Systems and methods for diagnosing medical conditions

• US 6,754,655 B1
• Filed: 11/12/1998
• Issued: 06/22/2004
• Est. Priority Date: 06/30/1998
• Status: Expired due to Term

• Current Assignee: SimulConsult, Inc.
• Original Assignee: SimulConsult, Inc.
• Inventors: Segal, Michael M.
• Primary Examiner(s): Alam, Shahid
• Assistant Examiner(s): FLEURANTIN, JEAN B
• Application Number:
  US09/190,812
• Time in Patent Office: 2,049 Days
• Field of Search: 707/1-5, 707/6-7, 707/9-10, 707/100-104, 705/2-3, 600/300, 706/924, 128/920-925, 128/898.01, 128/899, 128/898
• US Class Current: 1/1
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/55 Rule-based translation
• 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
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

The systems and methods described herein aid a clinician in the diagnostic process by providing the clinician with information about the available clinical procedures that most improve the clinician'"'"'s ability to reach a correct diagnosis. Specifically, the systems described herein include software tools that can process information about the patient, including age, sex, symptoms, and prior medical history, and information about the known findings associated with different possible medical conditions, and based on this information, rank the other findings that can be ascertained by the clinician to point out to those findings that are most likely to disambiguate between the multiple candidate disease and lead to the correct diagnosis.

Claims

1. A process for diagnosing a medical condition of a patient, comprising the acts of

identifying a plurality of candidate medical conditions,

identifying a plurality of findings to provide a list of findings, each of which is representative of clinical information that can be gathered about the patient'"'"'s condition,

determining for each finding, a likelihood that a particular finding can disambiguate between said candidate medical conditions, and

ranking said findings as a function of the likelihood that a finding can disambiguate between said plurality of medical conditions, whereby a clinician can employ said ranked findings to identify a finding that is likely to lead to a correct diagnosis of the patient'"'"'s medical condition.

2. A process according to claim 1, further comprising the act of

weighting the likelihood that a finding can disambiguate between a plurality of medical conditions by a factor representative of an economic cost of obtaining the clinical information representative of the finding.

3. A process according to claim 1, further comprising the act of

weighting the likelihood that a finding can disambiguate between a plurality of medical conditions by a factor representative of a possibility that a disease can be treated effectively.

4. A process according to claim 1, further comprising the act of

identifying a plurality of findings that can be determined from a single clinical procedure, and

determining a composite score representative of the likelihood that said plurality of findings can disambiguate between said plural medical conditions.

5. A process according to claim 1, comprising the further act of

selecting a plurality of findings that can be identified from a known battery of laboratory tests, and

determining a composite score representative of the likelihood that said plurality of findings can disambiguate between said plural medical conditions.

6. A process according to claim 1, comprising the further act of

allowing a clinician to enter finding data representative of the presence or absence of a finding presented in said list of findings, including the onset age of a finding in a patient, and

reordering remaining findings from said list of findings, as a function of the presence or absence of finding data, according to the likelihood that a finding can disambiguate between said plurality of medical conditions.

7. A process according to claim 1, comprising the further acts of

determining, as a function of the presence or absence of a finding, the onset age of a finding, and the probability of diseases, a usefulness signal representative of the change in likelihood that a patient has a particular disease.

8. A process according to claim 1, wherein determining for each finding a likelihood that a particular finding can disambiguate between said candidate medical conditions, comprises the act of

determining for each finding a usefulness signal representative of a summation of the changes in probability estimates for said candidate medical conditions occurring in response to an indication of the presence or absence of the respective finding in the patient.

9. A process according to claim 1, comprising the further acts of

allowing a clinician to select one of said plural medical conditions, and

determining for the selected medical condition the likelihood that a finding can identify the selected medical condition as the condition afflicting the patient, whereby the clinician can rule in or rule out the selected medical condition.

10. A process according to claim 1, comprising the further act of

displaying for a patient a listing of findings determined to be present for a patient and a list of findings determined to be absent for a patient, and

displaying, for a selected medical condition, a set of probabilities each associated with a respective one of findings and each being representative of the likelihood that the respective finding is present in a patient having the selected medical condition, whereby the clinician is provided information for justifying a diagnosis.

11. A process according to claim 1, comprising the further act of

displaying for a patient a listing of candidate medical conditions, and

displaying for each candidate medical condition a likelihood that the respective medical condition is the correct diagnosis, whereby a clinician can monitor the change in likelihood of candidate medical conditions in response to the entry of finding data.

12. A process according to claim 11, comprising the further act of

displaying for each candidate medical condition a likelihood that the respective medical condition is the correct diagnosis as a function of onset age of findings.

13. A process according to claim 1, comprising the further act of

generating a data record representative of the likelihood a particular finding will disambiguate between plural medical conditions, and

transmitting said data record to an authorization center for requesting authorization for performing a clinical procedure capable of determining the presence or absence of the particular finding in the patient.

14. A process according to claim 1, comprising the further act of

determining the likelihood of a finding being capable of disambiguating between a plurality of medical diseases as a function of the age of the patient and the age of onset of the finding.

15. A process for displaying clinical diagnostic information, comprising the acts of

employing a list of candidate medical conditions, each of which being associated with a ranking representative of the likelihood that the candidate medical disease is a correct diagnosis for a patient, and

providing a graphical control element for allowing a clinician to flip between displays associated with said candidate medical conditions and presenting screens of finding information.

16. A process according to claim 15, wherein the graphical control element allows flipping between adjacent candidate medical diseases in the list.

17. A process according to claim 15, wherein the graphical control element allows flipping to the first candidate medical disease in the list.

18. A process for displaying clinical diagnostic information, comprising the acts of

employing a list of findings, each being associated with a ranking representative of the likelihood that the finding can disambiguate between a plurality of candidate medical diseases, and

providing a graphical control element for allowing a clinician to flip between displays associated with said findings and presenting screens of disease information.

19. A process according to claim 18, wherein the graphical control element allows flipping between displays associated with adjacent findings in the list.

20. A process according to claim 18, wherein the graphical control element allows flipping to a display associated with the first finding in the list.

21. A method of displaying clinical diagnostic information, comprising the acts of

providing a plurality of findings and a set of probability values, each associated with a respective one of said plurality of findings and each being representative of the likelihood that the presence or absence of the finding can disambiguate between a plurality of medical conditions, and

displaying on a computer display said plurality of findings, wherein said plurality of findings are arranged on the computer display to indicate the likelihood that one of the findings can disambiguate between a plurality of candidate medical conditions.

22. A computer readable medium having stored thereon instructions for directing a computer to

provide a plurality of candidate medical conditions,

provide a plurality of findings, each of which is representative of clinical information that can be gathered about the patient'"'"'s condition,

determine for each finding, a likelihood that a particular finding can disambiguate between said candidate medical conditions, and

rank said findings as a function of the likelihood that a finding can disambiguate between said plurality of medical conditions, whereby a treating clinician can be provided with useful information regarding the likelihood that a finding can lead to the identification of the target medical condition.

23. A system for providing a clinician with a database of ranked findings for diagnosing a disease, comprising:

a computer network having a server that will receive information on findings and store for each finding a record having information representative of the likelihood that the finding with an onset age is present in a patient having a particular disease,

a computer program operating on said server to generate a data file representative of a plurality of such records, and

a transfer program capable of transferring said data file to a client station, whereby a clinician at the client station is provided with a database of information ranked in an order representative of the likelihood that a finding is useful in diagnosing the disease.

24. A method for selecting a clinical procedure for diagnosing a disease, comprising the acts of

identifying a plurality of candidate diseases, each having an associated likelihood that the candidate disease is a correct diagnosis for a patient'"'"'s medical condition,

identifying a plurality of candidate findings, each being representative of information that can be gathered about a patient'"'"'s medical condition,

selecting one of said candidate findings, and

determining for each of said candidate diseases a change in likelihood that the candidate disease is the correct diagnosis as a function of whether the selected candidate finding is present or absent.

25. A method according to claim 24, comprising the further acts of

selecting each of said candidate findings and determining for each of said candidate diseases the change in likelihood that the candidate disease is the correct diagnosis as a function of whether the selected candidate finding is present or absent, and

generating for each finding a value representative of a summation over all said candidate diseases of the changes in likelihood of the candidate disease being the correct diagnosis.

26. A method according to claim 24, comprising the further act of

determining the change in likelihood that a candidate disease is a correct diagnosis as a function of the age of the patient or the age of onset of the finding.

27. A method according to claim 24, comprising the further act of

determining the change in likelihood that a candidate disease is a correct diagnosis as a function of a cost of performing a clinical procedure for determining the presence or absence of the finding.

28. A method according to claim 24, comprising the further act of

determining the change in likelihood that a candidate disease is a correct diagnosis as a function of a probability representative of the likelihood that the candidate disease can be treated effectively.

29. A process for diagnosing a medical condition of a patient, comprising the acts of

providing a list of candidate medical conditions each being associated with a probability estimate representative of the likelihood that the candidate medical condition is a correct diagnosis,

providing finding information for the patient, including information representative of findings identified in the patient and including onset information representative of a time of onset associated with the finding, and

generating as a function of the onset information and the probability estimates, a compound graphical component for each of the candidate medical conditions capable of displaying probability data representative of a selected finding being present in the candidate disease during a specified onset period, whereby finding information can be entered to generate a set of graphical components that include a component that predicts new probability estimates that can result in response to specifying a selected finding.

30. A system for creating medical records for a patient, comprising

means for identifying a set of findings for diagnosing a medical condition and for displaying the set findings in an order representative of the likelihood that a finding can disambiguate between a plurality of medical conditions,

means for allowing a clinician to enter information representative of those findings identified in the patient, and

means for generating a data record representative of information gathered during a diagnostic process, said information including standard code signals for diseases and findings.

31. A method for justifying a clinical procedure, comprising

(a) providing a list of candidate findings, each being representative of information that can be gathered about a patient'"'"'s medical condition during a clinical procedure,

(b) providing a list of candidate diseases, each having an associated likelihood that the candidate disease is a correct diagnosis for a patient'"'"'s medical condition,

(c) selecting one of said candidate findings,

(d) determining for each of said candidate diseases a change in likelihood that the candidate disease is the correct diagnosis as a function of whether the selected candidate finding is present or absent, and summing the determined changes in likelihood to generate a measure of the usefulness of the selected candidate finding,

(e) repeating steps (c) and (d) to determine a measure of usefulness for at least a portion of the candidate findings in the list of candidate findings, and

(f) for at least a portion of the candidate findings, comparing the measure of usefulness for a candidate finding to a measure of burden, to determine if a clinical procedure for collecting information regarding the candidate medical condition is justified.