System and methods for referring physicians based on hierarchical disease profile matching

• US 8,489,418 B2
• Filed: 12/30/2010
• Issued: 07/16/2013
• Est. Priority Date: 12/30/2010
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Gustafson, Steven Matt, Cardoso, Matthew
• Primary Examiner(s): Fuelling, Michael
• Application Number:
  US12/982,365
• Publication Number:
  US 20120173280A1
• Time in Patent Office: 929 Days
• Field of Search: 705 2- 3
• US Class Current: 705/2
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 70/60 relating to pathologies

Abstract

Systems, apparatus, and methods for referring physicians based on hierarchical disease profile matching are disclosed. An example system includes a data store to include a plurality of disease profiles, each disease profile associated with a patient condition, a user interface to accept a user request for a referral of a patient to a physician, and a referral processor to compare a profile associated with the patient including a patient symptom to the plurality of disease profiles to generate one or more physician recommendations for referral, the referral processor to refine the one or more physician recommendations based on one or more characteristics associated with each of the one or more physician recommendations, the referral processor to provide the refined one or more physician recommendations to a user for review and selection via the user interface.

Claims

1. A computer-implemented method of generating physician referral recommendations for a patient, the method comprising:

categorizing, physicians in an organization by department and specialty to form one or more groups of one or more categorized physicians; and

classifying and assembling disease profiles for a plurality of diseases; and

determining a disease profile for a patient based on a patient condition profile associated with the patient; and

identifying, using a processor, a group of one or more categorized physicians matching the disease profile of the patient; and

refining, using the processor, the group of one or more categorized physicians associated with the patient disease profile based on one or more features associated with each physician in the group, the one or more features associated with each physician comprising physician performance data including one or more of the physician'"'"'s patient treatment history, patient feedback, clinical outcome data, and expected cost of delivery including financial and schedule analysis associated with the physician; and

generating, using the processor, a recommendation of one or more physicians based on the refined group of one or more categorized physicians; and

providing the recommendation of one or more physicians to a user for review and selection.

2. The method of claim 1, wherein generating the recommendation of one or more physicians comprises scoring each physician based on an association with the patient condition profile and the physician'"'"'s features.

3. The method of claim 1, wherein generating the recommendation of one or more physicians takes into account a cost of delivery.

4. The method of claim 1, further comprising creating disease profiles for one or more types of diseases.