What Sets Us Apart

The emtelliPro deep learning NLP engine and powerful development tools automate and simplify data collection and analysis across clinical systems, specialties, and patient populations to uncover meaningful insights from within your medical data. We do this by:

Effectively combining deep expertise in health informatics, clinical knowledge, and NLP and deep-learning. We believe that the combination of these disciplines is critical to the success of all medical NLP projects.

Providing a ‘one stop shop’ of specialists. Our team includes computer engineers and researchers specializing in NLP algorithms and machine learning, clinicians, medical annotators, systems engineers and data analysts, all working together to enable fast turnaround of custom features, optimizations, and emtelliPro deployments.

Supporting multiple use-case patterns:
 

• Non-interactive, non-realtime use cases - e.g. data extraction for biomedical research applications.

• Non-interactive, soft-real-time use cases - e.g. automated identification of reports for manual review.

• Interactive use cases - e.g. integration with EMRs for highlighting of terms of interest.

Measuring success according to clinically relevant output. By that we mean that the quality of the extracted data meets the needs of real-world clinical and research applications, as defined by the customer.

Delivering out-of-the box features for medical NLP extraction. In addition to entity recognition, the emtelliPro features highly accurate negation and uncertainty attribute extraction, and a variety of features such as medications, measurements, qualifiers, follow-up recommendations and radiology image links.

Addressing high-value use cases across the healthcare continuum including hospitals and health systems, medical imaging organizations, payer organizations, clinical researchers, technical integrators, and more.

​Working closely with customers to articulate a clear and well-defined understanding of the project data requirements and ensuring the system is appropriately configured and tuned for its intended purpose.

Designing with extensibility and

tuning in mind:
 

• A modular design supports addition of custom features, document types, and vocabularies (ontologies).

• An internal toolchain enables fast integration of custom annotations and iterative quality assurance.

​Meeting customer’s data governance requirements. In addition to emtelligent-hosted implementations, customer-hosted implementations are possible.