The data MDPortals extracts from a wide range of disparate sources comes in a variety of incompatible and unstructured formats. MDPortals synthesis engine prepares the ingested data for use with analysis tools and point-of-care guidance by transforming the raw inputs into a clean and reliable picture of a patients’ health.
The MDPortals synthesis engine utilizes OCR, advanced parsing techniques, Clinical Natural Language Processing (cNLP), proprietary logic and NPI matching to clean, de-duplicate and enrich all structured and unstructured inputs from data acquisition.
Faxed records, free-text physician notes, scanned charts and other unstructured inputs are converted into machine-readable text and mapped to the appropriate section in the patient’s structured record.
100+ normalization steps are applied to raw inputs to grade completeness & syntax;
Our code-mapping techniques leverage advanced cNLP terminology tools to recognize millions of permutations for clinical concepts;
The data is processed against over 30,000+ terminology mappings and clinical terms are into industry-standard classification, reference and billing terminologies for all major clinical domains (Allergies, Encounters, Medications, Immunizations, Payers, Problems, Procedures, Results & Vital Signs);
Support for all national standard vocabularies: CVX, CPT, HL7, ICD-9, ICD-10, LOINC, RxNorm, SNOMED, UCUM, NDC and UNII;
Mapping of SNOMED to ICD10 codes;
Inconsistent diagnosis, procedure, medication, and lab data from diverse systems are standardized into common, clinically validated terminology;
Context-sensitive information model produces more robust, consumable data than achieved with common parsing techniques.
Duplicate records, redundancies and inconsistencies are eliminated;
Precise matching techniques ensures data extracted from multiple systems is consistent and complete.
Multi-factor EHR identification with brand-specific extraction, parsing and classification;
Drug classification (NDF-RT) and ingredient decomposition for multi-ingredient drugs;
Problem classification (CCS);
Ontology and category assignment.
Infers missing medical concepts including:
Core ingredient decomposition for combination medications;
Medication dose form, dose strength, frequency, route and preconditions;
Laboratory interpretation and reference ranges;
Dates of services & type (ambulatory, emergency, inpatient);
Problem duration and resolution;
Error-fixing: automated correction of common vocabulary and syntax mistakes.
Addition of meta-data for streamlined analytics such as:
Laboratory result classification;
Allergy type classification;
Problem and diagnosis groupings;
All inputs from data acquisition are unified into the Compendium C-CDA, an enhanced composite longitudinal record in C-CDA format.