System and method for classifying and managing medical application disconnects
A method for processing information includes receiving a feature set for an application in a medical system, determining a disconnection between the application and a monitoring station, and determining a type of the disconnection based on information in the received feature set. The type of disconnection may be determined by inputting the feature set into a classifier trained to automatically determine the type of disconnection based on the information in the feature set. Information indicative of the type of disconnection may then be input into a rules-based engine, which generates a recommendation for remediating or otherwise managing the classified disconnection.
1. A method for processing information, comprising:
receiving a feature set for an application in a medical system;
determining a disconnection between the application and a monitoring station; and
determining a type of the disconnection based on information in the feature set, wherein the information in the feature set includes a plurality of categories of information relating to the application, each category in the plurality of categories of information being indicative of a different parameter relating to the disconnection,
wherein the plurality of categories of information include at least two of a first category including a plurality of application state features, a second category including a plurality of device state features, or a third category including a plurality of network statistics features, and
wherein determining the type of disconnection includes inputting the feature set into a classifier trained to automatically determine the type of disconnection based on a predetermined combination of one or more of the application state features of the first category, one or more of the device state features of the second category, and/or one or more of the network statistics features of the third category in the feature set.
2. The method of claim 1 , further comprising:
generating a confidence score indicating a probability for the type of the disconnection automatically determined by the classifier.
3. The method of claim 1 , further comprising:
generating information indicative of a recommended course of action for the type of the disconnection determined by the classifier.
4. The method of claim 3 , wherein generating the information includes:
inputting information indicative of the type of the disconnection into a rules-based engine,
wherein the rules-based engine matches the type of the disconnection to at least one predetermined rule that corresponds to the recommended course of action.
5. The method of claim 1 , further comprising:
outputting information of the type of the disconnection on a display at the monitoring station.
6. The method of claim 5 , wherein the monitoring station is at one of a technical support location, a nurses station, or a medical monitoring facility.
7. A system for processing information, comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to:
receive a feature set for an application in a medical system;
determine a disconnection between the application and a monitoring station; and
determine a type of the disconnection based on information in the feature set,
wherein the information in the feature set includes a plurality of categories of information relating to the application, wherein each category in the plurality of categories of information is indicative of a different parameter relating to the disconnection,
wherein the plurality of categories of information include at least two of a first category including a plurality of application state features, a second category including a plurality of device state features, or a third category including a plurality of network statistics features, and
wherein the processor is configured to determine the type of the disconnection based on a classifier trained to automatically determine the type of the disconnection based on a predetermined combination of one or more of the application state features of or more of the network statistics features of the third category in the feature set.
8. The system of claim 7 , wherein the processor is configured to execute the instructions to generate a confidence score indicating a probability for the type disconnection the automatically determined by the classifier.
9. The system of claim 7 , wherein the processor is configured to execute the instructions to generate information indicative of a recommended course of action for the type of the disconnection determined by the classifier.
10. The system of claim 9 , wherein generating the information includes:
inputting information indicative of the type of disconnection into a rules-based engine,
wherein the rules-based engine matches the type of disconnection to at least one predetermined rule that corresponds to the recommended course of action.
11. The system of claim 7 , wherein the processor is configured to execute the instructions to output information indicative of the type of the disconnection on a display at the monitoring station.
12. The system of claim 11 , wherein the monitoring station is at one of a technical support location, a nurses station, or a medical monitoring facility.
13. A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to:
receive a feature set for an application in a medical system;
determine a disconnection between the application and a monitoring station; and
determine a type of the disconnection based on information in the feature set,
wherein the information in the feature set includes a plurality of categories of information relating to the application, each category in the plurality of categories of information being indicative of a different parameter relating to the disconnection,
wherein the plurality of categories of information include at least two of a first category including a plurality of application state features, a second category including a plurality of device state features, or a third category including a plurality of network statistics features, and
wherein the type of the disconnection is determined by inputting the feature set into a classifier trained to automatically determine the type of the disconnection based on a predetermined combination of one or more of the application state features of the first category, one or more of the device state features of the second category, and/or one or more of the network statistics features of the third category in the feature set.
14. The non-transitory computer readable medium of claim 13 , wherein the instructions further cause the processor to generate a confidence score indicating a probability for the type of the disconnection automatically determined by the classifier.
15. The non-transitory computer readable medium of claim 13 , wherein the instructions further cause the processor to generate information indicative of a recommended course of action for the type of the disconnection determined by the classifier.
16. The non-transitory computer readable medium of claim 15 , wherein the instructions cause the processor to generate the information by inputting information indicative of the type of the disconnection into a rules-based engine, wherein the rules-based engine matches the type of the disconnection to at least one predetermined rule that corresponds to the recommended course of action.
17. The non-transitory computer readable medium of claim 13 , wherein the instructions further cause the processor to output information indicative of the type of the disconnection on a display at the monitoring station.
18. The non-transitory computer readable medium of claim 17 , wherein the monitoring station is at one of a technical support location, a nurses station, or a medical monitoring facility.