PICTURE: Adult General Floor Deterioration Prediction

Written By Phil Jacokes

PICTURE is a suite of machine learning algorithms that utilizes electronic health record (EHR) data to passively and accurately predict ICU transfer or death as a proxy for patient deterioration in hospital settings. The Adult General Floor Analytic is modeled specifically for adult inpatients in a general floor.

Enhancing Early Detection
PICTURE's Adult General Floor Analytic revolutionizes the early detection of patient deterioration, facilitating timely interventions that reduce mortality, shorten hospital stays, and drive down costs. Through advanced machine learning, PICTURE provides precise predictions of ICU transfers or potential mortality and supports clinicians with transparent, data-driven explanations for each prediction, aiding informed decision-making.

Competitive Advantage

  • Beyond Observable Symptoms: PICTURE goes further than what meets the eye, identifying risks that are not immediately apparent through standard clinical observations.

  • Proactive Alerts: On average, PICTURE predicts potential deterioration 30 hours before it may occur, empowering clinicians with ample time to intervene effectively.

  • Resource Optimization: The suite supports hospitals in delivering high-quality care while managing resources efficiently, a critical advantage in today's healthcare landscape.

Key Features

  • Explanatory Transparency: Each prediction is supported by an explanation of the main contributing factors, enhancing clinicians' understanding and trust in the model.

  • Seamless Integration: Utilizing routinely collected medical data, including common lab values, PICTURE integrates effortlessly into existing workflows, regardless of policy changes.

  • Customizable Precision Settings: Individual hospital units can customize precision thresholds to match their specific needs, aligning with care goals

  • Novel Physiology-Based Modeling: By focusing on physiological indicators rather than clinician behavior, PICTURE ensures the alarms provide novel information to care providers.

  • Adult Model-Specific Capabilities: The model evaluates additional critical events like Code Blue and Mechanical Ventilation transfers and includes Reference Range Normalization for lab values.

AI & Digital Health Innovation Support

AI & Digital Health Innovation has successfully implemented prospective data validation for the PICTURE model, ensuring its reliability and effectiveness in clinical settings.

 

Principal Investigators
Sardar Ansari, PhD
Kevin Ward, MD

Intellectual Property
Invention Disclosure # 2019-094, 2021-244, 2021-245, 2021-250, 2021-251
Patent Issued: #11587977

 

MARKET OPPORTUNITY
On average, PICTURE provides 30 hours advanced warning time and 17% fewer false alarms for every true alarm compared to the EPIC Deterioration Index when tested on COVID-19 patients. The PICTURE suite is part of a family of specialized data science tools available to be licensed from the Weil Institute. 

Weil is also open to discussions of new research utilizing the technology developed for the PICTURE platform. 

Please contact the Licensing Manager, Drew Bennett, for more information.

Phil Jacokes
Previous

PICTURE: Pediatric General Floor Deterioration Prediction
Next

PICTURE: Rapid Response Team (RRT)