SYSTEM AND METHOD FOR PROVIDING EVIDENCE-BASED EVALUATION

• US 20160012341A1
• Filed: 07/09/2014
• Published: 01/14/2016
• Est. Priority Date: 07/09/2014
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: RAMAN, Madhusudan
• Granted Patent: US 9,721,068 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• 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

Abstract

An approach is provided for determining associations and/or propensity among the word occurrences during a therapy interaction for supporting a procedure. The approach involves parsing captured therapy interaction data to identify one or more word occurrences. The approach also involves determining one or more associations among the one or more word occurrences using a fuzzy association analysis and deep belief networks. The approach further involves determining a propensity of the one or more associations based on a probability analysis. The approach also involves specifying the one or more associations as evidence data for supporting a therapeutic outcome, a mental state classification, or a combination thereof.

Claims

1. A method comprising:

parsing captured therapy interaction data to identify one or more word occurrences;

determining one or more associations among the one or more word occurrences using a fuzzy association analysis and deep belief networks;

determining a propensity of the one or more associations based on a probability analysis; and

specifying the one or more associations as evidence data for supporting a therapeutic outcome, a mental state classification, or a combination thereof.

2. A method of claim 1, further comprising:

determining the propensity of the one or more associations based on a probability that the one or more word occurrences imply a determined meaning.

3. A method of claim 1, further comprising:

determining a time-based setting for the one or more associations,

wherein the specifying of the one or more associations as the evidence data is further based on the time-based setting; and

wherein the time-based setting includes a survival time.

4. A method of claim 1, further comprising:

de-identifying the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof prior to a publication, an aggregation, or a combination thereof of the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof.

5. A method of claim 1, wherein the captured therapy interaction data is parsed using a natural language model.

6. A method of claim 5, wherein the natural language model supports a Dialectical Behavior Therapy (DBT) methodology, a Cognitive Behavioral Therapy (CBT) methodology, or a combination thereof.

7. A method of claim 1, further comprising:

changing a model for determining the one or more associations, determining the propensity of the one or more associations, or a combination thereof over time.

8. A method of claim 7, wherein the changing of the model is further based on a contextual parameter associated with a subject of the captured therapy interaction data.

9. An apparatus comprising a processor configured to:

parse captured therapy interaction data to identify one or more word occurrences;

determine one or more associations among the one or more word occurrences using a fuzzy association analysis and deep belief networks;

determine a propensity of the one or more associations based on a probability analysis; and

specify the one or more associations as evidence data for supporting a therapeutic outcome, a mental state classification, or a combination thereof.

10. An apparatus of claim 9, further comprising:

determine the propensity of the one or more associations based on a probability that the one or more word occurrences imply a determined meaning.

11. An apparatus of claim 9, further comprising:

determine a time-based setting for the one or more associations,

wherein the specifying of the one or more associations as the evidence data is further based on the time-based setting; and

wherein the time-based setting includes a survival time.

12. An apparatus of claim 9, further comprising:

de-identify the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof prior to a publication, an aggregation, or a combination thereof of the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof.

13. An apparatus of claim 9, wherein the captured therapy interaction data is parsed using a natural language model.

14. An apparatus of claim 13, wherein the natural language model supports a Dialectical Behavior Therapy (DBT) methodology, a Cognitive Behavioral Therapy (CBT) methodology, or a combination thereof.

15. An apparatus of claim 9, further comprising:

change a model for determining the one or more associations, determining the propensity of the one or more associations, or a combination thereof over time.

16. An apparatus of claim 15, wherein the changing of the model is further based on a contextual parameter associated with a subject of the captured therapy interaction data.

17. A system comprising a platform configured to:

parse captured therapy interaction data to identify one or more word occurrences;

determine one or more associations among the one or more word occurrences using a fuzzy association analysis and deep belief networks;

determine a propensity of the one or more associations based on a probability analysis; and

specify the one or more associations as evidence data for supporting a therapeutic outcome, a mental state classification, or a combination thereof.

18. A system of claim 17, wherein the platform is further configured to:

determine the propensity of the one or more associations based on a probability that the one or more word occurrences imply a determined meaning.

19. A system of claim 17, wherein the platform is further configured to:

determine a time-based setting for the one or more associations,

wherein the specifying of the one or more associations as the evidence data is further based on the time-based setting; and

wherein the time-based setting includes a survival time.

20. A system of claim 17, wherein the platform is further configured to:

de-identify the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof prior to a publication, an aggregation, or a combination thereof of the evidence data, the one or more associations, the one or more word occurrences, or a combination thereof.