Automatic recognition of known patterns in physiological measurement data
A method for analyzing physiological measurement values of a user is proposed. The method comprises at least one data acquisition step, wherein, during the data acquisition step, physiological measurement values of the user are acquired at different measurement times and stored in a measurement data record; at least one pattern selection step, wherein, during the pattern selection step, measurement values acquired during one comparison time interval are selected as at least one comparison pattern; and at least one pattern recognition step, wherein, during the pattern recognition step, patterns corresponding to the comparison pattern are sought after in the measurement data record.
1. A method for managing glucose levels of a user, comprising:
a) acquiring glucose concentration values from a glucose sensor at different measurement times and storing the glucose concentration values in a measurement data record;
b) using data reduction to generate a reduced measurement data record from the measurement data record, wherein the reduced measurement data record is used in at least one of step c) and step d);
c) selecting a current pattern from the glucose concentration values for a current time interval;
d) using pattern recognition to identify a historical pattern of the glucose concentration values that is similar to the current pattern;
e) generating a current profile of glucose concentration from the current pattern and generating a predicted future profile of glucose concentration from the historical pattern;
f) displaying the current profile and the predicted future profile on a display;
g) displaying a treatment instruction based upon the predicted future profile; and
h) the user administering the treatment.
2. The method of claim 1 , wherein the treatment instruction is one of: dosing insulin, engaging in physical activity, consuming carbohydrates and seeking medical attention.
3. The method of claim 1 , wherein the treatment instruction is dosing insulin.
4. The method of claim 1 , further comprising prompting the patient to enter a confirmation into a processor that the treatment instruction has been completed.
5. The method of claim 1 , wherein the data reduction used in step b) comprises indexing.
6. The method of claim 5 , wherein the indexing comprises checking whether a threshold is crossed between two adjacent measurement values.
7. The method of claim 6 , further comprising assigning the adjacent measurement value that is closer to the threshold to the reduced measurement data record.
8. The method according to claim 1 , wherein a correspondence between the current pattern and the historical pattern is calculated.
9. The method according to claim 8 , wherein the correspondence is a function of differences between individual measurement values in the current pattern and respective measurement values from the historical pattern.
10. The method according to claim 1 , wherein one or more boundary conditions are stored in the measurement data record and/or the reduced measurement data record.
11. The method according to claim 1 , wherein step d) comprises identifying a group of historical patterns.
12. The method according to claim 11 , wherein the group of historical patterns is subjected to an analysis.
13. The method according to claim 12 , wherein the analysis is a statistical analysis.
14. The method according to claim 13 , wherein the statistical analysis is performed using an averaged pattern and/or an error corridor.
15. A method for managing glucose levels of a user, comprising:
a) acquiring glucose concentration values from a glucose sensor at different measurement times and storing the glucose concentration values in a measurement data record;
b) using data reduction to generate a reduced measurement data record from the measurement data record, wherein the reduced measurement data record is used in at least one of step c) and step d);
c) selecting a current pattern from the glucose concentration values for a current time interval;
d) using pattern recognition to identify a historical pattern of the glucose concentration values that is similar to the current pattern;
e) generating a current profile of glucose concentration from the current pattern and generating a predicted future profile of glucose concentration from the historical pattern;
f) displaying the current profile and the predicted future profile on a display;
g) displaying an instruction to administer an insulin dose based upon the predicted future profile; and
h) administering the insulin dose.
16. The method of claim 15 , wherein the data reduction used in step b) comprises indexing.
17. The method of claim 16 , wherein the indexing comprises checking whether a threshold is crossed between two adjacent measurement values.
18. The method of claim 17 , further comprising assigning the adjacent measurement value that is closer to the threshold to the reduced measurement data record.