API Catalog

Context-Aware Extraction (CAE) transforms unstructured clinical notes into structured clinical data by extracting and normalizing problems and procedures. Outputs are mapped to clinician-friendly IMO lexical terms and relevant clinical coding systems, supporting reimbursement, analytics, quality measurement, and other downstream healthcare workflows. Clinical terminology included in each domain are the following: ICD-10-CM, ICD-9-CM, SNOMED CT and IMO lexical for the problem domain. CPT (Current Procedural Terminology), HCPCS (Healthcare Common Procedure Coding System), ICD-10-PCS, and IMO lexical for the procedure domain.

The De-Identification API provides capabilities to identify and obfuscate Protected Health Information (PHI) in unstructured clinical text. It exposes a two-step flow: a PHI Identification endpoint that extracts PHI entities using IMO's Named Entity Recognition models, and a PHI Obfuscation endpoint that redacts or replaces those entities according to a configurable per-entity policy. Together these endpoints support HIPAA Safe Harbor de-identification workflows.

The Clinical Comprehensive Pipeline API uses natural language processing (NLP) models to convert raw clinical notes into a computable dataset of entities resolved to standardized and coded terms.