A Machine Learning Approach to Uncovering Hidden Utilization Patterns of Early Childhood Dental Care Among Medicaid-Insured Children

Abstract

Background: Early childhood dental care (ECDC) is a significant public health opportunity since dental caries is largely preventable and a prime target for reducing healthcare expenditures. This study aims to discover underlying patterns in ECDC utilization among Ohio Medicaid-insured children, which have significant implications for public health prevention, innovative service delivery models, and targeted cost-saving interventions.Methods: Using 9 years of longitudinal Medicaid data of 24,223 publicly insured child members of an accountable care organization (ACO), Partners for Kids in Ohio, we applied unsupervised machine learning to cluster patients based on their cumulative dental cost curves in early childhood (24–60 months). Clinical validity, analytical validity, and reproducibility were assessed.Results: The clustering revealed five novel subpopulations: (1) early-onset of decay by age (0.5% of the population, as early as 28 months), (2) middle-onset of decay (3.0%, as early as 35 months), (3) late-onset of decay (5.8%, as early as 44 months), (4) regular preventive care (67.7%), and (5) zero utilization (23.0%). Patients with early-onset of decay incurred the highest dental cost [median annual cost (MAC) = $9,499, InterQuartile Range (IQR): $7,052–$11,216], while patients with regular preventive care incurred the lowest dental cost (MAC = $191, IQR: $99–$336). We also found a plausible correlation of early-onset of decay with complex medical conditions diagnosed at 0–24 months. Almost one-third of patients with early-onset of decay had complex medical conditions diagnosed at 0–24 months. Patients with early-onset of decay also incurred the highest medical cost (MAC = $7,513, IQR: $4,527–$12,546) at 0–24 months.Conclusion: Among Ohio Medicaid-insured children, five subpopulations with distinctive clinical, cost, and utilization patterns were discovered and validated through a data-driven approach. This novel discovery promotes innovative prevention strategies that differentiate Medicaid subpopulations, and allows for the development of cost-effective interventions that target high-risk patients. Furthermore, an integrated medical-dental care delivery model promises to reduce costs further while improving patient outcomes.

Dental Caries in Medicaid-Insured Preschool Children With or Without Special Health Care Needs in Northeast Ohio

“…For example, in a recent study of nearly 24 000 Medicaid-insured children in Ohio, children with complex medical conditions accounted for nearly one-third of those with early-onset decay, incurring nearly 10-fold greater costs in care. 26 However, the significant doseresponse association in our data between prevalence of dental caries and complexity of chronic conditions, as well as the consistency of our findings across analyses, are suggestive that our finding is not spurious.…”

Characterization of Supragingival Plaque and Oral Swab Microbiomes in Children With Severe Early Childhood Caries

“…In recent years, machine learning has become a commonly applied approach to early childhood oral health research (Peng et al, 2021). One of the challenges in microbiome data analysis is that the differential analysis methods generally lack the information about predictability.…”

Prediction Models of Early Childhood Caries Based on Machine Learning Algorithms

“…Considering oral diseases can have adverse effects on the development of permanent teeth, a healthy oral environment during early childhood is essential for determining one's oral health for a lifetime [5]. Therefore, the prevention of ECC is highly necessary for children to maintain their oral health, a healthy life, and reduced medical costs [6]. Although a sharp decline in ECC was observed in Korea until the early 2000s due to the efforts of academia and clinicians, there has been an increase since 2016 [7].…”

“…Conversely, ML has the disadvantage of requiring massive datasets with high-quality data for training. Another major challenge is the ability to interpret results generated by ML models properly [6].…”