The use of diverse types of healthcare information, ranging from medical images to genomic data, is typically a challenge to biomedical research, but a vendor is announcing the development of a platform intended to ease that process.

BioSymetrics is setting its sights on facilitating data analytics by launching a platform that prepares diverse types of data for analytical efforts.

It’s announcing the launch of Augusta, a proprietary technology that enables standardized processing and integration of diverse raw data types, with the intent of facilitating rapid deployment of artificial intelligence projects in precision medicine, health data applications and drug discovery.

The platform provides more than 150 modules for the processing of raw MRI, ECG/EEG, EMR, genomic and metabolomics data.

The platform grew out of the company’s years of work in machine learning, says Gabriel Musso, BioSymetrics’ chief scientific officer. “We spent a lot of time processing data, normalizing data, getting it ready for the process of applying machine learning,” he says. “That’s the most laborious part of doing analytics projects in machine learning, and that’s what we’re trying to automate and standardize.”

Gabriel Musso
Gabriel Musso

Much of the development for Augusta came as BioSymetrics came as it was doing research in autism and Alzheimer’s disease, he says, which involved a lot of effort in processing medical images and other medical data before actual analysis could begin. “We’ve sought to address this need by designing an easily deployable, automated pre-processing framework that can take multiple data types from source, process them, integrate them, and apply machine learning, all in a data-driven way,” he adds.

Specific benefits of Augusta include:

• Integrated analytics and machine learning solutions that can integrate large repositories of images, genomics data, streaming data and compounds.

• Modular and customizable pipelines for processing raw phenotypic, imaging, drug and genomic data types using any combination of datasets.

• Automated model optimization based on a proprietary parameter iteration method.

• Scalable solution architecture for enterprise and cloud computing applications that can be deployed anywhere (cloud services such as Microsoft Azure, AWS; and private or local servers.

• Fully dockerized distributed infrastructure that eliminates the need for transfer of sensitive data.

Musso says the platform is most likely to assist research efforts by healthcare organizations and pharmaceutical companies. It’s currently be pilot tested by Orb Care, a Toronto-based health cloud company that has health information on about 1 million Canadians.

Register or login for access to this item and much more

All Health Data Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access