Exploring AI-Driven Machine Learning Approaches for Optimal Classification of Peri-Implantitis Based on Oral Microbiome Data: A Feasibility Study

Background: Machine learning (ML) techniques have been recently proposed as a solution for aiding in the prevention and diagnosis of microbiome-related diseases. Here, we applied auto-ML approaches on real-case metagenomic datasets from saliva and subgingival peri-implant biofilm microbiomes to explore a wide range of ML algorithms to benchmark best-performing algorithms for predicting peri-implantitis (PI). Methods: A total of 100 metagenomes from the NCBI SRA database (PRJNA1163384) were used in this study to construct biofilm and saliva metagenomes datasets. Two AI-driven auto-ML approaches were used on constructed datasets to generate 100 ML-based models for the prediction of PI. These were compared with statistically significant single-microorganism-based models. Results: Several ML algorithms were pinpointed as suitable bespoke predictive approaches to apply to metagenomic data, outperforming the single-microorganism-based classification. Auto-ML approaches rendered high-performing models with Receiver Operating Characteristic–Area Under the Curve, sensitivities and specificities between 80% and 100%. Among these, classifiers based on ML-driven scoring of combinations of 2–4 microorganisms presented top-ranked performances and can be suitable for clinical application. Moreover, models generated based on the saliva microbiome showed higher predictive performance than those from the biofilm microbiome. Conclusions: This feasibility study bridges complex AI research with practical dental applications by benchmarking ML algorithms and exploring oral microbiomes as foundations for developing intuitive, cost-effective, and clinically relevant diagnostic platforms.