub-group. None of these were significant after Bonferoni correction. In the TDT analyses, a significantly reduced risk with rs10941679 (p = 0.003; OR = 0.43, CI:0.24-0.75) was observed and this was significant after Bonferroni correction. The rs10941679 was also significant (p = 0.003) in the DFAM analyses as well even after Bonferroni correction. Conclusion: The results from this study represent an important starting point for understanding the concurrent presentation of some cancers in orofacial clefts, and cancer risks in cleft patients. The associations observed warrant further investigation in a larger cohort and will set the stage for a more mechanistic approach toward understanding the risk for cancers in families with clefts.