NAVIGATION
    • Home
    • Cancer Information Data Trust

Cancer Information Data Trust

A multi-institutional, multi-modal, big data repository

Cancer Information Data Trust

A Comprehensive Cancer Information Data Trust for education, research, pharma and clinical activities

Leveraging the data and information derived from its cancer diagnostics workflow solution, Inspirata® is developing a multi-institutional, multi-modal database of cancer signatures cross-referenced to clinical treatment protocols and patient outcomes. This big data initiative will provide a wide range of users, including educators, physicians, patients, administrators, researchers and pharma, with curated and structured data related to diagnostic decision support, treatment options, prognostic information and population health metrics to help improve outcomes for cancer patients.

CIDT Diagram

The Cancer Information Data Trust (CIDT) is a big data repository of curated, structured and de-identified patient information and diagnostic data collected from various cancer centers (including whole slide images, radiographs and other diagnostic images). Applying sophisticated data analytics, Inspirata will be able to provide an “identity card” for a tumor based on large data stores collected on similar tumors. The CIDT will then provide information to the user in the form of a visual interpretive report.

The objective is to run analytics on this data to gain insights to make better decisions for patients and cancer treatment in general.

The CIDT uses big data analytics to unlock real-world patient information from various cancer centers and deliver the de-identified insights to educators, physicians, researchers, patients, pharma and others.

  • Monitor clinical quality measures
  • Identify a group of anonymous patients with shared (common) characteristics
  • Match patients with clinical research trials
  • Present trends that can help improve care
  • Leverage Content-Based Image Retrieval (CBIR) to match images to archived images for use in predictive analytics, prognostics and therapeutics
  • Provide personalized patient timeline (longitudinal information) in a visual snapshot of a patient’s treatments, side effects and outcomes
  • Convert unstructured data formats (pdf documents, etc.) into structured formats for natural language queries (NLP Engine)

 NLP Engine

Inspirata understands the value of structured, minable data. Our Natural Language Processing (NLP) engine is available as a tool for structuring a wide variety of unstructured data formats for reporting or research purposes. Leveraging the NLP within our data lake provides our CIDT with high quality de-identified data linked together with images, forming a unique and useful repository for the stakeholders it serves.

Careers

Explore opportunities to grow your career and make a difference with Inspirata.

Learn More
Academic Research Projects

Learn more about sponsored research for academic institutions.

Learn More
Meet Our CEO

Get to know Satish Sanan, the visionary behind Inspirata.

Learn More