Research Collaboration Explores Dynamic Pediatric Risk Scoring to Measure Criticality As a Step Towards Assistive Intelligence


KenSci and Children’s National collaborate to apply machine learning and artificial intelligence to create predictive models to study transitions to and from intensive care units (ICU)

WASHINGTON – (July 23, 2019) – A new research collaboration between Children’s National Health System and KenSci seeks to study how current pediatric risk scores can be enhanced and made more effective in clinical decision making. Leveraging KenSci’s platform and data science expertise, the partnership seeks to develop new models to understand the factors that impact criticality in pediatric patients.

“Since the mid-80s we have been able to predict mortality risks in pediatric ICUs using risk scores. In most cases these scores are used for quality assessment,” says Murray Pollack, M.D., MBA, Director of Outcomes Research at Children’s National Health System and a Professor of Pediatrics at George Washington University School of Medicine. “Our collaborative goals are to study the temporal variation in data, taking the first step towards dynamic risk scoring for pediatric ICUs.”

Ankur Teredesai, KenSci’s co-founder and Chief Technology Officer and Professor at the University of Washington Tacoma, acknowledged the strategic nature of this collaboration, “Time is our best ally if integrated appropriately with other variables in Healthcare Machine Learning and AI. Adding dynamism holds tremendous promise to be assistive for critical care. Caregivers in Pediatric ICUs serve the most vulnerable patients in our population, and this collaboration advances KenSci’s vision to be the best System of Intelligence for healthcare.”

“We see tremendous possibilities for how this research can be used safely and securely to supplement the clinician’s judgment,” says Hiroki Morizono, Ph.D., Director of Biomedical Informatics at the Children’s National Center for Genetic Medicine Research. “This type of modeling could predict an individual patient’s likelihood for deterioration or improvement.”

The joint team will leverage KenSci’s Healthcare AI platform to test different models and compare their predictive power to prior baselines developed by Children’s National, George Washington University, and others.

About KenSci

KenSci’s machine learning powered risk prediction platform helps healthcare providers and payers intervene early by identifying clinical, financial and operational risk to save costs and lives. KenSci’s platform is engineered to ingest, transform and integrate healthcare data across clinical, claims, and patient generated sources. With a library of pre-built models and modular solutions, KenSci’s machine learning platform to integrates into existing workflows allowing health systems to better identify utilization, variation and improve hospital operations. With Explainable AI models for healthcare, KenSci is making risk-based prediction more efficient and accountable.

KenSci was incubated at University of Washington’s Center for Data Science at UW Tacoma and designed on the cloud with help from Microsoft’s Azure4Research grant program. KenSci is headquartered in Seattle, with offices in Singapore and Hyderabad. For more information, visit www.kensci.com

This Press Release has been sponsored by House Communications

Digital Health Buzz!

Digital Health Buzz!

Digital Health Buzz! aims to be the destination of choice when it comes to what’s happening in the digital health world. We are not about news and views, but informative articles and thoughts to apply in your business.

Hey there!

Sign in

Forgot password?

Don't have an account? Register


    Processing files…