Adverse event prioritization and handling

• US 10,297,347 B2
• Filed: 04/06/2015
• Issued: 05/21/2019
• Est. Priority Date: 04/06/2015
• Status: Active Grant

• Current Assignee: Boston Scientific Cardiac Diagnostics Incorporated (Boston Scientific Corporation)
• Original Assignee: Preventice Solutions, Inc. (Boston Scientific Corporation)
• Inventors: Hutchins, James D., Smith, Richard M.
• Primary Examiner(s): Tiedeman, Jason S
• Application Number:
  US14/679,793
• Publication Number:
  US 20160292374A1
• Time in Patent Office: 1,506 Days
• Field of Search: 705 2, 705 3
• CPC Class Codes: G06Q 10/0633 Workflow analysis
• 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 40/63 for local operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

Collecting biometric data from a patient provides numerous opportunities for a care provider to monitor the health of the patient. In one embodiment, the biometric data is used to identify health events that are processed in a workflow that includes a plurality of interconnected processing nodes and queues. In one embodiment, the workflow processes the health events using a priority assigned to the health events. The priority may be assigned based on a severity of the event, the type of the health event, a characteristic of the patient whose biometric data generated the health event, and the like. Each processing node in the event engine may include multiple consumers or threads for processing health events with different priorities. By having more consumers assigned to high priority events, the latency for processing these events in the workflow may be reduced.

Claims

1. A method, comprising:

receiving a health event for a patient derived from biometric data generated by one or more sensor devices;

identifying a type of the health event by classifying the biometric data associated with the health event;

storing the health event in a first one or more queues for processing, wherein the health event comprises an associated priority;

monitoring the first one or more queues using a plurality of consumers operating on a first processing node, the plurality of consumers comprising a first number of high priority consumers assigned to process higher priority health events and a second number of low priority consumers assigned to process lower priority health events;

processing the health event using a first consumer, of the plurality of consumers, and generating a second health event relating to the health event;

storing the second health event in a second one or more queues for processing;

monitoring the second one or more queues using a second plurality of consumers operating on a second processing node, wherein the second plurality of consumers comprises a third number of high priority consumers and wherein the third number of high priority consumers is greater than the first number of high priority consumers; and

processing the second health event using a second consumer, of the second plurality of consumers.

2. The method of claim 1, further comprising:

changing a number of consumers in one of the plurality of consumers and the second plurality of consumers in response to a change in a number of health events received for processing.

3. The method of claim 1, wherein, each of the consumers in the plurality of consumers comprises a thread that performs a same process on received health events as the other consumers in the plurality of consumers.

4. The method of claim 1, further comprising:

receiving observation data generated by the one or more sensor devices, wherein the observation data includes both the biometric data and environmental data;

evaluating the observation data using one of the first processing node or the second processing node to generate a derived observation based on previous observations stored in a data repository; and

upon determining the derived observation satisfied a condition, triggering a different health event to be processed by the processing node, wherein the different health event comprises the derived observation.

5. The method of claim 1, further comprising:

generating a new health event using one of the first processing node or the second processing node based on determining whether a condition corresponding to a rule has been satisfied.

6. The method of claim 1, further comprising storing a third health event in the second one or more queues for processing, wherein the second one or more queues store more high priority health events than the first one or more queues.

7. The method of claim 1, wherein second plurality of consumers perform a different process on received health events than the plurality of consumers.

8. The method of claim 1, wherein the health event is received at a workflow server and wherein the health event is generated by classifying the biometric data at one of:

(i) a mobile device or (ii) a sensor device of the one or more sensor devices and wherein processing the health event comprises re-classifying the health event, using the workflow server, as the second health event.

9. The method of claim 8, wherein the second health event comprises a higher priority than the health event and wherein the second consumer is a high priority consumer.

10. The method of claim 9, wherein processing the second health event comprises providing the second health event to an action service and wherein the action service is configured to take an action based on the second health event.

11. The method of claim 10, wherein the action comprises forwarding the second health event to a monitoring service configured to allow review of the health event by a care provider for the patient.

12. A non-transitory computer-readable medium containing computer program code that, when executed by a processor, performs an operation for outputting information for display, the operation comprising:

receiving a health event for a patient derived from biometric data generated by one or more sensor devices;

identifying a type of the health event by classifying the biometric data associated with the health event;

storing the health event in a first one or more queues for processing, wherein the health event comprises an associated priority;

monitoring the first one or more queues using a plurality of consumers operating on a first processing node, the plurality of consumers comprising a first number of high priority consumers assigned to process higher priority health events and a second number of low priority consumers assigned to process lower priority health events;

processing the health event using a first consumer, of the plurality of consumers, and generating a second health event relating to the health event;

storing the second health event in a second one or more queues for processing;

monitoring the second one or more queues using a second plurality of consumers operating on a second processing node, wherein the second plurality of consumers comprises a third number of high priority consumers and wherein the third number of high priority consumers is greater than the first number of high priority consumers; and

processing the second health event using a second consumer, of the second plurality of consumers.

13. The non-transitory computer-readable medium of claim 12, the operation further comprising:

changing a number of consumers in one of the plurality of consumers and the second plurality of consumers in response to a change in a number of health events received for processing.

14. The non-transitory computer-readable medium of claim 12, wherein, each of the consumers in the plurality of consumers comprises a thread that performs a same process on received health events as the other consumers in the plurality of consumers.

15. The non-transitory computer-readable medium of claim 12, the operation further comprising:

receiving observation data generated by the one or more sensor devices, wherein the observation data includes both the biometric data and environmental data;

evaluating the observation data using one of the first processing node or the second processing node to generate a derived observation based on previous observations stored in a data repository; and

upon determining the derived observation satisfied a condition, triggering a different health event to be processed by the processing node, wherein the different health event comprises the derived observation.

16. The non-transitory computer-readable medium of claim 12, the operation further comprising:

generating a new health event using one of the first processing node or the second processing node based on determining whether a condition corresponding to a rule has been satisfied.

17. A system, comprising:

at least one sensor device to collect biometric data associated with a patient;

a workflow server comprising a first and second interconnected processing node, the workflow is configured to;

receive a health event for a patient derived from biometric data generated by the at least one sensor device;

identify a type of the health event by classifying the biometric data associated with the health event;

store the health event in a first one or more queues for processing, wherein the health event comprises an associated priority;

monitor the first one or more queues using a plurality of consumers operating on the first processing node, the plurality of consumers comprising a first number of high priority consumers assigned to process higher priority health events and a second number of low priority consumers assigned to process lower priority health events;

process the health event using a first consumer, of the plurality of consumers, and generating a second health event relating to the health event;

store the second health event in a second one or more queues for processing;

monitor the second one or more queues using a second plurality of consumers operating on the second processing node, wherein the second plurality of consumers comprises a third number of high priority consumers and wherein the third number of high priority consumers is greater than the first number of high priority consumers; and

process the second health event using a second consumer, of the second plurality of consumers.

18. The system of claim 17, wherein the workflow server is configured to change a number of consumers in one of the plurality of consumers and the second plurality of consumers in response to a change in a number of health events received for processing.

19. The system of claim 17, wherein, each of the consumers in the plurality of consumers comprises a thread that performs a same process on received health events as the other consumers in the plurality of consumers.

20. The system of claim 17, wherein the workflow server further comprises:

a plurality of event engines, each comprising one or more processing nodes for processing health events received from at least one sensor device; and

a load balancer configured to receive the health event and assign the health event to one of the plurality of event engines.