A Predictive Model for Primary Care Providers to Identify Children at Greatest Risk for Early Childhood Caries

Area of Science:

• Pediatric Dentistry
• Public Health
• Health Informatics

Background:

• Early childhood caries (ECC) poses a significant public health challenge.
• Integrating risk assessment into primary care well-child visits can improve early detection.
• Existing screening methods may not seamlessly fit into pediatric workflows.

Purpose of the Study:

• To develop and validate an ECC risk-screening tool for primary care provider (PCP) well-child workflows.
• To identify key predictors of ECC in infants and toddlers.
• To enable timely intervention for high-risk children.

Main Methods:

• Utilized integrated health records to build a predictive model for ECC risk.
• Trained the model on 2,009 patients with well-child visits and dental appointments.
• Validated the model independently on 880 children aged 18-48 months.

Main Results:

• Age at first dental visit strongly predicted caries risk (OR=2.11).
• Key risk factors identified: breastfeeding status, non-English preferred language, and high pediatric clinic no-show rates.
• Children with three non-age risk factors seen at 18 months had a 42% probability of caries; this rose to 83% if first seen at four years.

Conclusions:

• Existing clinical documentation and a validated predictive model facilitate effective ECC risk assessment during well-child visits.
• Early identification and intervention are crucial for mitigating ECC.
• The tool can be integrated into routine pediatric care to improve oral health outcomes.