Method and system for supporting a clinical diagnosis

• US 8,965,818 B2
• Filed: 05/16/2012
• Issued: 02/24/2015
• Est. Priority Date: 05/16/2012
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens AG
• Inventors: Zillner, Sonja, Oberkampf, Heiner
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): PELLETT, DANIEL T
• Application Number:
  US13/473,134
• Publication Number:
  US 20130310653A1
• Time in Patent Office: 1,014 Days
• Field of Search: None
• US Class Current: 706/14
• CPC Class Codes: G06N 5/00 Computing arrangements using knowledge-based models
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Methods and systems may support conclusions of a clinician by enabling the clinician to arbitrarily define the symptoms according to the patient'"'"'s record. The method may comprise: (a) determining a plurality of symptoms representing a patient and including characteristics of the patient, the symptoms being categorized as present symptoms, absent symptoms or open symptoms; (b) establishing a multi-tier relationship between said symptoms and a plurality of diseases based on a knowledge model; (c) adjusting weighting factor(s) for at least one multi-tier relationship based on said knowledge model; (d) optionally adjusting at least one weighting factor of step (c) by an expert; and (e) building a ranking of diseases from said multi-tier relationship based on said weighting factors. The method may provide an efficient ranking of disease information, thereby supporting a clinical diagnosis that may consider multiple symptoms while emphasizing particular symptoms in view of the clinician'"'"'s expertise.

Claims

1. An automated method for supporting a clinical diagnosis for a patient, comprising:

receiving, by a processor, patient-specific information regarding a plurality of symptoms associated with one or more of a plurality of diseases, wherein the patient-specific information regarding the plurality of symptoms categorizes each of a first subset of the plurality of symptoms as a present symptom determined as being present in the patient, and categorizes each of a second subset of the plurality of symptoms as an absent symptom determined as being absent in the patient;

storing in memory the patient-specific information regarding the plurality of symptoms associated with the patient;

the processor establishing or accessing a multi-tier relationship between said plurality of symptoms and the plurality of diseases defining, for each disease, one or more of the plurality of symptoms that match that disease;

the processor adjusting at least one weighting factor for at least one (a) at least one of said multi-tier relationships and (b) at least one of said symptoms, based on a knowledge model; and

the processor building a ranking of diseases from said multi-tier relationship based on said weighting factors and said patient-specific information regarding the plurality of symptoms;

wherein for each respective disease, the number of symptoms categorized as present symptoms for the patient that match the respective disease, as defined by the multi-tier relationship, increases the ranking of the respective disease; and

wherein the number of symptoms categorized as absent symptoms for the patient that match the respective disease, as defined by the multi-tier relationship, decreases the ranking of the respective disease.

2. The method of claim 1, wherein said multi-tier relationship between said plurality of symptoms and said plurality of diseases is implemented by a bipartite graph, the bipartite graph including a plurality of nodes with each node assigned to a symptom or disease, the bipartite graph including a plurality of edges expressing a particular relationship between a particular symptom and a particular disease.

3. The method of claim 1, wherein said weighting factors include at least one of a consideration of a patient-specific incidence of a disease, a strength of a disease-symptom relation, and an importance of a symptom.

4. The method of claim 1, wherein the received patient-specific information regarding the plurality of symptoms categorizes each of a third subset of the plurality of symptoms as an open system not determined as being present or absent in the patient.

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

a patient record configured to receive and store patient-specific information regarding a plurality of symptoms associated with a patient, wherein the patient-specific information regarding the plurality of symptoms categorizes each of a first subset of the plurality of symptoms as a present symptom determined as being present in the patient, and categorizes each of a second subset of the plurality of symptoms as an absent symptom determined as being absent in the patient;

a weighted disease-symptom module including a knowledge model defining a multi-tier relationship between said plurality of symptoms and a plurality of diseases, the multi-tier relationship defining, for each disease, one or more of the plurality of symptoms that match that disease;

the weighted disease-symptom module configured to adjust at least one weighting factor for at least one (a) at least one of said multi-tier relationships and (b) at least one of said symptoms, based on a medical ontology module;

the weighted disease-symptom module configured to generate a ranking of diseases from said multi-tier relationship weighted by said weighting factors and said patient-specific information regarding the plurality of symptoms;

wherein for each respective disease, the number of symptoms categorized as present symptoms for the patient that match the respective disease, as defined by the multi-tier relationship, increases the ranking of the respective disease; and

wherein the number of symptoms categorized as absent symptoms for the patient that match the respective disease, as defined by the multi-tier relationship, decreases the ranking of the respective disease; and

wherein the weighted disease-symptom module is embodied by software stored in a non-transitory computer-readable medium and executable by a processor.

6. The system of claim 5, wherein the patient-specific information received and stored in the patient record module categorizes each of a third subset of the plurality of symptoms as an open system not determined as being present or absent in the patient.