PRIMARY CARE CHALLENGES IN LABORATORY-SUPPORTED ORAL DIAGNOSIS: CONTRIBUTIONS OF FAMILY PHYSICIANS AND NURSING HEALTH CARE ASSISTANTS TO MEDICAL CODING QUALITY

Abstract

Background: Oral mucosal lesions constitute a significant yet often overlooked burden in primary care, with a prevalence of approximately 16.8% in general practice populations. The standard of care currently relies on the Physician-Only Coding Model [Intervention 2], where family physicians are solely responsible for the simultaneous visualization, diagnosis, and administrative coding of these complex pathologies. This conventional approach is limited by high cognitive load, resulting in a documented 13.8% coding error rate and widespread use of low-utility "unspecified" ICD-10 codes (e.g., K13.79), which degrade clinical data quality and revenue integrity. Team-Based Documentation and Digital Support [Intervention 1], utilizing Health Care Assistants (HCAs), medical scribes, and telediagnosis tools, has emerged as a promising alternative to mitigate these errors and improve data granularity.

Objective: The primary aim of this systematic review is to systematically compare the effectiveness of Team-Based Documentation and Digital Support [Intervention 1] versus the conventional Physician-Only Coding Model [Intervention 2] on medical coding accuracy, documentation quality, and diagnostic precision for Primary Care Providers [Population] managing Oral Mucosal Lesions [Condition].

Methods: We conducted a systematic search of PubMed, MEDLINE, Embase, CINAHL, and the Cochrane Library for studies published between 2015 and 2024. The review included randomized controlled trials, observational cohort studies, and quality improvement audits following the PICO framework. Primary outcomes included ICD-10 coding accuracy rates, frequency of omission errors, and documentation completeness. Secondary outcomes included revenue impact (claim denials) and clinician satisfaction. The review adhered to PRISMA 2020 guidelines, and risk of bias was assessed using QUADAS-2 and the Newcastle-Ottawa Scale.

Results: The search identified 30 eligible data sources, including key randomized trials and large-scale audits. The synthesis reveals that Intervention 1 significantly outperforms Intervention 2. Studies indicate that medical scribe support improves chart accuracy with an Odds Ratio (OR) of 4.61 compared to unassisted physicians. Targeted educational interventions for staff reduced coding risk errors by 37.9%. Furthermore, telediagnosis integration reduced the "intention to refer" by 63.8%, effectively replacing generic symptom codes with definitive diagnostic codes at the point of care. Conversely, the physician-only model was associated with a "satisficing" heuristic, where 25% of required secondary codes were omitted.

Conclusion: The Team-Based Documentation and Digital Support model demonstrates superior effectiveness in improving medical coding quality and diagnostic data integrity compared to the standalone physician model. Integrating Health Care Assistants and digital tools into the diagnostic workflow not only reduces administrative burden but also ensures that the "digital twin" of the patient accurately reflects their clinical reality. Implications for clinical practice in Primary Care Settings include the recommended adoption of scribe-assisted documentation and structured laboratory reporting standards. Future research should focus on the cost-benefit analysis of AI-driven coding assistants in low-resource settings.