At Inference Analytics, we are mimicking how the human brain understands language and images to extract critical insights
Neural Network Architecture
IANN’s deep learning based Natural Language Processing identifies information from text, narratives, and images using patterns similar to humans
Healthcare Corpus
IANN leverages a pre-trained healthcare auto-generated corpus and transfer learning to provide semantic meaning to healthcare terminology and images
Inference Engine
Unlike traditional NLP IANN functions more like
the human brain leveraging true semantic understanding of terms and images
IANN has been trained to assist in critical workflows for Radiology
Radiology Solutions
Auto Impression Assistant Allows radiologists to improve productivity and the quality of radiology reporting by suggesting tailored impression for dictations and highlighting errors such as laterality and gender mismatches. Available through Nuance and integrated directly into the Powerscribe platform.
Auto Annotation Assistant Uses our IANN infrastructure to annotate images by using reports. Report text is processed through our deep learning language models and annotations are created based on semantic understanding of each report. These annotations have a significant impact on AI model scalability, as reports are annotated in bulk, reducing the need for manual annotations.
Auto Protocoling Assistant Automates the process of protocoling for an upcoming exam, reducing the need for manual protocoling
Follow Up Manager Structures reports and identifies actionable follow up findings
Semantic Search Performs more powerful searches that are based on semantics, vs. traditional keyword searches. Facilitates research and identification of findings, analysis of reports, uncovering disease patterns, and assistance for identifying follow ups
Revenue Manager Identifies appropriate ICD-10 and CPT codes, helps to reduce claims rejections, streamlines FTE processes and reduces time needed to submit claims, and enhances compliance with federal billing regulations
Semantic Search
Inference Analytics Offers New Approach to Searches:
Standard Search A lexical search engine employing our word embedding model, and using our narrative cloud, that uses synonyms and related terminology to provide targeted reference materials
Research Search This is Semantic Search and is based on our proprietary ability to conceptualize text. This allows data searches, such as "Are there geographic variations in the rate of COVID-19 spread?". Results highlight the articles that relate to this question, without requiring specific, structured search terms
Revenue Manager
IANN at work to support Revenue Cycle Management
IANN has been trained to work within the revenue cycle management processes
Identifies appropriate ICD-10 codes by analyzing EMR information
Facilitates the revenue cycle process, reducing claims rejections, need for resubmission and lag time until payment
Enhances compliance with federal billing regulations
Readmission Risk Assistant
IANN has been trained to reduce the risk of readmission based on EMR data
Readmission of a patient within 30 days of discharge can result in penalties to the care provider
Understands narratives and unstructured information in notes to predict the risk of readmission with greater than 80% accuracy in testing performed
Guides optimal care and planning through application of this risk prediction algorithm during hospitalization
