Dropout Detection in Continuous Analyte Monitoring Data During Data Excursions

Abstract

Methods, devices, and systems are provided for identifying dropouts in analyte monitoring system sensor data including segmenting sensor data into a plurality of time series wherein each time series is associated with a different instance of a repeating event, selecting a first time series to analyze for dropouts from the plurality of time series; comparing the selected first time series to a second time series among the plurality of time series, determining whether the selected first time series includes a portion that is more than a predefined threshold lower than a corresponding portion of the second time series, and displaying, on a computer system display, an indication that the selected first time series includes a dropout if the selected first time series includes a portion that is more than the predefined threshold lower than the corresponding portion of the second time series.

What is claimed is: 
     
         1 . A method, comprising:
 receiving sensor data from an analyte sensor configured to be positioned at least in part in contact with a fluid under a skin layer, the sensor data corresponding to a monitored analyte level of the fluid;   segmenting the sensor data into a plurality of time segments, the plurality of time segments including a first segment comprising a first instance, and a second segment comprising a second instance;   applying a time dilation and correlation operation to the sensor data of the first segment to obtain a time dilated and correlated first segment, wherein the time dilation and correlation operation comprises:
 performing a first one of a time dilation operation or a correlation operation to the sensor data of the first segment,
 the time dilation operation comprising dilating the sensor data of the first segment to obtain the time dilated first segment, wherein the sensor data of the time dilated first segment over a first period of time corresponds to the sensor data of the second segment over a second period of time, and 
 the correlation operation comprising correlating the sensor data of the first segment over the first period of time to the sensor data of the second segment over the second period of time to obtain the correlated first segment; 
 
 applying a second one of the time dilation operation or the correlation operation to the time dilated first segment or the correlated first segment to obtain the time dilated and correlated first segment; and 
   determining that the first segment includes a dropout when the time dilated and correlated first segment over the first period of time differs by more than a threshold from the sensor data of the second segment over the second period of time.   
     
     
         2 . The method of  claim 1 , further comprising:
 providing an indication on a display that the first segment includes the dropout.   
     
     
         3 . The method of  claim 1 , further comprising:
 marking the segmented sensor data based on the determined dropout.   
     
     
         4 . The method of  claim 1 , further comprising at least one of:
 correcting the received sensor data based on the determined dropout; or   correcting future sensor data based on the determined dropout.   
     
     
         5 . The method of  claim 1 , further comprising:
 dynamically varying the threshold used for determining that the sensor data of the time dilated first segment over the first period of time differs from the sensor data of the second segment over the second period of time.   
     
     
         6 . The method of  claim 5 , wherein the dynamically varying threshold varies according to a noise quality of the analyte sensor. 
     
     
         7 . The method of  claim 1 , wherein the first instance and the second instance correspond to a periodic event, wherein the periodic event is a meal, and further comprising receiving a user input for a time marker of at least the first instance or the second instance. 
     
     
         8 . The method of  claim 1 , wherein applying the time dilation operation to the first segment comprises determining a set of time dilation parameters, and applying the set of time dilation parameters to the first segment to obtain the time dilated first segment; and
 wherein determining that the sensor data of the time dilated first segment over the first period of time differs by more than the threshold from the sensor data of the second segment comprises determining a ratio for the sensor data of the time dilated first segment and the sensor data of the second segment.   
     
     
         9 . The method of  claim 1 , wherein the first segment is a most recent segment of the plurality of time segments. 
     
     
         10 . The method of  claim 1 , wherein the first period of time and the second period of time are of different lengths. 
     
     
         11 . The method of  claim 1 , wherein the sensor data from the analyte sensor is received continuously. 
     
     
         12 . A system, comprising:
 an analyte sensor configured to be positioned at least in part in contact with a fluid under a skin layer to generate sensor data corresponding to a monitored analyte level of the fluid; and   a receiving device comprising one or more processors and a memory storing instructions which, when executed by the one or more processors, cause the system to:   receive sensor data from the analyte sensor;   segment the sensor data into a plurality of time segments, the plurality of time segments including a first segment comprising a first instance, and a second segment comprising a second instance;   apply a time dilation and correlation operation to the sensor data of the first segment to obtain a time dilated and correlated first segment, wherein the time dilation and correlation operation comprises:
 performing a first one of a time dilation operation or a correlation operation to the sensor data of the first segment,
 the time dilation operation comprising dilating the sensor data of the first segment to obtain the time dilated first segment, wherein the sensor data of the time dilated first segment over a first period of time corresponds to the sensor data of the second segment over a second period of time, and 
 the correlation operation comprising correlating the sensor data of the first segment over the first period of time to the sensor data of the second segment over the second period of time to obtain the correlated first segment; 
 
 applying a second one of the time dilation operation or the correlation operation to the time dilated first segment or the correlated first segment to obtain the time dilated and correlated first segment; and 
   determine that the first segment includes a dropout when the time dilated and correlated first segment over the first period of time differs by more than a threshold from the sensor data of the second segment over the second period of time.   
     
     
         13 . The system of  claim 12 , wherein the memory storing instructions which, when executed by the one or more processors, cause the system to:
 provide an indication on a display that the first segment includes the dropout.   
     
     
         14 . The system of  claim 12 , wherein the memory storing instructions which, when executed by the one or more processors, cause the system to:
 mark the segmented sensor data based on the determined dropout.   
     
     
         15 . The system of  claim 12 , wherein the memory storing instructions which, when executed by the one or more processors, cause the system to at least one of:
 correct the received sensor data based on the determined dropout; or   correct future sensor data based on the determined dropout.   
     
     
         16 . The system of  claim 12 , where the threshold used to determine that the sensor data of the time dilated first segment over the first period of time differs from the sensor data of the second segment over the second period of time is dynamically varied. 
     
     
         17 . The system of  claim 16 , wherein the dynamically varying threshold varies according to a noise quality of the analyte sensor. 
     
     
         18 . The system of  claim 12 , wherein the first instance and the second instance correspond to a periodic event, wherein the periodic event is a meal, and wherein the memory further stores instructions which, when executed by the one or more processors, cause the one or more processors to receive a user input for a time marker of at least the first instance or the second instance. 
     
     
         19 . The system of  claim 12 , wherein the one or more processors apply the time dilation operation to the first segment by at least determining a set of time dilation parameters, and applying the set of time dilation parameters to the first segment to obtain the time dilated first segment; and
 wherein the one or more processors determine that the sensor data of the time dilated first segment over the first period of time differs by more than the threshold from the sensor data of the second segment by at least determining a ratio for the sensor data of the time dilated first segment and the sensor data of the second segment.   
     
     
         20 . The system of  claim 12 , wherein the first segment is a most recent segment of the plurality of time segments. 
     
     
         21 . The system of  claim 12 , wherein the first period of time and the second period of time are of different lengths. 
     
     
         22 . The system of  claim 12 , wherein the sensor data from the analyte sensor is received continuously. 
     
     
         23 . The system of  claim 12 , wherein the memory further stores instructions which, when executed by the one or more processors, cause the system to replace the sensor data of the time dilated first segment which differs by more than the threshold from the sensor data of the second segment over the second period of time with a predetermined value.