Periodontal disease, a prevalent oral health condition, is characterized by the inflammation and destruction of the supporting tissues around the teeth and poses significant challenges to global public health. Objectives: To examine the association between the oral microbiome and periodontal disease progression in a Pakistani population. Methods: A total of 350 patients aged ≥ 18 years, diagnosed with periodontal disease, were registered from August 2023 to February 2024. Participants were evaluated for periodontal health indicators, including probing depth and clinical attachment loss, and their oral microbiome profiles were analyzed using high-throughput sequencing of the 16S rRNA gene. Machine learning algorithms, including Random Forest and Support Vector Machines, were applied to predict disease progression based on microbial profiles. Results: Porphyromonas gingivalis and Tannerella forsythia were strongly associated with greater probing depths and clinical attachment loss (β = 0.45, p < 0.01), indicating their role in disease progression. Conversely, Streptococcus and Lactobacillus were linked to reduced disease severity (β = -0.30, p < 0.05). The oral microbiome exhibited high diversity, with Firmicutes (35%), Bacteroidetes (25%), Proteobacteria (20%), and Actinobacteria (15%) being the predominant species. The Random Forest model predicted disease progression with 85% accuracy (Area under the curve (AUC) = 0.87), emphasizing the predictive value of microbial profiles. Conclusions: It was concluded that the study confirms a strong link between specific oral microbiota and periodontal disease progression, emphasizing the importance of microbial analysis in predicting and managing periodontal health.
Read full abstract