Apparatus for determining association variables

• US 20070179354A1
• Filed: 11/27/2006
• Published: 08/02/2007
• Est. Priority Date: 07/10/2004
• Status: Active Grant

• Current Assignee: Trigeminal Solutions, Inc.
• Original Assignee: Trigeminal Solutions, Inc.
• Inventors: Newman, Lawrence, Lanckriet, Gert, Carpenter, Chris, Stupp, Steven
• Granted Patent: US 8,241,211 B2
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 20/60 relating to nutrition control, e.g. diets
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics

Abstract

An apparatus, and related method, for determining one or more association variables is described. The apparatus includes at least one processor, at least one memory, and at least one program module. The program module is stored in the memory and is configurable to be executed by the processor. The program module includes instructions for determining a statistical relationship between one or more temporal onsets corresponding to one or more events and a pattern of occurrence of a compound variable. The compound variable corresponds at least to a pattern of occurrence of a first variable and a pattern of occurrence of a second variable. The determining includes contributions from presence and absence information in the pattern of occurrence of the compound variable.

Claims

1. A method of determining one or more migraine variables associated with migraines, comprising:

determining a statistical relationship between one or more temporal onsets corresponding to one or more events and a pattern of occurrence of a compound variable,

wherein the compound variable corresponds at least to a pattern of occurrence of a first variable and a pattern of occurrence of a second variable, and wherein the determining includes contributions from presence and absence information in the pattern of occurrence of the compound variable; and

identifying the first variable and the second variable as the migraine variables in accordance with the statistical relationship.

2. The method of claim 1, wherein the pattern of occurrence of the first variable is during a first set of time intervals and the pattern of occurrence of a second variable is during a second set of time intervals, and wherein a respective time interval in a respective set of time intervals precedes a respective temporal onset in the one or more temporal onsets.

3. The method of claim 2, wherein time intervals in at least one of the first set of time intervals and the second set of time intervals are offset in time from the one or more temporal onsets.

4. The method of claim 2, wherein time intervals in the first set of time intervals are different than time intervals in the second set of time intervals.

5. The method of claim 1, further comprising receiving information including the one or more temporal onsets corresponding to one or more events and the pattern of occurrence of the compound variable.

6. The method of claim 1, further comprising providing recommendations to one or more individuals in accordance with the first variable and the second variable.

7. The method of claim 1, wherein the determining uses a non-parametric statistical analysis technique including a chi-square analysis technique, a log-likelihood ratio analysis technique, or a Fisher'"'"'s exact probability analysis technique.

8. The method of claim 1, wherein the determining uses a supervised learning technique including a support vector machines (SVM) analysis technique or a classification and regression tree (CART) analysis technique.

9. The method of claim 1, wherein the pattern of occurrence of the first variable and the pattern of occurrence of the second variable comprise categorical data, and wherein a respective entry in the pattern of occurrence of the compound variable is determined by performing a logical operation on corresponding entries in the pattern of occurrence of the first variable and the pattern of occurrence of the second variable.

10. The method of claim 9, wherein the logical operation is a Boolean operation selected from a group consisting of AND, OR, NOT and XOR.

11. The method of claim 1, further comprising determining statistical relationships for a plurality of compound variables, wherein a respective compound variable in the plurality of compound variables corresponds to patterns of occurrence of at least two variables in a set of variables, one of at least the two variables occurring during one set of time intervals and another of at least the two variables occurring during another set of time intervals, and wherein a respective time interval in a respective set of time intervals precedes a respective temporal onset in the one or more temporal onsets.

12. The method of claim 11, further comprising ranking the plurality of compound variables in accordance with the statistical relationships.

13. The method of claim 11, further comprising ranking variables in the set of variables in accordance with a number of occurrences of the variables in the compound variables having statistical relationships that approximately exceed a statistical confidence threshold.

14. The method of claim 1, wherein the pattern of occurrence of the first variable and the pattern of occurrence of the second variable include presence and absence information.

15. The method of claim 1, wherein the migraine variables are migraine triggers and the one or more events correspond to one or more migraines experienced by at least one individual.

16. The method of claim 15, wherein one or more of the migraine triggers at least in part induce a migraine in at least the one individual if at least the one individual is exposed to one or more of the migraine triggers.

17. The method of claim 15, further comprising associating at least the one individual with one or more groups of migraine triggers in accordance with one or more of the identified migraine variables.

18. The method of claim 1, further comprising determining a subset of temporal onsets in a set of temporal onsets, wherein the subset of temporal onsets includes one or more onsets corresponding to one or more migraines experienced by at least one individual, the set of temporal onsets includes the subset of temporal onsets and one or more temporal onsets corresponding to one or more additional headaches experienced by at least the one individual, and wherein the determining of the statistical relationship uses the subset of temporal onsets and the pattern of occurrence of the compound variable.

19. The method of claim 18, wherein the one or more additional headaches include one or more rebound migraines, one or more recurrence migraines, or one or more tension headaches.

20. A method of determining one or more migraine variables associated with migraines, comprising:

transmitting a first data stream including one or more temporal onsets corresponding to one or more events, a pattern of occurrence of a first variable and a pattern of occurrence of a second variable; and

receiving a second data stream including information that identifies the first variable and the second variables as the migraine variables,

wherein the information is determined in accordance with a statistical relationship between the one or more temporal onsets and a pattern of occurrence of a compound variable, the compound variable corresponding at least to the pattern of occurrence of the first variable and the pattern of occurrence of the second variable, and wherein the statistical relationship includes contributions from presence and absence information in the pattern of occurrence of the compound variable.