METHOD AND SYSTEM FOR SUPPORTING A CLINICAL DIAGNOSIS

• US 20140012790A1
• Filed: 07/03/2012
• Published: 01/09/2014
• Est. Priority Date: 07/03/2012
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens AG
• Inventors: Oberkampf, Heiner, Zillner, Sonja
• Granted Patent: US 9,002,769 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method and system for supporting a clinical diagnosis is provided, the method including the steps of representing a patient by a plurality of initial symptoms, the symptoms including characteristics of the patient; determining, by querying and reasoning in a disease-symptom knowledge model, at least one likely disease for each of the plurality of initial symptoms; mapping the plurality of initial symptoms onto a set of said likely diseases; determining for each disease of said set of likely diseases a plurality of associated symptoms, the associated symptoms being associated to a respective disease of said set of likely diseases in said disease-symptom knowledge model; categorizing each of the plurality of associated symptoms into disjoint categories by mapping associated symptoms with initial symptoms; and representing likely diseases in the context of said categories of associated symptoms.

Claims

1. A method for supporting a clinical diagnosis, comprising:

a) representing a patient by a plurality of initial symptoms, the symptoms including characteristics of the patient;

b) determining, by querying and reasoning in a disease-symptom knowledge model, at least one likely disease for each of the plurality of initial symptoms;

c) mapping the plurality of initial symptoms onto a set of said likely diseases;

d) determining for each disease of said set of likely diseases a plurality of associated symptoms, the associated symptoms being associated to a respective disease of said set of likely diseases in said disease-symptom knowledge model;

e) categorizing each of the plurality of associated symptoms into disjoint categories by mapping associated symptoms with initial symptoms; and

f) representing likely diseases in the context of said categories of associated symptoms.

2. The method of claim 1, wherein in step e) symptoms are categorized in one of the following categories:

existing symptoms in case that a particular associated symptom is equally mapped by an initial symptom;

absent symptoms in case that a particular associated symptom is explicitly excluded in the mapping of said plurality of initial symptoms; and

open symptoms in case that a particular associated symptom is missing in the mapping of said plurality of initial symptoms.

3. The method of claim 2, including the step of:

g) enabling a user to change said categories of each of the plurality of associated symptoms.

4. The method of claim 3, including the step of:

h) enabling a user to request information entities stored in a record of the patient, the information entities being semantically related to at least one open symptom of said set of likely diseases.

5. The method of claim 4, including the step of:

i) inferring recommended examination steps by evaluating existing, absent and/or open symptoms in view of said disease-symptom knowledge model.

6. The method of claim 1, wherein said initial symptoms include at least one of findings, observations, symptoms, and negated symptoms.

7. The method of claim 1, including the step of:

treating the associated symptoms in step e) as initial symptoms and recurring the steps b) until f).

8. A system for supporting a clinical diagnosis, the system comprising:

a semantic patient data repository including semantically annotated initial symptoms representing a patient, the symptoms including characteristics of the patient;

an ontology repository including a knowledge model establishing a relationship between a plurality of diseases and a plurality of associated symptoms;

a query and reasoning component for mapping the plurality of initial symptoms onto a set of likely diseases and for mapping the plurality of initial symptoms onto a set of said likely diseases;

a ranking module for categorizing each of the plurality of associated symptoms into disjoint categories by mapping associated symptoms with initial symptoms; and

a user interaction module for representing likely diseases in the context of said categories of associated symptoms.

10. The system of claim 8, wherein the ranking module is configured to categorize the symptoms in one of the following categories:

existing symptoms in case that a particular associated symptom is equally mapped by an initial symptom;

absent symptoms in case that a particular associated symptom is explicitly excluded in the mapping of said plurality of initial symptoms; and

open symptoms in case that a particular associated symptom is missing in the mapping of said plurality of initial symptoms.

12. The system of claim 10, wherein the user interaction module is configured to enable a user to request information entities stored in a record of the patient, the information entities being semantically related to at least one open symptom of said set of likely diseases.

13. The system of claim 8, wherein said initial symptoms include at least one of findings, observations, symptoms, and negated symptoms.

9. A computer program product, which comprises a program code stored on a non-transitory computer-readable medium and which, when executed by a processor, is configured to:

a) represent a patient by a plurality of initial symptoms, the symptoms including characteristics of the patient;

b) determine, by querying and reasoning in a disease-symptom knowledge model, at least one likely disease for each of the plurality of initial symptoms;

c) map the plurality of initial symptoms onto a set of said likely diseases;

d) determine for each disease of said set of likely diseases a plurality of associated symptoms, the associated symptoms being associated to a respective disease of said set of likely diseases in said disease-symptom knowledge model;

e) categorize each of the plurality of associated symptoms into disjoint categories by mapping associated symptoms with initial symptoms; and

f) represent likely diseases in the context of said categories of associated symptoms.

11. The system of claim 9, wherein the user interaction module is configured to enable a user to change said categories of each of the plurality of associated symptoms.