Projects

Artemis is a cloud-based algorithmic platform that will track and record the physiological changes of neonatal infants. Personal health information collected at the bedside will be analyzed for the purpose of testing and validating Artemis as a real-time predictive analytics tool that can support clinical decision making for neonatal infants.

Cerebrum is a cardiovascular information reporting system that supports the integration of a variety of cardiac diagnostic and interventional discrete digital reporting software systems into an integrated modular plug and play suite of reporting products for use in Cardiac Centres provincially, nationally and internationally. New developments will include an inpatient management system, expansion of an information exchange portal and the development of a data repository for big data analytic applications.

A data analytics engine called Clinical Intelligence Engine™ (CIE) is being piloted at Southlake Regional Health Centre with the goal of identifying frequent users of Emergency Department services in order to reduce readmissions.

Dapasoft aims to develop a new and innovative commercial model to offer healthcare integration platform-as-a-service (iPaaS). The iPaaS will advance data and app integration, care collaboration solution and health analytics solutions. The project focus is to extend Dapasoft’s existing cloud solution to support new and emerging health data standards (CCDA, FHIR).

With more than 5 years of research in hand, DaasPatcher is a privacy-protected data sharing platform. The platform enables data providers to share a view of their information to end users (data scientists, business analysts, and researchers) who can use it to build and launch data queries within the provider’s infrastructure.

Diabetes devices, such as blood glucose meters and continuous glucose monitors, often struggle to communicate or share their data with other systems, hindering the patient’s ability to share data and use complementary tools for self-management of their condition. Through our work with JDRF, the ISO/IEEE 11073 Personal Health Device Working Group and the Bluetooth Special Interest Group Medical Device Working Group, we are furthering the development of interoperability standards for diabetes devices by identifying the barriers confronted by manufacturers when trying to implement the standards, and developing strategies to facilitate easy adoption. This includes delivery of workshops and toolkits for device manufacturers in order to facilitate knowledge transfer and accelerate adoption of standardized protocols within their technologies.

York University and OcularAI are bringing a validated risk model that predicts 7-day mortality in heart failure patients in hospitals. Furthermore, we will build a 30-day and 365-day versions of the model equipped with Machine Learning capabilities. The enhancements will be built with the objective to scale and secure wide-spread adoption.

The project will train and deploy a medical deep learning model capable of generating medical data insights, workflow efficiencies and improved patient outcomes for the detection and prioritization of emergency in-patient head CTs that demonstrate evidence of urgent conditions, including intracranial hemorrhaging, acute stroke and venous thrombosis (with additional modalities introduced over time).

This project will test the hypothesis that availability of genetic information will help participants reach their health and fitness goals and thus reduce risk of cardiovascular disease, diabetes and obesity.

This technology is a stand-alone online web portal aimed at bringing together the surgeon, patient and post-op care clinicians including physiotherapists, nurses, occupational therapists and home care attendants.

The Real-Time Analytics Platform is a web-based analytics platform tailored to facilitate the practice of evaluating consumer mHealth apps. The platform will enable innovators to view all analytics-enabled study data collected from their evaluations, in real time. Innovators will be able to visually monitor effective engagement indicators collected by platform-connected mHealth apps, perform comparative analysis, and conduct statistical analysis on dynamic datasets. In this way, the platform will support the adaptation of mHealth apps at the right time and under the right circumstances to accelerate research conduct and improve patient outcomes.

Imagine a secure, reliable resource for patient health information across primary care (family medicine) practices. This is what Utopian intends to deliver. We will support the development and evaluation of a data safe haven to support data extraction from multiple EMRs, all on different platforms, into one secure, searchable repository.

This first of its kind multi-site virtual incubator project will create a viable product and further develop and spread the technology so that incubators and accelerators across the world can be linked. Users will connect with global partners and markets more easily and will innovate more effectively.