Predisposition prediction using attribute combinations

• US 8,051,033 B2
• Filed: 05/13/2007
• Issued: 11/01/2011
• Est. Priority Date: 03/16/2007
• Status: Active Grant

• Current Assignee: 23andme Incorporated (23andMe Holding Co.)
• Original Assignee: Expanse Networks, Inc.
• Inventors: Eldering, Charles Anthony, Kenedy, Andrew Alexander
• Primary Examiner(s): HICKS, MICHAEL J
• Application Number:
  US11/747,913
• Publication Number:
  US 20080228723A1
• Time in Patent Office: 1,633 Days
• Field of Search: None
• US Class Current: 707/603
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/2282 Tablespace storage structures; Management thereof
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 20/40 Population genetics; Linkage disequilibrium
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/20 : relating to practices or guidelines
• CPC Class Codes: H04L 67/306 : User profiles

Abstract

A method and system are presented in which predisposition predictions are generated for an individual with respect to an attribute indicated in a query. The predictions are based on the identification of predisposing attribute combinations within the attribute profile of the individual and statistical results that indicate the strength of association of the identified attribute combinations with the query attribute.

Claims

1. A computer based method for predisposition prediction wherein a relative likelihood of medical disease predisposition for an individual may be determined based on datasets containing predetermined association of attributes combining pangenetic and non-pangenetic attributes and combinations thereof with said disease, said method performed on a computer including a user interface, a processor, a memory, and a display, comprising:

a) said computer receiving a medical disease associated query attribute via said user interface into said processor;

b) said processor accessing an attribute profile of said individual contained in said memory;

c) said processor accessing a stored dataset in said memory containing said predetermined attribute combinations combining pangenetic and non-pangenetic attributes and statistical results that indicate the strength of association of each of the attribute combinations in said stored dataset, said statistical association having been created by comparing previously submitted and assessed attribute profiles of individuals with the medical disease query attribute and comparing the submitted attribute profiles with attributes profiles of those not having the medical disease query, so as to eliminate shared attribute combinations and list only those combinations of attributes beyond a threshold strength of association with the medical disease query;

d) identifying attribute combinations from the stored dataset of predetermined attribute combinations associated with said medical disease that occur in the attribute profile of said individual by comparing the attribute combinations occurring in both the attribute profile of the individual and in the dataset attribute profiles; and

e) generating a dataset ranked output of one or more predisposition predictions for the individual based on the identified attribute combinations appearing in both the predetermined dataset and in the attribute profile of said individual and the statistical results indicating a relative predisposition of said individual to acquire said disease.

2. The computer based method of claim 1, wherein the predisposition predictions are generated based on the statistical results for the largest identified attribute combination.

3. The computer based method of claim 1, further comprising:

f) storing the predisposition predictions in said memory.

4. The computer based method of claim 1, further comprising:

f) associating the predisposition predictions with the individual and storing the association in said memory.

5. The computer based method of claim 4, wherein storing the association comprises storing a link to one or more of an identifier of the individual, the attribute profile of the individual, and a record of the individual.

6. The computer based method of claim 1, further comprising:

f) repeating steps (a)-(e) for a succession of query attributes to create a tabulated predisposition prediction report, profile or record.

7. The computer based method of claim 1, further comprising:

f) transmitting the predisposition predictions as output.

8. The computer based method of claim 1, further comprising:

f) transmitting the predisposition predictions to create an attribute prediction report, profile or record.

9. The computer based method of claim 1, further comprising:

f) updating attribute combinations and statistical results contained in the dataset based on the content of the attribute profile.

10. The computer based method of claim 1, wherein the query attribute comprises a combination of two or more attributes.

11. The computer based method of claim 4, wherein the predisposition predictions meet one or more statistical requirements.

12. The computer based method of claim 8, wherein the predisposition predictions meet one or more statistical requirements.

13. The computer based method of claim 12, wherein the one or more statistical requirements are selected from the group consisting of a minimum statistical value, a maximum statistical value, and a value of statistical significance.

14. The computer based method of claim 1, further comprising:

f) eliminating predisposition predictions that are based on attribute combinations which lack one or more specified attributes.

15. The computer based method of claim 1, further comprising:

f) eliminating predisposition predictions that are based on attribute combinations which contain one or more specified attributes.

16. A computer based system for predisposition prediction wherein a relative likelihood of medical disease predisposition for an individual may be determined based on datasets containing predetermined association of attributes combining pangenetic and non-pangenetic attributes and combinations thereof with said disease, comprising:

a) a data receiving subsystem processor for receiving a query attribute associated with said medical disease;

b) a first data accessing subsystem memory for accessing a previously stored attribute profile of said individual;

c) a second data accessing subsystem memory for accessing a dataset containing previously stored attribute combinations combining pangenetic and non-pangenetic attributes and statistical results that indicate the strength of association of each of the attribute combinations in said stored dataset with the medical disease query attribute, said statistical strength of association having been created by comparing previously submitted and assessed attribute profiles of individuals with the medical disease query attribute and comparing the submitted attribute profiles with attributes profiles of those not having the medical disease query, so as to eliminate shared attribute combinations and list only those combinations of attributes beyond a threshold strength of association with the medical disease query;

d) a data processing subsystem processor comprising;

i) a data comparison subsystem means for identifying attribute combinations from the stored data set that occur in the attribute profile of said individual; and

ii) a statistical predisposition prediction subsystem means for generating and displaying one or more predisposition predictions for the individual based on the identified attribute combinations and the statistical results indicating a relative predisposition of said individual to acquire said disease, said prediction of relative predisposition obtained by comparing the attribute combinations occurring in both the attribute profile of the individual and in the respective dataset of attribute profiles.

17. The computer based system of claim 16, further comprising:

e) a data storage subsystem means for storing the predisposition predictions and for storing an association between the predisposition predictions and the individual.

18. The computer based system of claim 16, further comprising:

e) a communications subsystem means for transmitting the predisposition predictions.

19. The computer based system of claim 16, wherein the data processing subsystem further comprises:

iii) a database updating subsystem means for updating attribute combinations and statistical results contained in the set based on the content of the attribute profile.

20. The computer based system of claim 16, wherein the data processing subsystem further comprises:

iii) a data elimination subsystem means for eliminating predisposition predictions that are based on attribute combinations which lack one or more specified attributes, or alternatively, which contain one or more specified attributes.