Adverse drug event (ADE, ADR) NLP model for clopidogrel-induced bleeding events in free-text

**Overview**

- IMO’s adverse event NLP model focuses on contributions of different features and types of adverse events. In particular, this model focuses on Aspirin or other Clopidogrel-induced bleeding events in large swaths of free-text clinical and patient-generated datasets.
- The model uses a hybrid approach that combines deep learning-based models, curated lexicons, and pattern-based rules applied to quickly build, maintain, and expand using the proven industry NLP development tool (CLAMP), now owned by IMO.
- The workflow can be repurposed for other use cases where existing clinical NLP tools need to be customized for specific information within a short time.

- The model extracts, analyzes, identifies, and interprets:
- Drug names inclusive of strength, route, frequency, form dose and duration
- Clinical diagnosis concepts, related symptoms, and patient-reported event concepts
- Temporal objects including timing and event duration representation between bleeding and clopidogrel event
- Clinical assertion from physician notes

**Publications**
- [A comparative study of different methods for automatic identification of clopidogrel-induced bleedings in electronic health records](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5543340/)

**Use Cases**
- Predicable and successful projects have been liked to both patient and clinician generated notes, but also biobanks linked to large EHR datasets
- Identifying patients with specific Adverse Drug Reactions (ADR) events in EHR, dictation, patient reported documentation and pathology lab datasets

**Product Details**
- Deploy trustworthy, accurate, and usable datasets in a fraction of a time, with fewer resources required from high-cost FTEs
- IMO’s adverse event NLP model, its pipeline, underlying NLP development platform, and named entity extraction solutions are award-winning operations that leverage more than 30 years of terminology experience
- The solution delivers high accuracy in extracting meaningful concepts and seamlessly mapping these entities to all appropriate standard codes.
- Comprehensively review extracted clinical entities and their relation to drugs names, connections to clinical diagnosis concepts, temporality of the events between them, and identify assertion status based on the clinician’s voice during documentation.
- Intuitive interface to review, accept, and adjust matched data as needed
- Proven pipeline development platform (CLAMP) is now owned by IMO and offers updated out-of-the-box NLP models to extract meaningful concepts, identifyconnections across those concepts to meaningful events, and ensure all entities are mapped to metadata important for entity resolution.
- Includes code mapping to RxNorm, NDC, ICD10CM, SNOMED, SNOMED US, etc.
- Data processed through this NLP model 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