PICTURE: Rapid Response Team (RRT)

Overview

PICTURE is a suite of machine learning algorithms that utilizes electronic health record (EHR) data to predict patient deterioration in hospital settings. This iteration of the model is providing insight to the RTT Team to priortize patient care.

Value Proposition to Michigan Medicine

Early detection of patient deterioration has been found to lead to reduced mortality risk, reduced length-of-stay and decreased hospital costs, yet identifying patient deterioration is a challenge for clinicians. PICTURE’s Adult RRT Analytic is a combination of machine learning algorithms utilizing electronic health record (EHR) data to passively and accurately predict ICU transfer or death as a proxy for patient deterioration. PICTURE also provides explanations for every single prediction, adding transparency to the model and how it calculated its output. This transparency is invaluable to clinicians who can use these explanations to guide decisions around patient care.

Principal Investigator(s)

Sardar Ansari, PhD
Kevin Ward, MD

Clinical Champion

MM Rapid Response Team 

Digital Health Innovation Support

The Weil Institute has set forth an ambitious agenda to study the usability and efficacy of deterioration models. These studies are complex and interface with a number of clinical and research stakeholders within Michigan Medicine. DHI worked with the Weil Institute to address barriers by connecting the team to subject matter experts and clinical champions. These partnerships lead to the deployment of the PICTURE Adult model to MiChart (Epic Nebula). Developing this data pipeline supported the infrastructure needed to pass data into the model and to display results for the Rapid Response Team. In addition, To support model development, DHI worked with the MM CPR committee to ensure rapid response team and code data were available to researchers in RDW. 

Partnerships

Weil Institute 

Clinical Intelligence Committee (CIC)

Health Information Technology and Services (HITS)

Michigan Medicine CPR Committee

Intellectual Property

Invention Disclosure # 2019-094, 2021-244, 2021-245, 2021-250, 2021-251

Patent Issued: #11587977