SYSTEMS AND METHODS FOR DETECTING GLUCOSE LEVEL DATA PATTERNS
Systems and methods for detecting and reporting patterns in analyte concentration data are provided. According to some implementations, an implantable device for continuous measurement of an analyte concentration is disclosed. The implantable device includes a sensor configured to generate a signal indicative of a concentration of an analyte in a host, a memory configured to store data corresponding at least one of the generated signal and user information, a processor configured to receive data from at least one of the memory and the sensor, wherein the processor is configured to generate pattern data based on the received information, and an output module configured to output the generated pattern data. The pattern data can be based on detecting frequency and severity of analyte data in clinically risky ranges.
1 . An analyte monitoring system configured to measure an analyte concentration of a host, the system comprising:
a sensor configured to generate sensor data indicative of a concentration of an analyte in a host over time;
a memory configured to store the sensor data;
a processor configured to receive the sensor data from at least one of the memory and detecting a pattern in the data, the detecting comprising identifying a plurality of events based on the sensor data, associating at least some of the plurality of events based on a criterion to from a set of events, and qualifying the set of events as the detected pattern; and
an output module configured to output information representative of the detected pattern.
2 . The system of claim 1 , wherein the criterion is a timeframe.
3 . The system of claim 1 , wherein qualifying the set of events as a pattern comprises determining a priority score associated with the set.
4 . The system of claim 3 , wherein the set qualifies as a pattern if the priority score exceeds a threshold.
5 . The system of claim 3 , wherein the associating includes forming a plurality of sets, and wherein the set qualifies as a pattern if the priority score of the set is greater than a predetermined number of priority scores associated with the plurality of sets.
6 . The system of claim 3 , wherein the qualifying further comprises scoring each event in a set based on one or more scoring criteria, wherein the priority score is a summation of the scores associated with the events in the set.
7 . The system of claim 6 , wherein the scoring criteria comprising a time of day associated with the event, wherein events associated with certain predefined times of day are scored higher than events associated with other times of day.
8 . The system of claim 1 , wherein identifying the plurality of events comprises calculating an average distance for a segment of time of the sensor data that exceeds a first predetermined threshold analyte level.
9 . The system of claim 8 , wherein identifying the plurality of events further comprises comparing a total amount of time the segment exceeds a second predetermined threshold analyte level to a threshold amount of time.
10 . The system of claim 9 , wherein the first predetermined threshold analyte level and the second predetermined threshold analyte level are the same.
11 . The system of claim 1 , wherein the outputting comprises displaying the information representative of the detected pattern on a user interface, wherein the displaying comprises one or more of displaying a line graph depicting the detected pattern, highlighting a chart corresponding to the detected pattern and providing a timeframe in a textual format of a timeframe associated with the detected pattern.
12 . The system of claim 1 , further comprising instructions stored in computer memory, wherein the instructions, when executed by the processor, cause the processor to perform the detecting and outputting.
13 . A method for identifying patterns based on monitored analyte concentration sensor data, the method comprising:
receiving data from at least one input, the data including measurements of an analyte concentration and time of day information associated with the measurement;
analyzing the received data to identify a plurality of clinically significant events;
determining patterns in the analyzed data, the determining comprising grouping the events based on time of day information into a plurality of event sets; and
displaying information based on one or more of the determined patterns.
14 . The method of claim 13 , wherein the measurements are generated using a continuous analyte sensor.
15 . The method of claim 14 , further comprising receiving user input indicating a timeframe and selecting the measurements that fall within the timeframe for the analyzing.
16 . The method of claim 13 , wherein the analyzing comprises detecting a plurality of episodes, wherein each of the plurality of episodes is detected by scanning the measurements using predefined criteria to determine a start and end of each episode.
17 . The method of claim 16 , wherein analyzing further comprises qualifying an episode as an event by filtering the episodes based on one or more episode characteristics.
18 . The method of claim 17 , wherein the characteristics comprise one or more of an average distance below a predetermined analyte level and a total time below a predetermined analyte level.
19 . The method of claim 13 , wherein grouping the events comprises calculating times between the events and grouping the events into sets based on the times.
20 . The method of claim 19 , wherein calculating the times between the events comprises calculating a time between the end of a first event and the end of a second event.
21 . The method of claim 19 , wherein calculating the times between the events comprises calculating a time between a nadir point of a first event and a nadir point of a second event.
22 . The method of claim 13 , wherein the determining further comprises selecting one or more sets as patterns, the selecting comprising filtering the plurality of sets based on a priority score of each group.
23 . The method of claim 22 , wherein the filtering filters out sets that have a priority score less than a threshold amount.
24 . The method of claim 22 , wherein the filtering filters out sets that have a priority score that is lower than the priority score of a predetermined number of other sets of the plurality of sets.
25 . The method of claim 13 , wherein the measurements are glucose concentration measurements and the events are hypoglycemic events.
26 . The method of claim 13 , wherein the displaying comprises displaying a timeframe corresponding to the at least one or more detected patterns.
27 . The method of claim 13 , wherein the method is performed automatically upon the expiration of a predetermined amount of time.
28 . The method of claim 13 , wherein the method is performed responsive to user input indicative of a request to initiate pattern detection.
29 . An analyte concentration pattern detection system configured to perform the method of claim 13 , the system comprising a continuous analyte sensor to generate the analyte concentration measurements, computer memory to store the generated analyte concentration measurements, a processor module configured to perform the analyzing and determining, and a user interface configured to perform the displaying.
30 . The system of claim 29 , further comprising instructions stored in the memory, wherein the instructions, when executed by the processor module, cause the processor module to perform the analyzing and determining.