PICTURE: Adult Rehabilitation
PICTURE is a suite of machine learning algorithms that utilizes electronic health record (EHR) data to predict patient deterioration in hospital settings. PICTURE Adult Rehabilitation is modeled specifically for an inpatient rehabilitation unit.
Value Proposition
For patients undergoing inpatient rehabilitation, readmission to the acute care hospital can result in a prolonged length of stay, adverse functional outcomes, additional testing and, ultimately, higher healthcare expenditure. The PICTURE Adult Rehabilitation analytic accurately predicts the likelihood that one of these patients might require an acute care transfer, enabling staff and clinicians to provide better care more efficiently.
About PICTURE
PICTURE is a suite of machine learning algorithms utilizing electronic health record (EHR) data to passively and accurately predict patient deterioration. Each PICTURE analytic 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.
Competitive Advantage
Identifies a patient’s risk of deterioration beyond easily observable symptoms - particularly useful when the rehabilitation team is focused on recovery over acute care treatment
Predicts deterioration an average of 30 hours in advance of the event, giving clinicians time to act
Helps hospitals maintain a high level of patient care and distribute tightly-stretched resources efficiently
Unique Features
Provides an explanation of the main factors contributing to its prediction in each instance
Uses data that is collected during routine medical care such as common lab values
Will not disrupt clinician workflows or practices, even if policy changes alter routine tests
Defined thresholds allow the Rehabilitation unit to specify their desired precision
Designed to model patient’s physiology as opposed to clinician behavior, ensuring the alarms provide novel information to care providers
Substantial additional departmental, school and center based support.
Data capture
Model testing and training
Pilot study
Seeking partner rehabilitation clinic for external validation of the PICTURE Adult Rehabilitation analytic
Analytic updates and improvements
