Comprehensive clinical entity extraction NLP pipeline - ICD, SNOMED, RxNorm, NDC, LOINC, HCPCS, more

**Overview**
IMO’s Comprehensive Clinical NLP pipeline is injected with more than 30 years of managed terminology and expert systems to enahce accuracy and true coded intent of entites extracted. Formerly known as MelaxTech's CLAMP and LANN pipeline and annotation development platforms are now joined with IMO's expert system managed terminology services, the IMO NLP pipelines provide the most scalable, robust and easily deployable entity extraction with assertion status solution in the industry. The NLP pipeline outputs all relevant metadata related to the entity extracted including standards-based coding, body system location, and other informatics-based data operations important for healthcare data operations.

This comprehensive pipeline recognizes four primary clinical entity types and also understands assertion status and temporality from clinical notes:

- **Medical problems** – Also known as diagnosis, problems, symptoms, and adverse events. The breath of medical problems could include biomedical, clinical, claims, genomic, and patient lexicon representations. For example “MI” in context with a pediatric patient will tag “Mitral incompetence” and include all appropriate metadata attached like ICD10CM(s), SNOMED(s), HCC, body location, etc.
- **Medications**- Includes generic and brand-specific terminology variations, form, dosage, strength, route, duration, and frequency. The code set resolution of medication entities extracted also includes RxNorm, NDC, and others upon request.
- **Treatments**– These are also known as procedures and include both observational and orderable procedures. The entity extraction breath of treatments includes anything you can order, perform, have a history of, or charge during an encounter, and includes many local colloquialisms used across healthcare including an understanding of local lab batteries. The code set resolution of procedure entities extracted also include ICD10PCS, CPT, HCPCS, LOINC, SNOMED, CVx, and others upon request.
- **Labs**– These Lab entities also include any variation of both order and result representation. The breadth of entity extraction labs includes batteries, large lab provider compendia representation, local laboratory support, specimen representation, and result range understanding. The code set resolution of labs extracted also includes ICD10PCS, CPT, LOINC, and SNOMED.
- **Assertion Status** – Metadata related to entity extraction will include assertion status like “negation,” “severity,” “uncertainty,” “condition,” “subject,” and “body location” for “medical problems;” (2) “form,” “dosage,” “strength,” “route,” “duration,” and “frequency” for “medications;” (3) “negation” for “treatments;” and (4) “negation” and “value” for “lab tests.”
- **Temporality**– Time delineation metadata also known as temporal information associated with primary entities is extracted.

**Use cases**

- In both bulk and transactional data operations, the Comprehensive Clinical NLP pipeline can run concurrent NLP entity extraction and analysis pipelines. The pipelines have been trained on more than 30 years of clinical terminology understanding across well over 10,000 deployments in multiple different use cases. IMO’s NLP pipeline development operations and can easily be tuned to meet the changing and scalable needs of our customers.
- Comprehensive entity extraction for Review of Systems (RoS), Physical Exam (PE), Ambient Encounter Summarization (AES), Discharge Summary (DS), Adverse Event (AE) and many others.

**Product details**

- IMO’s Comprehensive Clinical Pipeline and underlying NLP and entity extraction solutions are an award-winning operation which leverages more than 30 years of terminology experience to extract meaningful concepts and seamlessly map these entities to all appropriate standard codes. This leads to a more quickly deployed, trustworthy, accurate and usable dataset in a fraction of a time with less high-cost FTE People power.
- Comprehensively map structured and unstructured data to all appropriate standard codes (Including ICD10, ICD9, SNOMED, DSM5TR, LOINC, CPT, HCPCS, DRG, CVx, RxNorm, NDC, and more).
- Standardize diagnosis, problems, symptoms, adverse events, procedures, medications, and lab data from various systems
- Ensures specific and accurate coding to optimize downstream data uses
- Processes up to 300,000 terms per minute per node deployment
- Intuitive interface to review, accept and adjust matched data as needed
- Proven industry pipeline development platform (CLAMP) is now owned by IMO and offers updated out-of-the-box pipelines for use in the Comprehensive Clinical Pipeline
- Data processed through IMO’s Comprehensive Clinical Pipeline is updated at least monthly to make sure you don't lose any sleep over miscoding or under-coding during regulatory updates
- Deploy locally, on cloud, or through SAAS connection points
- Please reach out with any questions

**Additional Insights**
Read more about IMO's NLP pipelines at