MaxMD is excited to bring you MaxNLP™ powered by Wired Informatics, a scalable knowledge extraction engine to summarize any payload, including CCDs, exchanged via the Direct Protocol. Wired Informatics is a pioneer in clinical NLP. MaxNLP™ supplements MaxMD’s HISP with Invenio™ advanced clinical Natural Language Processing (NLP) platform which can parse bloated incoming or outgoing messages and develop precise clinical summaries of desired attributes and semantic types as requested by our clients.

MaxNLP™ can also identify context-based attributes such as Negation, Subject, Generic mentions, relationships, etc. contained in the unstructured text. Whenever a user sends or receives CCDA via Direct, or virtually any type of digital payload , MaxNLP™ will process the structured and unstructured data of the CCD to generate the summary in real-time and deliver it along with the original file. This allows the user to highlight relevant information for a possible Medicare patient whose CCD might be hundreds of pages long. Thus, MaxNLP™ offers a high degree of configurability and scalability to achieve business objectives when dealing with large volumes of clinical data. Ask us for a demonstration.



Supports Distributed Architecture & Parallel Processing

  • Scalability
  • Duraility

Provides Input/Output Customizations

  • Custom Outputs
  • Interface Adapters

Provides High Impact Annotators

  • Lab value extractor
  • Discrepancy extractor

Provides Value Added Services

  • Structured and Unstructured Data Search
  • Semantic Similarity Detection

For more information on Natural Language Processing please visit

Variety of Use Cases:

  • Clinical Intelligent Search
    1. Semantic search
  • Consolidated Clinical Document
    1. Automated creation of consolidated clinical document
  • Clinical Summarization and Audit
    1. Automated review of medical charts and procedures summaries
  • Clinical Chart Discrepancy Discovery
    1. Automated review of chart discrepancy
  • Cohort Discovery
    1. Automated discovery of patient cohorts