Automated clustering for patient disposition

• US 8,589,187 B2
• Filed: 12/28/2010
• Issued: 11/19/2013
• Est. Priority Date: 12/28/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Gillam, Michael T., Cazangi, Renato R., Kontsevoy, Alexey P., Kartoun, Uri, Wu, Hao Fang
• Primary Examiner(s): Fuelling, Michael
• Application Number:
  US12/979,363
• Publication Number:
  US 20120166208A1
• Time in Patent Office: 1,057 Days
• Field of Search: 705 2- 3
• US Class Current: 705/3
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The described concepts relate to automated patient disposition. One example can receive a clinician'"'"'s disposition for a patient. This implementation can perform parameter-based cluster analysis on the patient and a set of patients to identify a sub-set of the patients with which the patient has a high similarity. This example can also cause a graphical user interface to be generated that conveys parameters from the sub-set of the patients and the patient.

Claims

1. A method, comprising:

receiving patient values of one or more parameters, wherein the patient values of the one or more parameters are associated with a patient;

performing parameter-based cluster analysis on the patient and a set of patients, the performing comprising;

identifying a first sub-set of the set of patients having an associated first disposition and a second sub-set of the set of patients having an associated second disposition, wherein the first sub-set has first values for the one or more parameters and the second sub-set has second values, different from the first values, for the one or more parameters, and,

determining that the patient fits in the first sub-set rather than the second sub-set based on similarity of the patient values for at least some of the one or more parameters to the first values for the one or more parameters; and

,

causing a graphical user interface (GUI) to be generated that conveys;

that the patient fits in the first sub-set that is associated with the first disposition,

the one or more parameters utilized in the cluster analysis and other patient parameters that were excluded from the cluster analysis, and

the patient values for the one or more parameters,

wherein the causing further includes generating an option to change some of the one or more parameters utilized in the cluster analysis,

and further wherein at least the performing and the causing are performed by a computing device.

2. The method of claim 1, wherein the performing occurs before the receiving of a clinician'"'"'s disposition for the patient, or wherein one of the parameters used in the performing is the clinician'"'"'s disposition, or wherein the performing is repeated after receiving the clinician'"'"'s disposition.

3. The method of claim 1, wherein the causing further includes causing the first disposition associated with the first sub-set to be presented.

4. The method of claim 1, wherein the GUI further includes an option to further differentiate the first sub-set of the set of patients into multiple sub-clusters.

5. A system, comprising:

a display device;

a clinical relevancy engine configured to;

select a sub-set of available patient parameters that are potentially relevant to treatment of a patient,

cause individual patient parameters included in the sub-set to be presented on a graphical user interface (GUI) on the display device, and

allow a user to interact with the GUI to adjust values of the individual patient parameters included in the sub-set;

a parameter normalization module configured to normalize the values of the patient parameters of the sub-set;

a clustering tool configured to;

identify similarities between the patient and other patients based upon the normalized values,

compare the similarities to a predetermined similarity threshold, and

cause disposition information for individual patients of the other patients that satisfy the predetermined similarity threshold to be presented on a subsequent GUI as an aid for the user in making patient care decisions; and

,

at least one processor configured to execute the clustering tool.

6. The system of claim 5, wherein the clinical relevancy engine is configured to obtain the available patient parameters from an electronic master patient index.

7. The system of claim 5, wherein the individual patient parameters include at least one parameter relating to a treatment facility and wherein the user can compare care between different treatment facilities or within an individual treatment facility via the clustering tool.