Automating 100K+ Medical Codes for Faster Reimbursement

Overview

CodaMetrix's AI-powered Contextual Coding Automation Platform, CMX CARE, automatically translates clinical documentation into billable medical codes, processing over 300K patient encounters daily on the Databricks Data + AI Platform. The company reduced manual coding by 70%, cut coding-related denials by 60%, improved operational efficiency by 40%, and lowered AWS compute costs by 30%.

The challenge

CodaMetrix needed a solution to provide stronger observability and governance for managing sensitive protected health information (PHI) and evolving code sets. Before adopting Databricks, CodaMetrix struggled with disjointed systems that required engineers to either bring models to the data or vice versa, lacked observability and governance controls critical for compliance with SOC 2 and HIPAA standards, and lacked a reliable method for querying petabyte-scale datasets while managing a constantly evolving set of over 100,000 medical codes.

The solution

By leveraging the Databricks Data + AI Platform, CodaMetrix has unified pipelines and automated compliance workflows. Delta Lake provides the storage foundation for analytics and ML use cases, Lakeflow Jobs and Spark Declarative Pipelines handle large-scale data ingestion and transformation, MLflow manages model experimentation, versioning, deployment and serving, and Unity Catalog enforces fine-grained access controls and data lineage tracking. CodaMetrix also leverages AI/BI Genie, enabling medical coders and technical researchers to explore data using natural language, and integrates with electronic health record systems like Epic for automated billing.

Reported business value

CodaMetrix has cut model delivery time from weeks to days, improved efficiency by 40%, and lowered compute costs by 30%. Since adopting the platform, the team has reduced manual coding by 70% and coding-related denials by 60%.