A Network-Medicine Framework for Intra-Oral Comorbidity: Age-Stratified Clustering and Quasi-Causal Progression Modeling from Outpatient Electronic Health Records.
Source: PubMed, NCBI / U.S. National Library of Medicine
Network medicine has reshaped how systemic comorbidities are quantified, but the internal comorbidity structure of oral diseases remains undescribed at four-character ICD-10 granularity. A total of 2,863,671 outpatient visit records from 583,614 patients (2011-2025) were analyzed. Using ICD-10 four-character codes (75 disease nodes), comorbidity networks were constructed for five age strata, with edges selected by relative risk (RR) > 1.5 and Bonferroni-corrected Fisher's exact tests. Patient-level longitudinal sequences were mined for progression trajectories, and quasi-causal analyses-Cox regression, negative outcome controls, and Baron-Kenny mediation-were used to evaluate pathway directionality and specificity. The all-age network contained 75 nodes and 167 edges (modularity = 0.53), forming eight communities. Network complexity peaked at 18-29 years and declined with age. Dental caries emerged as the strongest hub in the 60+ stratum (degree = 9). Cox regression adjusted for age, sex, and healthcare utilization confirmed pathway directionality (pulpitis → tooth defect: hazard ratio (HR) = 2.65; caries → pulpitis: HR = 2.25), and negative outcome controls confirmed biological specificity. Mediation analysis showed that pulpitis completely mediated the caries → tooth defect association (proportion mediated ≈ 100%; 95% confidence interval (CI), 90-128%). An oral mucosal immune cluster (burning mouth syndrome, lichen planus, candidiasis, and xerost
Abstract
Network medicine has reshaped how systemic comorbidities are quantified, but the internal comorbidity structure of oral diseases remains undescribed at four-character ICD-10 granularity. A total of 2,863,671 outpatient visit records from 583,614 patients (2011-2025) were analyzed. Using ICD-10 four-character codes (75 disease nodes), comorbidity networks were constructed for five age strata, with edges selected by relative risk (RR) > 1.5 and Bonferroni-corrected Fisher's exact tests. Patient-level longitudinal sequences were mined for progression trajectories, and quasi-causal analyses-Cox regression, negative outcome controls, and Baron-Kenny mediation-were used to evaluate pathway directionality and specificity. The all-age network contained 75 nodes and 167 edges (modularity = 0.53), forming eight communities. Network complexity peaked at 18-29 years and declined with age. Dental caries emerged as the strongest hub in the 60+ stratum (degree = 9). Cox regression adjusted for age, sex, and healthcare utilization confirmed pathway directionality (pulpitis → tooth defect: hazard ratio (HR) = 2.65; caries → pulpitis: HR = 2.25), and negative outcome controls confirmed biological specificity. Mediation analysis showed that pulpitis completely mediated the caries → tooth defect association (proportion mediated ≈ 100%; 95% confidence interval (CI), 90-128%). An oral mucosal immune cluster (burning mouth syndrome, lichen planus, candidiasis, and xerostomia) emerged as a clinically actionable community. Oral diseases form biologically coherent, age-evolving comorbidity communities, and pulpitis is the critical mediating intervention point in the caries-to-tooth-defect cascade. The framework provides a reusable network-medicine substrate for age- and sex-specific risk-stratified oral disease management.