Clinical decision support for sepsis

• US 10,734,115 B1
• Filed: 08/09/2013
• Issued: 08/04/2020
• Est. Priority Date: 08/09/2012
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S., Murrish, John Christopher, Kailasam, Kanakasabha, Hoffman, Mark A., Ryan, Hugh, Sutariya, Bharat, Perez, Leo V., Kuckelman, John
• Primary Examiner(s): Weisenfeld, Aryan E
• Assistant Examiner(s): Blanchette, Joshua B
• Application Number:
  US13/963,732
• Time in Patent Office: 2,552 Days
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

Methods are provided for validating theoretical improvements in the decision-support processes facilitating surveillance and monitoring of a patient'"'"'s risk for developing a particular disease or condition and detecting the disease or condition. Patient information is received from a source and populated into an active risk assessment that monitors the patient'"'"'s risk for developing Sepsis. At least a first and second set of actionable criteria for determining a patient'"'"'s risk for developing sepsis are received. For each set of actionable criteria, it is determined that actionable criteria have been met. In some embodiments, software agents, operating in a multi-agent computing platform, perform each determination of whether actionable criteria are met. In some embodiments, in response to actionable criteria being met, a notification or alert is provided, and in some embodiments the results of the determinations of each set of actionable criteria are provided to facilitate validation of theoretical improvements.

Claims

1. A method for detecting sepsis in a patient in a multi-agent computing system, the method comprising:

receiving, from a first source, a first set of patient information corresponding to a patient;

generating a multi-site risk assessment array for the patient representing the patient'"'"'s risk of developing sepsis, the multi-site risk assessment array being a computing data structure and including a plurality of state nodes, each state node corresponding to a distinct condition parameter, wherein the status of each state node is updateable by a computing agent operating on the multi-site risk assessment array when the multi-site risk assessment array is active;

for a first node of the active multi-site risk assessment array corresponding to the first set of patient information, populating at least one value of the first node with at least a portion of the first set of patient information;

receiving, from a second source, a second set of patient information corresponding to the patient, wherein the first source is distinct and separate from the second source each source utilizing different record systems;

for a second node of the active multi-site risk assessment array corresponding to at least a portion of the second set of patient information, populating at least one value of the second node with the at least the portion of the second set of patient information;

receiving a first set of sepsis-specific actionable criteria for determining whether a patient is at risk for developing sepsis and a second set of sepsis-specific actionable criteria for determining whether a patient is at risk for developing sepsis, the first set of actionable criteria being different from the second set of actionable criteria;

associating the first set of actionable criteria with a first computing agent of the multi-agent computer system, the first computing agent having a first set of agent parameters, and the second set of actionable criteria with a second computing agent of the multi-agent computer system, the second computing agent having a second set of agent parameters, wherein the first computing agent and the second computing agent continuously monitor the multi-site risk assessment array in parallel, the monitoring comprising applying the first set of agent parameters to the multi-site risk assessment array by the first computing agent and applying the second set of agent parameters to the multi-site risk assessment array by the second computing agent to generate plurality of evaluations of the multi-site risk assessment array based on the actionable criteria associated with each computing agent;

for each of the first and second computing agents, based on their respective agent parameters and associated sets of actionable criteria, determining that at least one set of actionable criteria have been met based on at least the values stored in the first node and the second node of the active multi-site risk assessment array, wherein the first computing agent and the second computing agent are dynamically swapped by the multi-agent computer system based on at least one evaluation, the swapping invoked automatically based on a determination by the multi-agent system that the first computing agent or the second computing agent yields a more accurate evaluation for sepsis based on a comparison, by the multi-agent system, of the at least one evaluation; and

providing a notification that the sepsis-specific actionable criteria have been met based on an evaluation generated by at least one of the first computing agent and the second computing agent.

2. The method of claim 1, wherein each of the first node and the second node represent one or more of a heart rate, a body temperature, a respiration rate, a white blood cell count, glucose, bands, lactate level, systemic blood pressure, mean arterial pressure, oxygen saturation, creatinine, bilirubin, platelet count, partial thromboplastin time (PTT), or the PaO₂/FiO₂ ratio.

3. The method of claim 1, wherein the active risk assessment representing the patient'"'"'s risk of developing sepsis remains active for 24 to 72 hours.

4. The method of claim 1, wherein the first source is a first medical organization, the second source is a second medical organization, and notification is provided to each of the first medical organization and the second medical organization such that providers who treated the patient at each of the first and second medical organizations are alerted as to the patient meeting the sepsis-specific actionable criteria.

5. The method of claim 1, wherein the notification includes the results of the determination from each agent of whether the actionable criteria are met.

6. The method of claim 5, wherein a health care provider designates results from one of the agents for results to be reported.

7. The method of claim 1, wherein a patient identity management is applied to determine that the first and second sources of patient information correspond to the same patient.

8. The method of claim 1, wherein the first source is a first medical organization, the second source is a second medical organization, and further comprising:

determining that the actionable criteria set by the first medical organization have been met;

determining that the actionable criteria set by the second medical organization have not been met; and

providing the notification to the first medical organization that the actionable criteria have been met.

9. The method of claim 1, wherein the notification is provided by communicating the notification to all providers with documented patient contact during a period of time that the active risk assessment array has been active.

10. The method of claim 1, further comprising providing a recommended care plan to one or more providers based on the first and second sets of patient information.

11. One or more computer storage media having computer-executable instructions embodied thereon, that when executed by a computing system having a processor and memory, cause the computing system to perform a method for detecting sepsis in a patient, the method comprising:

receiving a first set of patient information comprising clinical data for a patient from a first source;

based on the first set of patient information, determining that the patient is to be monitored for developing sepsis;

generating a multi-site risk assessment array for the patient representing the patient'"'"'s risk of developing sepsis, the multi-site risk assessment array being a computing data structure and including a plurality of state nodes, each state node corresponding to a distinct condition parameter, wherein the status of each state node is updateable by a computing agent operating on the multi-site risk assessment array when the multi-site risk assessment array is active;

populating values of a first set of nodes of the active multi-site risk assessment array with at least a portion of the first set of patient information;

receiving a second set of patient information comprising clinical data for the patient from a second source, wherein the first source is distinct and separate from the second source each source utilizing different record systems;

determining that the active multi-site risk assessment array that is specific to sepsis is currently active;

populating the values of a second set of nodes of the active multi-site risk assessment array with at least a portion of the second set of patient information;

receiving a first set of sepsis-specific actionable criteria and a second set of sepsis-specific actionable criteria, the first set of actionable criteria being different from the second set of actionable criteria;

associating the first set of actionable criteria with a first computing agent of the multi-agent computer system, the first agent having a first set of agent parameters, and the second set of actionable criteria with a second computing agent of the multi-agent computer system, the second agent having a second set of agent parameters, wherein the first agent and the second agent continuously monitor the multi-site risk assessment array in parallel, the monitoring comprising applying the first set of agent parameters to the multi-site risk assessment array by the first agent and applying the second set of agent parameters to the multi-site risk assessment array by the second agent to generate multiple evaluations of the multi-site risk assessment array based on the actionable criteria associated with each agent;

for each set of actionable criteria associated with at least one of the first agent and the second agent, based on the values stored in the first set of nodes and the second set of nodes of the multi-site risk assessment array, determining that the patient has met the actionable criteria for being at risk for developing sepsis, wherein the first agent and the second agent are dynamically swapped based on at least one evaluation, the swapping invoked automatically based on at least one evaluation and a determination by the multi-agent system that the first agent or the second agent yields a more accurate evaluation for sepsis based on a comparison, by the multi-agent system, of the at least one evaluation; and

providing notification to a health care provider associated with the patient that the patient has met actionable criteria for developing sepsis based on an evaluation generated by at least one of the first agent and the second agent.

12. The computer storage media of claim 11, wherein providing notification includes providing the results of each determination from the first and second sets of actionable criteria.

13. The computer storage media of claim 11, wherein the notification includes one result from among the results of the determinations.

14. The computer storage media of claim 13, wherein the notification comprises one or more of a flag in the patient'"'"'s medical record, a message sent to a pager, an email, a text message, a message received at a message center, a telephone call, or a fax.

15. The computer storage media of claim 11, wherein the first and second sets of actionable criteria for a patient being at risk for developing sepsis are different, and wherein the first source of patient information provides the first set of actionable criteria and the second source of patient information provides the second set of actionable criteria.

16. The computer storage media of claim 15, wherein once the first set of actionable criteria of the first source of patient information have been met, the first source is notified.

17. The computer storage media of claim 14, wherein the second source of patient information is not notified if the actionable criteria of the second source have not yet been met.

18. One or more computer storage media having computer-executable instructions embodied thereon, that when executed by a computing system having a processor and memory, cause the computing system to perform a method for detecting sepsis in a patient based on multi-site surveillance, the method comprising:

receiving from a first source, a first set of patient information comprising clinical data corresponding to a patient and a first set of sepsis-specific actionable criteria for performing escalation actions, wherein the first set of sepsis-specific actionable criteria is associated with a first agent, the first agent having a first set of agent parameters;

determining, based on the first set of patient information, that the patient is to be monitored for developing sepsis;

generating an active multi-site risk assessment array for the patient representing the patient'"'"'s risk of developing sepsis, the multi-site risk assessment array being a computing data structure and including a plurality of state nodes, each state node corresponding to a distinct condition parameter, wherein the status of each state node is updateable by a computing agent operating on the multi-site risk assessment array when the multi-site risk assessment array is active;

populating values of a first set of nodes of the active multi-site risk assessment array with at least a portion of the first set of patient information;

receiving a second set of patient information comprising clinical data from a second source that maintains a different medical record system than the first source;

determining that the first set of patient information corresponds to the same patient as the second set of patient information, and associating the first set of patient information with the second set of patient information;

populating the values of a second set of nodes of the active multi-site risk assessment array with the second set of patient information;

receiving a second set of sepsis-specific actionable criteria for performing escalation actions, wherein the second set of sepsis-specific actionable criteria is associated with a second agent, the second agent having a second set of agent parameters;

based on the active multi-site risk assessment array, for each set of actionable criteria, determining that the actionable criteria have been met by applying the first and second set of agent parameters by the first and second agent to the multi-site risk assessment array to generate multiple evaluations of the multi-site risk assessment array, wherein the actionable criteria are met when the patient has a particular high risk for developing sepsis; and

in response to at least one set of the first and second sets of actionable criteria being met, performing one or more escalation actions associated with at least one of the first agent and the second agent, wherein the escalation actions comprise providing notification that actionable criteria has been met for the patient based on at least one evaluation generated by at least one of the first agent and the second agent, and dynamically swapping the first agent and the second agent based on the escalation actions, the swapping invoked automatically based on a determination by the multi-agent system that the first agent or the second agent yields a more accurate evaluation for sepsis based on a comparison, by the multi-agent system, of the at least one evaluation.

19. The computer storage media of claim 18, further comprising:

providing the results of the determinations performed with each set of actionable criteria to a health care provider.