Graph database for outbreak tracking and management

Patent metadata

Field	Value
Publication number	US-11966397-B2
Application number	US-202217986332-A
Country	US
Kind code	B2
Filing date	Nov 14, 2022
Priority date	Jul 2, 2018
Publication date	Apr 23, 2024
Grant date	Apr 23, 2024

Abstract

A graph database for outbreak tracking and management is disclosed. In an example embodiment, an outbreak management system includes a memory device storing instructions that define a graph database for disease outbreak tracking. The instructions specify for a given host that a host node is created and an episode node is connected to the host node via a ‘case’ link. The episode node is associated with episode parameters that are related to a disease classification of the host. In addition, the instructions specify that an outbreak node is connected to the episode node via a ‘part of’ link to indicate that the host has become part of an outbreak of the disease. The outbreak node is connected to a definition node via a ‘defined as’ link. The definition node specifies disease parameters of the disease that is related to the outbreak node.

First claim

The invention is claimed as follows:

1. An outbreak management apparatus comprising:
a node processor;
an outbreak tracking graph database for a particular disease including an outbreak node connected to a definition node via a ‘defined as’ link, the definition node specifying disease parameters of the disease including conditions for disease classification including a ‘possible’ classification for the disease, a ‘probable’ classification for the disease, and a ‘confirmed’ classification for the disease; and
a memory device storing machine-readable instructions, which when executed by the node processor, cause the node processor to:
receive, via an interface, patient data related to a patient,
determine whether the patient should be associated with the outbreak node that corresponds to the disease by comparing the patient data to the disease parameters of the definition node, wherein
the ‘possible’ classification is selected when at least some of the patient data matches at least some clinical criteria specifying at least one symptom,
the ‘probable’ classification is selected when at least some of the patient data matches
at least some of the clinical criteria specifying at least one symptom, and
the patient has an epidemiological link to a known host of the outbreak tracking graph database for the disease, and

the ‘confirmed’ classification is selected when at least some of the patient data matches
at least some of the clinical criteria specifying at least one symptom, and
at least some laboratory criteria for diagnosis specifying at least one of isolation, detection, identification, or an antibody response related to the disease, and

when at least one of the ‘possible’, ‘probable’, or ‘confirmed’ classification is determined for the patient, add the patient to the outbreak tracking graph database for the disease.

2. The apparatus of claim 1 , wherein the node processor is configured to add the patient to the outbreak tracking graph database by:
creating a host node for the patient;
creating an episode node that is connected to the host node via a ‘case’ link, the episode node being associated with episode parameters that are related to the disease classification of the patient; and
connecting the episode node to the outbreak node via a ‘part of’ link to indicate that the patient has become part of the outbreak for the disease.

3. The apparatus of claim 2 , wherein the interface is configured to receive the patient data from at least one of an Electronic Medical Record (“EMR”) server or a third-party server, and wherein the patient data includes at least one of patient medical data, social media data, location data, or demographic data.

4. The apparatus of claim 2 , wherein the instructions further cause the node processor to, when specimen data is available within the patient data:
create a specimen node that is linked to the host node via a specimen link, the specimen node being associated with specimen parameters that indicate a time or status of a specimen acquired from the patient;
create an isolate node that is linked to the specimen node via an isolate link, the isolate node being associated with isolate parameters that specify an isolate in specimen results that are related to the acquired specimen; and
create an organism node that is linked to the isolate node via an organism link, the organism node being associated with organism parameters that specify at least one organism that was found in an isolation routine.

5. The apparatus of claim 1 , wherein the epidemiological link includes at least one of an ‘airborne’ link, an ‘animal reservoir’ link, an ‘environmental reservoir’ link, a ‘food and drinking water’ link, an ‘insect bite’ link, an ‘animal-to-person contact’ link, a ‘contaminated object’ link, a ‘droplet spread’ link, or a ‘person-to-person contact’ link, and
wherein the known host is at least one of a patient, a clinician, a person, an animal, a fomite, or an object.

6. The apparatus of claim 1 , wherein the known host has at least one of a ‘possible’ classification for the disease, a ‘probable’ classification for the disease, or a ‘confirmed’ classification for the disease to enable the epidemiological link to be made with the patient.

7. The apparatus of claim 6 , wherein the known host is associated with a second host node that is connected to a second episode node via a ‘case’ link, and wherein the second episode node is connected to the outbreak node of the outbreak tracking graph database via a ‘part of’ link.

8. The apparatus of claim 1 , wherein the node processor is configured to use at least one of social media data, demographic relationship data, geographic location data, clinician notes, or a treatment schedule of the patient or the known host to determine the epidemiological link between the patient and the known host.

9. The apparatus of claim 1 , wherein the ‘possible’ classification is selected additionally when at least some of the patient data includes a clinician's judgement regarding the disease.

10. The apparatus of claim 1 , wherein the instructions further cause the node processor to:
compare a number of host nodes or episode nodes that were added to the outbreak tracking graph database for the disease within a defined time period to a threshold, and
generate an alert indicative of an outbreak of the disease when the number of host nodes or episode nodes exceeds the threshold.

11. The apparatus of claim 10 , wherein the alert includes at least one text message or push notification that is transmitted to at least one clinician device.

12. The apparatus of claim 10 , wherein the comparison is performed for only episode nodes or host nodes that are associated with a ‘probable’ classification or a ‘confirmed’ classification.

13. An outbreak management method comprising:
storing an outbreak tracking graph database for a particular disease including an outbreak node connected to a definition node via a ‘defined as’ link, the definition node specifying disease parameters of the disease including conditions for disease classification including a ‘possible’ classification for the disease and a ‘confirmed’ classification for the disease;
receiving, in a server, patient data related to a patient;
determining, via the server, whether the patient should be associated with the outbreak node associated with the disease by comparing the patient data to the disease parameters of the definition node, wherein
the ‘possible’ classification is selected when at least some of the patient data matches at least some clinical criteria specifying at least one symptom, and
the ‘confirmed’ classification is selected when at least some of the patient data matches
at least some of the clinical criteria specifying at least one symptom, and
at least some laboratory criteria for diagnosis specifying at least one of isolation, detection, identification, or an antibody response related to the disease; and

when at least one of the ‘possible’ or ‘confirmed’ classification is determined for the patient, adding, via the server, the patient to the outbreak tracking graph database for the disease.

14. The method of claim 13 , wherein the patient is added to the outbreak tracking graph database by:
creating, via the server, a host node for the patient;
creating, via the server, an episode node that is connected to the host node via a ‘case’ link, the episode node being associated with episode parameters that are related to the disease classification of the patient; and
connecting, via the server, the episode node to the outbreak node via a ‘part of’ link to indicate that the patient has becom

Assignees

• Baxter Int
• Baxter Healthcare Sa

Inventors

• Randall Paul
• Smith Ian
• Haynes Jonathan
• Wilkinson Sam

Classifications

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• H04L67/01

  Protocols · CPC title

• G06F3/0484

  for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title

• G16H70/60

  relating to pathologies · CPC title