Self-improving classification system

• US 8,027,791 B2
• Filed: 06/21/2005
• Issued: 09/27/2011
• Est. Priority Date: 06/23/2004
• Status: Active Grant

• Current Assignee: Yougene Corp.
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Soykan, Orhan
• Primary Examiner(s): BORIN, MICHAEL L
• Application Number:
  US11/157,514
• Publication Number:
  US 20060019397A1
• Time in Patent Office: 2,289 Days
• Field of Search: None
• US Class Current: 702/19
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 70/60 relating to pathologies

Abstract

A self-improving classification system classifies specimens based on class identifiers. The system stores specimen profiles in a database that is updated with additional specimen profiles and with follow-up data that corrects classification of specimens that were initially incorrectly classified. Algorithms use the updated database to discover new class identifiers, modify thresholds of known class identifiers, and drop unnecessary class identifiers to improve classification of specimens.

Claims

1. A self improving method of classifying a specimen from a patient at possible risk of ventricular tachyarrhythmia/ventricular fibrillation (VT/VF), the method comprising:

using an algorithm, by a computer, for classifying specimens based on at least one class identifier, wherein said class identifier includes a Single Nucleotide Polymorphism (SNP), the SNP selected from the group consisting of SEQ ID NO.'"'"'s 1-83 and 102;

generating a specimen profile from the specimen by analyzing the genomic information of the specimen and storing, by a computer, the specimen profile in a database;

classifying, based on the specimen profile, the specimen into a class of being from a patient at possible risk of VT/VF;

the classifying being carried out using the algorithm;

determining if reclassification of the specimen is necessary;

refining the algorithm based on a refinement of the at least one class identifier, and

reclassifying the specimen if necessary, by a computer.

2. The self-improving method of classifying a specimen of claim 1 wherein the specimen profile includes data selected from a group consisting of demographic, historical, psychiatric, physiological, pathological, metabolic, genomic, proteomic, and lipidomic information.

3. The self-improving method of classifying a specimen of claim 1 wherein the class identifier is based on a class distinction of previously classified specimens.

4. The self-improving method of classifying a specimen of claim 1 wherein the specimen is a person.

5. The self-improving method of classifying a specimen of claim 1 wherein refining the algorithm comprises:

identifying new class identifiers.

6. The self-improving method of classifying a specimen of claim 1 wherein the algorithm is based on a plurality of class identifiers.

7. The self-improving method of classifying a specimen of claim 1, wherein determining if reclassification of the specimen is necessary is based on follow-up data.

8. The self-improving method of classifying a specimen of claim 1, wherein said algorithm is a type selected from the group consisting of linear, non-linear, and logical algorithms.

9. The self-improving method of classifying a specimen of claim 1, wherein the algorithm evaluates if a patient had no prior stent and has an a/a genotype of the Single Nucleotide Polymorphism (SNP) represented by SEQ ID NO. 30, then the patient is placed in a first group for those patients deemed not at risk of ventricular tachyarrhythmia, whereas if the patient had no prior stent and has a g/a or g/g genotype of SEQ ID NO. 30, then the patient is placed in a second group for further partitioning.

10. The self-improving method of classifying a specimen of claim 9, wherein if the patient has the g/a or g/g genotype of SEQ ID NO. 30, and has a c/c or t/c genotype of the Single Nucleotide Polymorphism (SNP) represented by SEQ ID NO. 105, then the patient is placed in a third group for those patients deemed to be at risk of ventricular tachyarrhythmia, whereas if the patient has a t/t genotype of SEQ ID NO. 105, then the patient is placed in a fourth group for further partitioning.

11. The self-improving method of classifying a specimen of claim 10, wherein if the patient has the t/t genotype of SEQ ID NO. 105, and has g/g genotype of the Single Nucleotide Polymorphism (SNP) represented by SEQ ID NO. 81, then the patient is placed in a fifth group for those patients deemed not at risk of ventricular tachyarrhythmia, whereas if the patient has a g/a or a/a genotype of SEQ ID NO. 81, then the patient is placed in a sixth group for further partitioning.

12. The self-improving method of classifying a specimen of claim 11, wherein if the patient has the g/a or a/a genotype of SEQ ID NO. 81, and has a g/g genotype of the Single Nucleotide Polymorphism (SNP) represented by SEQ ID NO. 63, then the patient is placed in a seventh group for those patients deemed at risk of ventricular tachyarrhythmia, whereas if the patient has an a/a or g/a genotype of SEQ ID NO. 63 then the patient is placed in an eighth group for further partitioning.

13. The self-improving method of classifying a specimen of claim 12, wherein if the patient has the a/a or g/a genotype of SEQ ID NO. 63, and has a g/g genotype of the Single Nucleotide Polymorphism (SNP) represented by SEQ ID NO. 102, then the patient is placed in a ninth group of patients deemed at risk of ventricular tachyarrhythmia, whereas if the patient has an a/a or g/a genotype of SEQ ID NO. 102 then the patient is placed in a tenth group of patients deemed not at risk of ventricular tachyarrhythmia.