System and method for protocol adherence

• US 9,785,744 B2
• Filed: 09/13/2011
• Issued: 10/10/2017
• Est. Priority Date: 09/14/2010
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Johnson, Christopher Donald, Tu, Peter Henry, Bonissone, Piero Patrone, Lizzi, Jr., John Michael, Akbay, Kunter Seref, Yu, Ting, Bufi, Corey Nicholas, Avasarala, Viswanath, Iyer, Naresh Sundaram, Yao, Yi, Patwardhan, Kedar Anil, Gao, Dashan
• Primary Examiner(s): Rao, Andy
• Application Number:
  US13/231,639
• Publication Number:
  US 20120154582A1
• Time in Patent Office: 2,219 Days
• Field of Search: 348521, 348 77, 348143-160
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G08B 21/245 Reminder of hygiene compliance policies, e.g. of washing hands
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 80/00 ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring

Abstract

The system and method disclosed herein provides an integrated and automated workflow, sensor, and reasoning system that automatically detects breaches in protocols, appropriately alarms and records these breaches, facilitates staff adoption of protocol adherence, and ultimately enables the study of protocols for care comparative effectiveness. The system provides real-time alerts to medical personnel in the actual processes of care, thereby reducing the number of negative patient events and ultimately improving staff behavior with respect to protocol adherence.

Claims

1. An apparatus comprising:

an optical sensing system including;

a plurality of optical sensors configured to capture visual input in a monitored environment and generate optical sensor data characterizing a layout of the monitored environment, the plurality of optical sensors arranged to dynamically divide the monitored environment into a plurality of geo-spatial zones defining the layout, wherein each zone is associated with a task in a healthcare protocol to be monitored as part of a clinical workflow and wherein a crossing of an object between at least two zones is associated with a task in the healthcare protocol to be monitored;

a computer vision subsystem configured to utilize one or more of the plurality of optical sensors to transform the optical sensor data from the one or more optical sensors into a vector space identifying at least one of a location and trajectory of one or more monitored people and objects in the monitored environment;

an artificial intelligence engine configured to instantiate an augmented state transition network for each healthcare protocol to be monitored, the augmented state transition network encoding the protocol as states corresponding to protocol tasks and state transitions between tasks, the states representing the tasks and queued for monitoring, the state transitions based on a probability distribution associated with the at least one of a location and trajectory of one or more monitored people and objects in the vector space, wherein the artificial intelligence engine converts the probability distribution into a likelihood of protocol breach for the healthcare protocol to be monitored; and

an information broker configured to publish messages from the augmented state transition network while the augmented state transition network is instantiated, the messages including the likelihood of protocol breach and information regarding the at least one of a location and trajectory of one or more monitored people and objects in the vector space; and

a reasoning engine configured to subscribe to messages published by the information broker from the augmented state transition network, the reasoning engine to dynamically determine a protocol task violation based on deviation from a protocol state calculated using the messages, the reasoning engine triggering an alarm to report the deviation,

wherein the reasoning engine is instantiated by a request from the clinical workflow and includes at least a protocol reasoning engine for the protocol, a task reasoning engine for protocol task, and a state reasoning engine for protocol state that work together to determine protocol compliance, and wherein the reasoning engine determines, using the messages and an ordered ontology for a healthcare domain, the protocol state formed from the messages using the ordered ontology based on i) a first state associated with an agent to perform an action, ii) a second state associated with an object that is a recipient of the action, and iii) a third state associated with an event that associates the action with the object and the agent, the ordered ontology enabling a processing of the protocol state and a comparison of the protocol state to identify the deviation based on an illegal state transition.

2. The apparatus of claim 1, wherein the optical sensing system and the reasoning engine are to be hosted in a message brokered computing environment.

3. The apparatus of claim 1, wherein one or more of the plurality of optical sensors is to identify an optical pattern on at least one of the monitored people and objects.

4. The apparatus of claim 3, wherein one or more of the plurality of optical sensors is to read dynamic signals produced on the display of a monitored object.

5. The apparatus of claim 1, wherein the augmented transition network is active while a monitored person is in the monitored environment and wherein the artificial intelligence engine destroys the instantiation of the augmented transition network when the monitored person has left the monitored environment based on information from one or more of the optical sensors.

6. The apparatus of claim 1, wherein proximity of a monitored object or person can be quantified by a geo-spatial zone defined to cover a volume of the monitored object or person.

7. The apparatus of claim 6, wherein an interaction between a first monitored object or person and a second monitored object or person is detected based on interaction between a first geo-spatial zone associated with the first monitored object or person and a second geo-spatial zone associated with the second monitored object or person.

8. The apparatus of claim 1, wherein at least one of the optical sensors includes a camera.

9. The apparatus of claim 1, wherein information captured from the one or more optical sensors is used to adjust a lighting level in the monitored environment.

10. The apparatus of claim 1, wherein the alarm includes at least one of audible feedback, visual feedback, or text-based feedback.

11. A non-transitory, computer-readable medium including instructions which, when executed by a processor, configure the processor to implement an apparatus comprising:

an optical sensing system including;

a plurality of optical sensors configured to capture visual input in a monitored environment and generate optical sensor data characterizing a layout of the monitored environment, the plurality of optical sensors arranged to dynamically divide the monitored environment into a plurality of geo-spatial zones defining the layout, wherein each zone is associated with a task in a healthcare protocol to be monitored as part of a clinical workflow and wherein a crossing of an object between at least two zones is associated with a task in the healthcare protocol to be monitored;

a computer vision subsystem configured to utilize one or more of the plurality of optical sensors to transform the optical sensor data from the one or more optical sensors into a vector space identifying at least one of a location and trajectory of one or more monitored people and objects in the monitored environment;

an artificial intelligence engine configured to instantiate an augmented state transition network for each healthcare protocol to be monitored, the augmented state transition network encoding the protocol as states corresponding to protocol tasks and state transitions between tasks, the states representing the tasks and queued for monitoring, the state transitions based on a probability distribution associated with the at least one of a location and trajectory of one or more monitored people and objects in the vector space, wherein the artificial intelligence engine converts the probability distribution into a likelihood of protocol breach for the healthcare protocol to be monitored; and

an information broker configured to publish messages from the augmented transition network while the augmented state transition network is instantiated, the messages including the likelihood of protocol breach and information regarding the at least one of a location and trajectory of one or more monitored people and objects in the vector space; and

a reasoning engine configured to subscribe to messages published by the information broker from the augmented state transition network, the reasoning engine to dynamically determine a protocol task violation based on deviation from a protocol state calculated using the messages, the reasoning engine triggering an alarm to report the deviation,

wherein the reasoning engine is instantiated by a request from the clinical workflow and includes at least a protocol reasoning engine for the protocol, a task reasoning engine for protocol task, and a state reasoning engine for protocol state that work together to determine protocol compliance, and wherein the reasoning engine determines, using the messages and an ordered ontology for a healthcare domain, the protocol state formed from the messages using the ordered ontology based on i) a first state associated with an agent to perform an action, ii) a second state associated with an object that is a recipient of the action, and iii) a third state associated with an event that associates the action with the object and the agent, the ordered ontology enabling a processing of the protocol state and a comparison of the protocol state to identify the deviation based on an illegal state transition.

12. The computer-readable medium of claim 11, wherein the optical sensing system and the reasoning engine are to be hosted in a message brokered computing environment.

13. The computer-readable medium of claim 11, wherein one or more of the plurality of optical sensors is to identify an optical pattern on at least one of the monitored people and objects.

14. The computer-readable medium of claim 13, wherein one or more of the plurality of optical sensors is to read dynamic signals produced on the display of a monitored object.

15. The computer-readable medium of claim 11, wherein the augmented transition network is active while a monitored person is in the monitored environment and wherein the artificial intelligence engine destroys the instantiation of the augmented transition network when the monitored person has left the monitored environment based on information from one or more of the optical sensors.

16. The computer-readable medium of claim 11, wherein proximity of a monitored object or person can be quantified by a geo-spatial zone defined to cover a volume of the monitored object or person.

17. The computer-readable medium of claim 16, wherein an interaction between a first monitored object or person and a second monitored object or person is detected based on interaction between a first geo-spatial zone associated with the first monitored object or person and a second geo-spatial zone associated with the second monitored object or person.

18. The computer-readable medium of claim 11, wherein at least one of the optical sensors includes a camera.

19. The computer-readable medium of claim 11, wherein information captured from the one or more optical sensors is used to adjust a lighting level in the monitored environment.

20. The computer-readable medium of claim 11, wherein the alarm includes at least one of audible feedback, visual feedback, or text-based feedback.