Life Image and Graticule Launch GLIMPS in the New AWS Data Exchange
Glimps (Graticule Life Image Machine Parsed Set) Is a de-Identified Patient Level Data Set Including a Summary of Features Generated from NLP Processing on Life Image Data
Life Image, one of the world’s largest medical evidence networks for clinical and imaging data, and its strategic partner, Graticule, an advanced real world data firm, announced the availability of GLIMPS (Graticule Life Image Machine Parsed Set) data licensing subscriptions in AWS Data Exchange, a new service that makes it easy for millions of Amazon Web Services (AWS) customers to securely find, subscribe to, and use third-party data in the cloud.
Graticule has published GLIMPS in the AWS Data Exchange. GLIMPS is a de-identified patient level data set including a summary of features generated from NLP processing from Life Image data, which has been de-identified using industry-leading tools with Life Image’s own expert determination service that uses a combination of human validators with a proprietary machine learning algorithm specifically designed to catch personal health information (PHI) that can be hiding within the image pixels or meta tags. The HIPAA-compliant repository of diagnostic images provides insights from a broad set of geographically-diverse providers in the U.S. that contain a rapidly growing cohort of 140,000 patients, 360,000 studies, and 92 million de-identified images. Because much of the important data in imaging is stored in unstructured reports or within images, it is difficult to construct queries to identify studies with features of interest to solve researcher questions. GLIMPS provides a safe, structured view of the patient-level medical information by providing coded values using open vocabularies such as ICD9 or SNOMED to execute feasibility analysis.
“Diagnostic images and radiology reports contain interpretations and other information that provide rich diagnostic and outcomes data but have historically been extremely difficult to access and aggregate at scale,” said Dan Housman, CTO and Co-founder of Graticule. “AWS Data Exchange provides a sea change opportunity that allows us to distribute our data to provide a transparent view of available images and tools to deliver deeper data insights on demand.”
The goal of GLIMPS is to provide a cost-effective patient level snapshot to biopharma data science teams to fuel the necessary discussions about these data, leading to sourcing broad curated sets or building artificial intelligence (AI) models to answer high value questions. The GLIMPS data model includes key fields from DICOM headers and a machine parsed mapping created using multiple medical Natural Language Processing (NLP) tools. Custom extraction approaches provide an additional deeper layer of clinical context using measurable values such as Ejection Fraction within echocardiograms. The data model was built to be compatible with the OHDSI (Observational Health Data Sciences and Informatics) Common Data Model to rapidly integrate into Real World Data tools used by Life Sciences companies and regulators.
Graticule provides data subscriptions and on-demand data collaborations to pharma clients to unlock the value in advanced real world data such as imaging, genomics, and free text notes. Graticule provides extensions to technologies with mature adoption within health systems to eliminate IT overhead and to accelerate the data collaboration process. Graticule is focused on curating data resources and applications for Neurology, Cardiology, Oncology and Rare Diseases. Uses of Graticule data by life sciences clients include machine learning model development, biomarker development, clinical trial recruitment, and identification of undiagnosed patients.
Life Image is the world’s largest medical evidence network providing access to points of care and curated clinical and imaging data. It is the only company in the market today with Real World Imaging™ that provides large-scale, heterogeneous, de-identified imaging sets that are linkable to other longitudinal data.