PREDICTIVE NOTIFICATIONS FOR ADVERSE PATIENT EVENTS

• US 20140028464A1
• Filed: 07/26/2012
• Published: 01/30/2014
• Est. Priority Date: 07/26/2012
• Status: Active Grant

• Current Assignee: Carefusion 303 Incorporated (Becton, Dickinson & Co)
• Original Assignee: Carefusion 303 Incorporated (Becton, Dickinson & Co)
• Inventors: GARIBALDI, Federico
• Granted Patent: US 10,062,457 B2
• Time in Patent Office: Days
• US Class Current: 340/870.02
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Methods for providing predictive notifications to a monitoring device are provided. In one aspect, a method includes receiving retrospective patient data collected from a plurality of medical devices, and determining, based on a comparison of the retrospective patient data with current patient data for a patient from a medical device, a likelihood of a potential adverse medical event occurring for the patient. The method also includes providing a notification to a monitoring device indicative of the potential adverse medical event for the patient. Systems, graphical user interfaces, and machine-readable media are also provided.

Claims

1. A system for providing predictive notifications to a monitoring device, the system comprising:

a memory comprising retrospective patient data collected from a plurality of medical devices; and

a processor configured to;

determine, based on a comparison of the retrospective patient data with current patient data for a patient from a medical device, a likelihood of a potential adverse medical event occurring for the patient; and

provide a notification indicative of the potential adverse medical event for the patient to a monitoring device.

2. The system of claim 1, wherein the processor is configured to determine the likelihood of the potential adverse medical event occurring for the patient using a pattern matching algorithm.

3. The system of claim 2, wherein a pattern match comprises identifying at least two parameters in the current patient data for the patient that are equal to or within a certain predetermined range of values in the retrospective patient data, or identifying a trend that is substantially similar between the current patient data for the patient and the retrospective patient data.

4. The system of claim 3, wherein the parameters comprises values indicating at least two of CO₂ level, O₂ level, drug name, drug concentration, CO₂ degree of change over time, O₂ degree of change over time, age, medical condition, race, or gender.

5. The system of claim 2, wherein the pattern matching algorithm comprises at least one of keypoint matching, elementary image processing, histogram matching, string searching, approximate string matching.

6. The system of claim 2, wherein the comparison of the retrospective patient data with current patient data comprises comparing a previously identified pattern for the potential adverse medical event with the current patient data.

7. The system of claim 1, wherein the retrospective patient data and the current patient data include at least one of information on medication being provided to a patient or a physiological statistic of a patient.

8. The system of claim 1, wherein the notification includes at least one of information indicating the likelihood of the potential adverse medical event occurring for the patient, a description of the potential adverse medical event, a description of a cause for the occurrence of the potential adverse medical event, or information on how to configure the medical device in order to reduce the occurrence of the potential adverse medical event.

9. The system of claim 1, wherein the retrospective patient data is received from a server that is configured to collect, over a network, the retrospective patient data from the plurality of medical devices across a plurality of health institutions.

10. The system of claim 9, wherein the received retrospective patient data is a subset of the retrospective patient data collected from the plurality of medical devices across the plurality of health institutions.

11. The system of claim 1, wherein the retrospective patient data comprises patient data that is older than one day, and wherein the current patient data comprises patient data that is obtained from a patient within at least one of a past 5 seconds, 10 seconds, 15 seconds, 30 seconds, one minute, two minutes, five minutes, ten minutes, thirty minutes, or an hour.

12. The system of claim 1, wherein the medical device from which the retrospective patient data is collected comprises at least one of an infusion pump system, ventilator system, or a physiological statistic monitor.

13. A method for providing predictive notifications to a monitoring device, the method comprising:

receiving retrospective patient data collected from a plurality of medical devices;

determining, based on a comparison of the retrospective patient data with current patient data for a patient from a medical device, a likelihood of a potential adverse medical event occurring for the patient; and

providing a notification indicative of the potential adverse medical event for the patient to a monitoring device.

14. The method of claim 13, wherein the determination of the likelihood of the potential adverse medical event occurring for the patient is made using a pattern matching algorithm.

15. The method of claim 14, wherein a pattern match comprises identifying at least two parameters in the current patient data for the patient that are equal to or within a certain predetermined range of values in the retrospective patient data, or identifying a trend that is substantially similar between the current patient data for the patient and the retrospective patient data.

16. The method of claim 15, wherein the parameters comprises values indicating at least two of CO₂ level, O₂ level, drug name, drug concentration, CO₂ degree of change over time, O₂ degree of change over time, age, medical condition, race, or gender.

17. The method of claim 14, wherein the pattern matching algorithm comprises at least one of keypoint matching, elementary image processing, histogram matching, string searching, approximate string matching.

18. The method of claim 14, wherein the comparison of the retrospective patient data with current patient data comprises comparing a previously identified pattern for the potential adverse medical event with the current patient data.

19. The method of claim 13, wherein the retrospective patient data and the current patient data include at least one of information on medication being provided to a patient or a physiological statistic of a patient.

20. The method of claim 13, wherein the notification includes at least one of information indicating the likelihood of the potential adverse medical event occurring for the patient, a description of the potential adverse medical event, a description of a cause for the occurrence of the potential adverse medical event, or information on how to configure the medical device in order to reduce the occurrence of the potential adverse medical event.

21. The method of claim 13, wherein the retrospective patient data is received from a server that is configured to collect, over a network, the retrospective patient data from the plurality of medical devices across a plurality of health institutions.

22. The method of claim 21, wherein the received retrospective patient data is a subset of the retrospective patient data collected from the plurality of medical devices across the plurality of health institutions.

23. The method of claim 13, wherein the retrospective patient data comprises patient data that is older than one day, and wherein the current patient data comprises patient data that is obtained from a patient within at least one of a past 5 seconds, 10 seconds, 15 seconds, 30 seconds, one minute, two minutes, five minutes, ten minutes, thirty minutes, or an hour.

24. The method of claim 13, wherein the medical device from which the retrospective patient data is collected comprises at least one of an infusion pump system, ventilator system, or a physiological statistic monitor.

25. A machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method for providing predictive notifications to a monitoring device, the method comprising:

receiving retrospective patient data collected from a plurality of medical devices;

determining, based on a comparison of the retrospective patient data with current patient data for a patient from a medical device, a likelihood of a potential adverse medical event occurring for the patient; and

providing a notification indicative of the potential adverse medical event for the patient to a monitoring device.