Hospital operating rooms (OR) are currently under tremendous pressure to maximize patient outcomes and safety while reducing costs. Hospitals that focus on disadvantaged socioeconomic populations are often further burdened to meet these growing demands with a significant lack of resources. The U.S. spent $2.6 trillion on healthcare in 2010 with 56% comprised of healthcare worker wages. Unlike virtually all other sectors, healthcare has experienced no gains in labor productivity over the last 20 years. A healthcare productivity crisis exists, as changing regulatory and insurance standards are complicating delivery of care and increasing documentation burden. Therefore, technology solutions, which use intelligent sensors to reduce manual burden and intelligent algorithms to navigate the complex healthcare operations and logistics, can solve significant unmet productivity challenges and allow clinical staff to focus on patient care, safety, and outcomes. Operating rooms require a complex set of resources, planning, data entry and logistics. Accuracy, speed, and accessibility of information to support real-time changes to planned logistics and operational decision- making significantly impact patient outcomes and safety, clinician and patient satisfaction, and efficiency and cost savings. The operational target is to ensure the patient, surgeon, anesthesiologist, technicians, nurses, janitorial staff, equipment, instruments, supplies, rooms and beds are available at required times and locations. High stress clinical environments, which require dynamic information across stakeholders and resources to make timely and accurate decisions, can significantly benefit from automated sensor inputs and artificial intelligence to minimize manual burden. Therefore, the objective is to develop Whiteboard Coordinator (WC), a software command and control system for hospital operating rooms to reduce manual clinician burden, optimize efficiency, and allow a patient care focus. The technology will integrate sensors and machine learning to detect and track resources for planned surgical events, recognize deviations and delays, and update human, equipment, and facility resource allocation in real-time to maximize efficiency and information accessibility. Significant innovation will differentiate WC from existing dashboard and electronic medical record (EMR) apps. First, an intelligent camera network and machine vision algorithms will automatically detect and update availability and location of OR resources. Secondly, software will automate existing manual documentation procedures that currently take up to 50% of clinician time. Third, while other systems are reactionary and focus on billing documentation, WC machine learning algorithms will facilitate care coordination and parallel workflow to maximize efficient and resource allocation. Finally, WC information will quickly be disseminated to all OR stakeholders (surgeons, nurses, technicians, janitorial staff, etc.) across multiple platforms and devices. Additionally, technology to optimize human and equipment resources can level the playing field for socioeconomic disparate locations to maximize limited resources on patient care and safety. !

Public Health Relevance

Hospital operating rooms depend on accuracy, speed, and accessibility of information to support real-time changes to planned surgical logistics and operational decisions that significantly impact patient outcomes and safety, clinician and patient satisfaction, and efficiency and cost savings. The objective is to develop, deploy, and demonstrate feasibility of Whiteboard Coordinator, a software command and control system for hospital operating rooms to reduce manual clinician burden, optimize efficiency, and allow a patient care focus. The technology will integrate sensors and machine learning to detect and track resources for planned surgical events, recognize deviations and delays, and update human, equipment, and facility resource allocation in real-time to maximize efficiency and information accessibility.

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Small Business Innovation Research Grants (SBIR) - Phase I (R43)
Project #
1R43LM013026-01A1
Application #
9773420
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Ye, Jane
Project Start
2019-08-01
Project End
2020-01-31
Budget Start
2019-08-01
Budget End
2020-01-31
Support Year
1
Fiscal Year
2019
Total Cost
Indirect Cost
Name
Artisight, Inc.
Department
Type
DUNS #
081004328
City
Northfield
State
IL
Country
United States
Zip Code
60093