Methods and kits for managing diagnosis and therapeutics of bacterial infections

• US 7,418,399 B2
• Filed: 10/05/2001
• Issued: 08/26/2008
• Est. Priority Date: 03/10/1999
• Status: Expired due to Term

• Current Assignee: Illinois Institute of Technology, Northwestern University
• Original Assignee: Illinois Institute of Technology, Northwestern University
• Inventors: Frieder, Ophir, Schaeffer, Anthony J.
• Primary Examiner(s): Gilligan; C Luke
• Assistant Examiner(s): Najarian; Lena
• Application Number:
  US09/972,762
• Publication Number:
  US 20020107641A1
• Time in Patent Office: 2,517 Days
• Field of Search: 705/2, 705/3, 600/300
• US Class Current: 705/2
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/60 relating to pathologies

Abstract

A method for the construction and utilization of a medical records system capable of providing a continuous data stream of epidemiological data to the records system via kits provided to the symptomatic population to obtain and record an epidemiological profile in a searchable database by applying data mining or automated intelligence techniques whereby, when a valid epidemiological profile is established in the database, automated diagnosis and prescription of treatment may be had for patients presenting similar symptoms. Knowledge discovery techniques may further operate on the database to provide suggested courses of treatment for a virtual class of patients, epidemic threat awareness, and knowledge of drug resistance mutations by a pathogen without direct query of the database.

Claims

1. A method for the construction and utilization of a medical records system, comprising:

collecting epidemiological information of female persons having or previously having a urinary tract infection, wherein the epidemiological information includes identifications of bacterial pathogens, treatment antimicrobials, and antimicrobial efficacy;

entering and storing the collected epidemiological information in an electronic database, the database including a record of a plurality of different types of bacterial pathogens known for causing urinary tract infections, antimicrobials used for treating the urinary tract infections, and treatment efficacy of the antimicrobials;

creating an automated knowledge discovery system, including organizing the epidemiological information in the electronic database to make the epidemiological information amenable to data mining;

receiving through a query function of the database patient epidemiological information from a patient having a urinary tract infection, the patient epidemiological information including at least one symptom of the patient and demographic and personal information for the patient;

automatically predicting with the knowledge discovery system a bacterial pathogen causing the patient'"'"'s urinary tract infection from the plurality of different types of bacterial pathogens known for causing urinary tract infections by data mining the organized epidemiological information as a function of similarities of the patient epidemiological information with the organized epidemiological information and without first performing a diagnostic test on a sample from the patient;

automatically predicting with the knowledge discovery system an antimicrobial treatment for the patient based on the bacterial pathogen prediction of the data mining; and

automatically issuing to a medical practitioner treating the patient a report including the antimicrobial treatment for the patient based on the bacterial pathogen prediction.

2. The method according to claim 1, further comprising allowing the female persons to self-test for bacterium identification, and entering results of the self-test into the database.

3. The method according to claim 1, further comprising allowing the female persons to self-test for the treatment efficacy, and entering results of the self-test into the database.

4. The method according to claim 1, wherein the data mining comprises a technique selected from Discrimination, Association Rules (Analysis), Classification (Decision Trees), Clustering data mining techniques, and combinations thereof.

5. The method according to claim 1, further comprising:

providing a kit to each of the female persons for collecting at least one of epidemiological information and a diagnostic sample;

receiving from the female persons the epidemiological information and a plurality of diagnostic samples;

evaluating the diagnostic samples to obtain bacterial pathogen information;

entering and storing the collected epidemiological information and the bacterial pathogen information in the electronic database;

providing a similar kit to the patient for collecting the patient epidemiological information.

6. The method according to claim 5, further comprising:

receiving from the female persons a plurality of second diagnostic samples obtained after antimicrobial treatment;

evaluating the second diagnostic samples to obtain further bacterial pathogen information;

entering and storing the further bacterial pathogen information in the electronic database.

7. The method according to claim 1, wherein the course of antimicrobial treatment comprises an enumeration of antimicrobials not to be prescribed to the patient.

8. The method according to claim 1, wherein the data mining comprises identifying information common to the female persons who developed an infection from a particular pathogen.

9. The method according to claim 8, wherein the data mining comprises identifying the efficacy of antimicrobials used in treating a particular bacterial pathogen.

10. The method according to claim 1, wherein the data mining comprises identifying the efficacy of antimicrobials used in treating a particular bacterial pathogen.

11. The method according to claim 1, wherein the data mining comprises continuously executing knowledge discovery operations on the data and giving suggestions selected from treatment patterns and epidemiological scenarios, for presentation to a health care practitioner.

12. The method according to claim 11, wherein the suggestions are based at least in part on past health care practitioner decisions entered into the electronic database.

13. The method according to claim 11, wherein the suggestions are based at least in part on past health care practitioner comments regarding a validity or value of given suggestions, the comments being stored as further information in the knowledge discovery system.

14. The method according to claim 1, the knowledge discovery system further providing predictive treatment outcome generation via a virtual patient to develop answers to hypothetical scenarios by automatically mining the data to derive potential treatment patterns for a virtual patient or group of patients.

15. The method according to claim 1, the knowledge discovery system further providing epidemic threat detection through data mining related to group diagnostic patterns and demographic categories.

16. The method according to claim 1, wherein creating the knowledge discovery system comprises data cleaning of the entered epidemiological information for integration of data from several sources.

17. The method according to claim 1, wherein creating the knowledge discovery system comprises data transformation of the entered epidemiological information to a common format.

18. The method according to claim 1, wherein creating the knowledge discovery system comprises data mining of the entered epidemiological information to detect patterns found in the entered epidemiological information.

19. The method according to claim 1, wherein creating the knowledge discovery system comprises pattern evaluation and knowledge representation.

20. The method according to claim 1, wherein creating the knowledge discovery system includes a process comprising iterative refinement of the following steps:

data cleaning of the entered epidemiological information;

data transformation of the entered epidemiological information to a common format;

data mining of the entered epidemiological information; and

pattern evaluation and knowledge representation of knowledge gained from the data mining.

21. A method for the construction and utilization of a medical records system, comprising:

collecting epidemiological information of members of a population having or previously having a urinary tract infection, the epidemiological information selected from the group consisting of personal information, demographic information, symptoms, samples, and combinations thereof;

entering and storing the collected epidemiological information in an electronic database, the database including a record of a plurality of different types of bacterial pathogens known for causing urinary tract infections, antimicrobials used for treating the urinary tract infections, and treatment efficacy of the antimicrobials;

creating an automated knowledge discovery system including organizing the epidemiological information in the electronic database to provide organized epidemiological information that is amenable to data mining;

obtaining in a data processing device from a requester epidemiological information of a patient having a urinary tract infection, wherein the requester is a medical practitioner treating the patient and the epidemiological information of the patient includes at least one symptom of the patient and demographic and personal information for the patient and is entered into a query function of the database;

automatically predicting from the plurality of different types of bacterial pathogens known for causing urinary tract infections a pathogen causing the patient'"'"'s urinary tract infection using only the data processing device by data mining the organized epidemiological information as a function of similarities of the patient epidemiological information with the organized epidemiological information and without first performing a diagnostic test on a sample from the patient; and

automatically submitting to the requester the pathogen prediction for prescribing antimicrobial treatment to the patient based on the prediction.

22. The method according to claim 21, wherein the data mining comprises a technique selected from Discrimination, Association Rules (Analysis), Classification (Decision Trees), Clustering data mining techniques, and combinations thereof.

23. The method according to claim 21, wherein collecting prior epidemiological information of members of a population comprises:

providing a kit to each of a plurality of members of a population having symptoms associated with a urinary tract infection for collecting at least one of prior epidemiological information of and a diagnostic sample from each of the members of the population;

receiving from the members of a population epidemiological information and a plurality of diagnostic samples;

evaluating the diagnostic samples to obtain pathogen information.

24. The method according to claim 23, wherein the kit includes a diagnostic test for obtaining the diagnostic sample.

25. The method according to claim 23, wherein the diagnostic samples are forwarded to an evaluating entity.

26. The method according to claim 21, wherein organizing the epidemiological information comprises a data cleaning of the collected epidemiological information.

27. The method according to claim 26, wherein the data cleaning comprises review of the data set, removal or correction of erroneous data, and the transformation of the data to a common format to support the processing of the data.

28. A method for the construction and utilization of a medical records system, comprising:

distributing a plurality of first kits to a population presenting symptoms of a urinary tract infection, wherein the first kits are for establishing and recording epidemiological data for the population;

establishing and recording epidemiological data of the population, the epidemiological data including the symptoms in the population, demographic and personal information in the population, incidence of bacterial pathogens causing symptoms in the population, use of a medicine for treatment of the bacterial pathogens in the population, and results of treatment via the medicine in the population;

building in a searchable database an epidemiological profile of the population via data mining of the epidemiological data, the database including a record of a plurality of different types of bacterial pathogens known for causing urinary tract infections, antimicrobials used for treating the urinary tract infections, and treatment efficacy of the antimicrobials;

distributing a second kit to an undiagnosed patient presenting symptoms of a urinary tract infection for establishing and recording epidemiological data for the undiagnosed patient;

receiving the epidemiological data for the undiagnosed patient in a data processing device in combination with the database, the epidemiological data including at least one symptom for the undiagnosed patient and demographic and personal information for the undiagnosed patient; and

the data processing device automatically predicting from the plurality of different types of bacterial pathogens known for causing urinary tract infections a bacterial pathogen causing the undiagnosed patient'"'"'s urinary tract infection from identification of the bacterial pathogens recorded in the searchable database by comparing the epidemiological data for the undiagnosed patient to the epidemiological profile of the population and without first performing a diagnostic test on a sample from the patient; and

automatically issuing to a medical practitioner treating the patient a report including the antimicrobial treatment for the patient based on the bacterial pathogen prediction.

29. The method according to claim 28, wherein the data mining comprises a technique selected from Discrimination, Association Rules (Analysis), Classification (Decision Trees), Clustering data mining techniques, and combinations thereof.

30. The method according to claim 28, further comprising automatically prescribing with the knowledge discovery system a course of treatment for the patient based on the pathogen prediction of the data mining.

31. The method according to claim 30, wherein the course of treatment comprises an enumeration of antimicrobials not to be prescribed to the patient.