Optimizing test procedures for a subject under test

• US 8,762,165 B2
• Filed: 12/31/2010
• Issued: 06/24/2014
• Est. Priority Date: 06/14/2006
• Status: Active Grant

• Current Assignee: Bosch Automotive Service Solutions LLC (SPX Corporation)
• Original Assignee: Bosch Automotive Service Solutions LLC (SPX Corporation)
• Inventors: Gilbert, Harry M., Portyanko, Alex, Mayes, Randy L., Fountain, Gregory J., Wittliff, William III
• Primary Examiner(s): Rangrej, Sheetal R
• Application Number:
  US12/982,975
• Publication Number:
  US 20110161104A1
• Time in Patent Office: 1,271 Days
• Field of Search: 705 2- 3
• US Class Current: 705/2
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

In a computer-implemented method of optimizing a diagnostic test sequence to diagnose a medical condition of a subject. A group of diagnostic tests related to a symptom is determined from a pool of diagnostic tests. A probabilistic failure mode analysis is conducted to determine the efficacy of each of the diagnostic tests based on historical outcomes of actual diagnostic testing. The comparative utility of each diagnostic tests based on a plurality of factors that can affect problem resolution is analyzed. A weight is assigned to each factor involved in the probabilistic failure mode analysis. The diagnostic tests are ordered based upon at least one of: a probability of the diagnostic test identifying a cause of the failure mode in a minimum amount of time; a probability of the diagnostic test identifying the cause of the failure mode at a minimum cost; and a relative weighting of minimizing time versus minimizing cost. A first diagnostic test is selected from the group based at least in part on a probabilistic failure mode analysis and the weighted factors involved therein.

Claims

1. A computer-implemented method of optimizing a diagnostic test sequence to diagnose a medical condition of a subject, comprising:

determining a group of diagnostic tests related to a symptom of the subject from a pool of diagnostic tests;

conducting a probabilistic medical condition analysis determining an efficacy of each of the diagnostic tests based on historical outcomes of actual diagnostic testing;

analyzing a comparative utility of each diagnostic tests based on a plurality of factors that can affect a problem resolution;

assigning a weight to each factor involved in the probabilistic medical condition analysis;

ordering the diagnostic tests based upon at least one of the following;

a probability of the diagnostic test identifying a cause of the medical condition in a minimum amount of time;

a probability of the diagnostic test identifying the cause of the medical condition at a minimum cost; and

a relative weighting of minimizing time versus minimizing cost; and

selecting a first diagnostic test from the group of diagnostic tests based at least in part on the probabilistic medical condition analysis and the weighted factors involved therein.

2. The computer-implemented method according to claim 1 further comprising performing the probabilistic medical condition analysis to quantify the comparative utility of an individual diagnostic test of the group of diagnostic tests.

3. The computer-implemented method according to claim 1, wherein the probabilistic medical condition analysis is based at least on one factor selected from the following:

an estimated time required to perform the first diagnostic test, a difficulty of performing the first diagnostic test, an estimated cost to perform the first diagnostic test, and availability of health insurance to pay for the first diagnostic test.

4. The computer-implemented method according to claim 1, wherein the probabilistic medical condition analysis is based on one factor selected from the following:

an availability of a medical device to perform the first diagnostic test, an estimated cost of performing the first diagnostic test, an estimated cost per time unit of labor, an empirical data regarding a probability that the medical condition exists given the existence of the symptom, an estimate of the probability that the medical condition exists given the existence of the symptom, a frequency of the medical condition, a medical history of the subject, other pre-existing conditions of the subject, and family medical history of the subject.

5. The computer-implemented method according to claim 1, wherein the weight assigned is based at least in part on a medical professional'"'"'s preference setting.

6. The computer-implemented method according to claim 1, wherein the probabilistic medical condition analysis is based at least in part on a medical diagnostic test manual.

7. The computer-implemented method according to claim 1 further comprising receiving a medical history of the subject, and wherein the step of selecting the first diagnostic test is further based at least in part on the medical history.

8. The computer-implemented method according to claim 7, wherein the medical history comprises at least one component selected from the following:

a pre-existing condition, an age of the subject, a gender of the subject, environmental exposures of the subject, and family medical history of subject.

9. The computer-implemented method according to claim 1, wherein the first diagnostic test has a highest probability of identifying a cause of the symptom in a least amount of time among the group of diagnostic tests based at least in part on the probabilistic medical condition analysis.

10. The computer-implemented method according to claim 1, wherein the first diagnostic test has a highest probability of identifying a cause of the symptom with a lowest cost among the group of diagnostic tests based at least in part on the medical condition analysis.

11. The computer-implemented method according to claim 1, further comprising:

selecting a plurality of additional diagnostic tests from the group of diagnostic tests based at least in part on the medical condition analysis; and

ordering the plurality of additional diagnostic tests based at least in part on the probabilistic medical condition analysis.

12. The computer-implemented method according to claim 11, wherein the selecting and ordering of the plurality of additional tests are further based on a decreasing probability of each of the plurality of additional diagnostic tests identifying a cause of the symptom in a least amount of time based on the probabilistic medical condition analysis.

13. The computer-implemented method according to claim 11, wherein the selecting and ordering of the plurality of additional diagnostic tests are further based on a decreasing probability of each of the plurality of additional diagnostic tests identifying a cause of the symptom with a lowest cost based on the probabilistic medical condition analysis.

14. A diagnostic tool for optimizing a diagnostic test sequence to diagnose a medical condition of a subject, comprising:

a diagnostic test selector configured to determine a group of diagnostic tests related to a symptom of the subject from a pool of diagnostic tests;

a medical condition analyzer configured to determine an efficacy of each of the diagnostic tests of the group of diagnostic tests based on historical outcomes of actual diagnostic testing via a probabilistic medical condition analysis;

an analyzer configured to analyze a comparative utility of each diagnostic tests of the group of diagnostic tests based on a plurality of factors that can affect a problem resolution;

a weighter configured to assign a weight to each factor involved in the probabilistic medical condition analysis;

an orderer configured to order the group of diagnostic tests based upon at least one of the following;

a probability of the diagnostic test identifying a cause of the medical condition in a minimum amount of time;

a probability of the diagnostic test identifying the cause of the medical condition at a minimum cost; and

a relative weighting of minimizing time versus minimizing cost; and

a sequence optimizer configured to select a first diagnostic test from the group of diagnostic tests based at least in part on a probabilistic medical condition analysis and the weighted factors involved therein.

15. The diagnostic tool according to claim 14, wherein the medical condition analyzer is configured to quantify a comparative utility of an individual diagnostic test of the group of diagnostic tests.

16. The diagnostic tool according to claim 15, wherein the medical condition analyzer is further configured to base the comparative utility on one factor selected from the following:

an estimated time required to perform the first diagnostic test, a difficulty of performing the first diagnostic test, an estimated cost to perform the first diagnostic test, and availability of health insurance to pay for the first diagnostic test.

17. The diagnostic tool according to claim 14, wherein the medical condition analyzer is further configured to base a comparative utility on one factor selected from the following:

an availability of a medical device to perform the first diagnostic test, an estimated cost of performing the first diagnostic test, an estimated cost per time unit of labor, an empirical data regarding a probability that the medical condition exists given the existence of the symptom, an estimate of the probability that the medical condition exists given the existence of the symptom, a frequency of the medical condition, a medical history of the subject, other pre-existing conditions of the subject, and family medical history of the subject.

18. The diagnostic tool according to claim 15, wherein the weighter is configured to assign the weight to each of the factors selected from the following:

an estimated time required to perform the first diagnostic test, a difficulty of performing the first diagnostic test, an estimated cost to perform the first diagnostic test, an empirical data regarding a probability that the medical condition exists given the existence of the symptom, an estimate of the probability that the medical condition exists given the existence of the symptom, a frequency of the medical condition, an age of the subject, a general health of the subject.

19. The diagnostic tool according to claim 14, wherein the weighter is further configured to base the weight on a user preference setting.

20. The diagnostic tool according to claim 14, further comprising a medical history receiver configured to receive a medical history of the subject, and wherein the medical condition analyzer is further configured to base a comparative utility at least in part on the medical history.

21. The diagnostic tool according to claim 14, wherein the sequence optimizer is further configured to order a plurality of additional diagnostic tests from the group of diagnostic tests based at least in part on the probabilistic medical condition analysis.

22. A diagnostic tool for optimizing a diagnostic test sequence to diagnose a medical condition of a subject, comprising:

a diagnostic test selector configured to determine a group of diagnostic tests related to a symptom of the subject from a pool of diagnostic tests;

a sequence optimizer configured to select a first diagnostic test from the group based at least in part on a probabilistic medical condition analysis, the probabilistic medical condition analysis being based on historical outcomes of actual diagnostic testing;

a medical condition analyzer configured to quantify a comparative utility of an individual diagnostic test of the group of diagnostic tests based on a plurality of factors that can affect a problem resolution;

a factor weighter configured to assign a weight to each of a plurality of probabilistic medical condition analysis factors; and

a medical history receiver configured to receive a medical history of the subject, wherein the medical condition analyzer is further configured to base the comparative utility at least in part on the medical history.

23. A computer-implemented method of optimizing a diagnostic test sequence to diagnose a medical condition of a subject, comprising:

determining a group of diagnostic tests related to a symptom of the subject from a pool of diagnostic tests; and

optimizing an order of the group of diagnostic tests, the optimization comprising;

conducting a probabilistic medical condition analysis to determine an efficacy of each of the diagnostic tests of the group based on historical outcomes of actual diagnostic testing;

analyzing a comparative utility of each diagnostic tests of the group of diagnostic tests based on a plurality of factors that can affect a problem resolution;

assigning a weight to each factor involved in the probabilistic medical condition analysis;

selecting a first diagnostic test from the group of diagnostic tests; and

iteratively optimizing the order of the group of diagnostic tests in response to prompting by an intermediate diagnostic test information being received.

24. The method according to claim 23, wherein the probabilistic medical condition analysis is based on one factor selected from the following:

an estimated time required to perform the first diagnostic test, a difficulty of performing the first diagnostic test, an estimated cost to perform the first diagnostic test, and availability of health insurance to pay for the first diagnostic test.

25. The method according to claim 23, wherein the probabilistic medical condition analysis is based on one factor selected from the following:

an availability of a medical device to perform the first diagnostic test, an estimated cost of performing the first diagnostic test, an estimated cost per time unit of labor, an empirical data regarding a probability that the medical condition exists given the existence of the symptom, an estimate of the probability that the medical condition exists given the existence of the symptom, a frequency of the medical condition of the subject, a medical history of the subject, other pre-existing conditions of the subject, and family medical history of the subject.

26. The method according to claim 23, wherein the factor is selected from one of the following:

an estimated time required to perform the first diagnostic test, a difficulty of performing the first diagnostic test, a frequency of the medical condition, an age of the subject, and a general health of the subject.

27. The method according to claim 23, wherein the weight is based on a user preference setting.

28. The method according to claim 23 further comprising receiving a medical history of the subject, wherein the step of selecting the first diagnostic test is further based at least in part on the medical history.

29. The method according to claim 23, wherein the first diagnostic test has a highest probability of identifying a cause of the symptom in a least amount of time among the group based at least in part on the probabilistic medical condition analysis.

30. The method according to claim 23, wherein the first diagnostic test has a highest probability of identifying a cause of the symptom with a lowest cost among the group based at least in part on the probabilistic medical condition analysis.