Systems and methods of medical device data collection and processing

1. A system for processing medical device data, the system comprising:

at least one computer memory to store computer-executable instructions; and

a processor to execute the computer-executable instructions, wherein the computer-executable instructions cause the processor to:

receive a plurality of streaming time series of medical device data from one or more medical devices in real time or near real time, wherein the medical device data comprises machine data comprising at least one alarm, at least one device status, at least one device setting, at least one message, or a combination thereof;

store the plurality of streaming time series of medical device data in the at least one computer memory;

apply a plurality of case identification rules to the plurality of streaming time series of medical device data to identify portions of the plurality of streaming time series of medical device data representing clinical cases in the plurality of streaming time series of medical device data, wherein the portions of the plurality of streaming time series representing the clinical cases are identified based on a change in a status detected by delivery or consumption of an anesthetic agent, wherein the plurality of streaming time series of medical device data comprises binary data;

execute streaming analytics to apply a plurality of event detection rules to the portions of the plurality streaming time series of medical device data corresponding to the identified clinical cases to identify events within the streaming time series of medical device data of each identified clinical case;

generate one or more groups for the identified events based upon predefined recipients of notifications for the identified events;

transmit an event notification for each of the identified events to the predefined recipients associated with the one or more groups across at least one communication platform associated with the one or more groups, the event notification indicating a change to an alarm parameter of the one or more medical devices, wherein the change to the alarm parameter is applied to the one or more medical devices automatically by the system; and

automatedly refine at least one case identification rule or at least one event detection rule with the plurality of stored clinical cases in a learning network.

2. The system of claim 1 , wherein the portions of the plurality of streaming time series of the medical device data representing the clinical cases are further identified based on a start of a surgical case, a start of a medical device providing therapy or patient monitoring, detection of induction, maintenance or emergence phases, or an end of a medical procedure, or a combination thereof.

3. The system of claim 1 , wherein the processor is to preprocess the streaming time series of medical device data, wherein the streaming time series of medical device data comprises raw sensor data.

4. The system of claim 1 , wherein the processor is to process the streaming time series of medical device data to provide the time series of medical device data in one or more consistent units of measurement.

5. The system of claim 4 , wherein the processor is to create a clinical case summary from the streaming time series medical device data and store the clinical case summary in a clinical summary database, wherein each clinical case summary stored in the clinical case summary database is linked to the portions of the plurality of streaming time series of medical device data associated with the identified clinical case resulting in the clinical case summary.

6. A method for medical device data processing, the method comprising:

receiving, in real time or near real time, a plurality of streaming time series of medical device data from one or more medical devices, wherein the medical device data comprises machine data comprising at least one alarm, at least one device status, at least one device setting, at least one message, or a combination thereof;

storing the plurality of streaming time series of medical device data in at least one computer memory;

applying a plurality of case identification rules to the plurality of streaming time series of medical device data to identify portions of the plurality of streaming time series of medical device data representing clinical cases in the plurality of streaming time series of medical device data, wherein the portions of the plurality of streaming time series representing the clinical cases are identified based on a change in a status detected by detecting delivery or consumption of an anesthetic agent;

upon identification of a clinical case in the streaming time series medical device data, storing the portions of the plurality of streaming time series of medical device data of the identified clinical cases in a computer memory;

conducting further streaming analytics to apply a plurality of event detection rules to the portions of the plurality streaming time series of medical device data corresponding to the identified clinical cases to identify events within the streaming time series of medical device data of each identified clinical case; and

generating one or more groups for the identified events based upon predefined recipients of notifications for the identified events;

transmitting an event notification for each of the identified events to the predefined recipients associated with the one or more groups across at least one communication platform associated with the one or more groups, the event notification indicating a change to an alarm parameter of the one or more medical devices, wherein the change to the alarm parameter is applied to the one or more medical devices automatically by the system; and

automatedly refining at least one case identification rule or at least one event detection rule with the plurality of stored clinical cases in a learning network.

7. The method of claim 6 , wherein the portions of the plurality of streaming time series of the medical device data are further identified based on a start of a surgical case, a detection of a start of delivery of anesthesia or a medical device providing therapy or patient monitoring, detection of induction, maintenance or emergence phases, an end of a medical procedure, or a combination thereof.

8. The method of claim 6 , wherein the medical device data comprises machine data, wherein the machine data comprises at least one alarm, at least one device status, at least one device setting, at least one message, or a combination thereof.

9. The method of claim 6 , further comprising:

evaluating stored clinical cases as normal cases or outlier cases; and

providing the outlier cases to a user for manual review.

10. The method of claim 9 , further comprising tagging outlier cases with outcome data to facilitate manual review by the user.

11. The method of claim 10 , further comprising receiving an input of an acceptance by the user regarding an outlier case of the plurality of outlier cases and upon the input of the acceptance, providing the outlier case to a learning network.

12. The method of claim 11 , further comprising:

providing the normal cases to a learning network comprising a plurality of stored clinical cases.

13. The method of claim 6 , wherein the one or more medical devices include at least one anesthesia delivery machine, and wherein the streaming time series of medical device data comprises streaming time series data of anesthetic agent use.

14. The method of claim 13 , further comprising receiving surgical event scheduling data and wherein the streaming analytics further comprises applying the surgical event scheduling data to the streaming time series data of anesthetic agent use to identify a start and an end for each of the identified clinical cases.

15. The method of claim 13 , further comprising: providing an anesthetic agent use dashboard on a graphical display, the anesthetic agent use dashboard to comparatively present the anesthetic agent used by the at least one anesthesia delivery machine across a plurality of clinical cases comprising the administration of anesthesia.

16. The method of claim 13 , further comprising normalizing the streaming time series data of anesthetic agent use by converting the time series data of anesthetic agent use to time series data of liquid anesthetic flow.

17. The method of claim 6 , further comprising evaluating stored clinical cases from the computer memory to profile clinician actions in the operation of the one or more medical devices.

18. A non-transitory machine-executable medium for processing medical device data, the non-transitory machine-executable medium comprising a plurality of instructions that, in response to execution by a processor, cause the processor to:

receive a plurality of streaming time series of medical device data from one or more medical devices in real time or near real time, wherein the medical device data comprises machine data comprising at least one alarm, at least one device status, at least one device setting, at least one message, or a combination thereof;

store the plurality of streaming time series of medical device data in the at least one computer memory;

apply a plurality of case identification rules to the plurality of streaming time series of medical device data to identify portions of the plurality of streaming time series of medical device data representing clinical cases in the plurality of streaming time series of medical device data, wherein the portions of the plurality of streaming time series representing the clinical cases are identified based on a change in a status detected by delivery or consumption of an anesthetic agent, wherein the plurality of streaming time series of medical device data comprises binary data;

execute streaming analytics to apply a plurality of event detection rules to the portions of the plurality streaming time series of medical device data corresponding to the identified clinical cases to identify events within the streaming time series of medical device data of each identified clinical case;

generate one or more groups for the identified events based upon predefined recipients of notifications for the identified events;

transmit an event notification for each of the identified events to the predefined recipients associated with the one or more groups across at least one communication platform associated with the one or more groups, the event notification indicating a change to an alarm parameter of the one or more medical devices, wherein the change to the alarm parameter is applied to the one or more medical devices automatically by the processor; and

automatedly refine at least one case identification rule or at least one event detection rule with the plurality of stored clinical cases in a learning network.

19. The non-transitory machine-executable medium of claim 18 , wherein the portions of the plurality of streaming time series of the medical device data are further identified based on a start of a surgical case, a detection of a start of delivery of anesthesia or a medical device providing therapy or patient monitoring, detection of induction, maintenance or emergence phases, an end of a medical procedure, or a combination thereof.

20. The system of claim 1 , wherein the plurality of streaming time series of medical device data further comprises a plurality of waveforms and numeric data in a time series format.