System and method for electronically managing medical data files in order to facilitate genetic research

• US 20050060195A1
• Filed: 07/16/2004
• Published: 03/17/2005
• Est. Priority Date: 02/24/1998
• Status: Active Grant

• Current Assignee: Luc Bessette, Marie-Pierre Dube
• Original Assignee: Luc Bessette, Marie-Pierre Dube
• Inventors: Bessette, Luc, Dube, Marie-Pierre
• Granted Patent: US 7,734,656 B2
• Time in Patent Office: Days
• US Class Current: 705/2
• CPC Class Codes: G06Q 90/00 Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
• CPC Class Codes: G06Q 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G16B 50/00 ICT programming tools or database systems specially adapted for bioinformatics
• CPC Class Codes: G16B 50/30 Data warehousing; Computing architectures
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 10/65 stored on portable record carriers, e.g. on smartcards, RFID tags or CD
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: H04L 67/01 Protocols

Abstract

A method for conducting genetic research on medical data. The method includes the step of accessing a database storing a plurality of medical records associated with a plurality of individuals, each medical record including at least one unique identifier associated with a certain individual and medical data associated with the certain individual. The method also includes the steps of extracting from the database the medical data associated with at least a subset of the plurality of individuals and, for each individual of the subset, obtaining electronically stored genetic data associated with the respective unique identifier. Also, the method includes processing the extracted medical data and obtained genetic data for attempting to identify an association between particular genetic data and a particular medical condition.

Claims

1. A method for conducting genetic research on medical data, said method comprising:

a) accessing a database storing a plurality of medical records associated with a plurality of individuals, each medical record including;

i) at least one unique identifier associated with a certain individual, and

ii) medical data associated with the certain individual;

b) extracting from said database the medical data associated with at least a subset of the plurality of individuals;

c) obtaining electronically stored genetic data on a basis of the respective unique identifier for each of said at least a subset of the plurality of individuals; and

d) processing the extracted medical data and obtained genetic data for attempting to identify an association between particular genetic data and a particular medical condition.

2. The method as defined in claim 1, wherein, for each of said at least a subset of the plurality of individuals, the associated medical data includes health status information, said method including processing the health status information and the genetic data for attempting to identify an association between particular genetic data and a particular medical condition.

3. The method as defined in claim 1, wherein, for each of said at least a subset of the plurality of individuals, the associated medical data includes disease status information, said method including processing the disease status information and the genetic data for attempting to identify an association between particular genetic data and a particular medical disease.

4. The method as defined in claim 1, wherein said step of obtaining electronically stored genetic data associated with each respective unique identifier includes extracting from said database the genetic data associated with said at least a subset of the plurality of individuals.

5. The method as defined in claim 1, wherein said database is a first database, said step of obtaining electronically stored genetic data associated with each respective unique identifier includes accessing a second database storing a plurality of medical files associated with respective individuals, each medical file including:

i) said at least one unique identifier associated with the respective individual, and

ii) genetic data associated with the respective individual.

6. The method as defined in claim 1, wherein each medical record further includes:

a) at least one pointer, said pointer using a URL addressing system to indicate the address of a location containing medical data not included in the medical record for the certain individual, the address being in a form allowing a machine to access the location and import the medical data from the location, and

b) at least one data field, said data field associated with said pointer, said data field being indicative of the particular nature of the medical data at the location pointed to by the pointer;

said step of extracting from said database the medical data associated with at least a subset of said plurality of individuals including importing the medical data from the location pointed to by said at least one pointer.

7. The method as defined in claim 2, wherein processing the extracted genetic data and health status information includes generating an association model.

8. The method as defined in claim 7, further comprising updating said association model when new electronically stored genetic data becomes available.

9. The method as defined in claim 7, including generating said association model on the basis of principal components statistics.

10. The method as defined in claim 7, including generating said association model on the basis of an artificial neural network.

11. The method as defined in claim 10, wherein generating said association model includes training said artificial neural network.

12. The method as defined in claim 11, wherein training said artificial neural network includes providing input and output training data to said artificial neural network, said input training data including the genetic data and said output training data including the health status information.

13. The method as defined in claim 1, wherein the step of obtaining electronically stored genetic data associated with the respective unique identifier includes obtaining genetic data in a format selected from one of a segment of a sequence of patient chromosomal genome, an entire sequence of patient chromosomal genome, a segment of a sequence of patient mitochondrial genome, an entire sequence of patient mitochondrial genome, an entire sequence of patient chromosomal and mitochondrial genome, a single nucleotide polymorphism (SNP), a SNP haplotype, a SNP haplotype tag, or a polymorphic marker.

14. A method for conducting genetic research on medical data, said method comprising:

(a) accessing a database storing a plurality of medical records associated with a plurality of individuals, each medical record including;

(i) at least one unique identifier associated with a certain individual,

(ii) medical data associated with the certain individual, said medical data including health status information, and

(iii) genetic data associated with the certain individual;

(b) extracting from said database the health status information and the genetic data associated with at least a subset of said plurality of individuals; and

(c) processing the extracted medical data and genetic data for attempting to identify an association between particular genetic data and a particular medical condition.

15. A method for conducting genetic research on medical data, said method comprising:

a) accessing a database storing a plurality of medical records associated with a plurality of individuals, each medical record including;

i) at least one unique identifier associated with a certain individual, and

ii) medical data associated with the certain individual, said medical data including health status information;

b) extracting from said database the health status information associated with at least a subset of said plurality of individuals;

c) obtaining electronically stored genetic data associated with the respective unique identifier for each of said at least a subset of said plurality of individuals; and

d) providing the genetic data and health status information to an adaptive expert system, said adaptive expert system capable of processing the genetic data and health status information for attempting to identify an association between particular genetic data and a particular medical condition.

16. A method for conducting genetic research on medical data of a network system, said network system including at least one server managing a database, said database containing a plurality of medical records associated with respective individuals, said method comprising:

a) including in each medical record at least one unique identifier associated with a certain individual and a collection of medical data elements associated with the certain individual, said collection of medical data elements including genetic data and health status information;

b) accessing at least a subset of said medical records stored in said database;

c) extracting the genetic data and health status information from said at least a subset of medical records; and

d) providing the extracted genetic data and health status information to an adaptive expert system, said adaptive expert system capable of processing the extracted genetic data and health status information for attempting to identify an association between particular genetic data and a particular medical condition.

17. In combination:

a) a network server having a first database storing a plurality of medical records associated with respective individuals, each medical record having;

i) at least one unique identifier associated with a certain individual, and

ii) a collection of medical data elements associated with the certain individual, said collection of medical data elements including health status information;

b) a second database storing a plurality of medical files associated with respective individuals, each medical file having;

i) said at least one unique identifier associated with the respective individual, and

ii) genetic data associated with the respective individual; and

c) an adaptive expert system able to extract from said first and second databases the health status information and genetic data associated with at least a subset of individuals, said adaptive expert system operative to process the extracted genetic data and health status information for attempting to identify an association between particular genetic data and a particular medical condition.

18. In combination:

a) a network server having a database storing a plurality of medical records associated with a plurality of individuals, each medical record having;

i) at least one unique identifier associated with a certain individual, and

ii) a collection of medical data elements associated with the certain individual, said collection of medical data elements including health status information and genetic data; and

b) an adaptive expert system able to extract from said database the health status information and genetic data associated with at least a subset of said plurality of individuals, said adaptive expert system operative to process the extracted genetic data and health status information to attempt to identify an association between particular genetic data and a particular medical condition.

19. A network server, comprising:

I) a processor; and

II) a memory including;

A) a plurality of medical records associated with respective individuals, each medical record having at least one unique identifier associated with a certain individual and having a collection of medical data elements associated with the certain individual, said collection of medical data elements including genetic data;

B) a program element including individual instructions for execution by said processor, said program element being responsive to a genetic research query issued by a client connected to said server through a data communication pathway for;

(1) identifying at least a subset of said plurality of medical records,

(2) extracting at least a portion of said collection of medical data elements from each identified medical record, said at least a portion of said collection of medical data elements including selected genetic data associated with the respective individual, and

(3) transferring said at least a portion of said collection of medical data elements towards the client over the data communication pathway.

20. The network server as defined in claim 19, wherein each said medical record further has:

a) at least one pointer, said pointer using a URL addressing system to indicate the address of a location containing medical data not included in the medical record for the certain individual, the address being in a form allowing a machine to access the location and import the medical data from the location; and

b) at least one data field, said data field associated with said pointer, said data field being indicative of the particular nature of the medical data at the location pointed to by the pointer.