Mathematical and AI-Based Predictive Modelling for Dental Caries Risk Using Clinical and Behavioural Parameters

Area of Science:

• Dentistry
• Biomedical Engineering
• Data Science

Background:

• Dental caries is a prevalent global chronic disease.
• Caries development involves complex dietary, hygienic, and biological interactions.
• Accurate individual risk assessment is crucial for effective prevention.

Purpose of the Study:

• To develop and validate a hybrid predictive framework for estimating individual dental caries risk.
• To integrate mathematical modeling with artificial intelligence (AI) for enhanced risk prediction.
• To identify key determinants influencing caries development.

Main Methods:

• A first-order balance differential equation simulated demineralisation-remineralisation dynamics.
• A feed-forward artificial neural network (ANN) was trained on simulated and literature data.
• Individual risk was assessed using sugar intake, oral hygiene, salivary pH, fluoride exposure, age, and sex.

Main Results:

• The hybrid model achieved 91.2% accuracy and an AUC of 0.98 in risk classification.
• Sensitivity analysis revealed sugar intake and oral hygiene as primary risk factors.
• Salivary pH and fluoride exposure demonstrated protective effects against caries.

Conclusions:

• Combining mechanistic and data-driven approaches offers a feasible strategy for caries risk assessment.
• The developed framework supports intelligent, personalized screening tools in preventive dentistry.
• Early identification of high-risk individuals can improve preventive strategies.