Method and system for medical suggestion search

• US 10,192,639 B2
• Filed: 02/03/2015
• Issued: 01/29/2019
• Est. Priority Date: 08/22/2014
• Status: Active Grant

• Current Assignee: DrFirst.com, Incorported
• Original Assignee: DrFirst.com, Incorported
• Inventors: Sellars, David Andrew
• Primary Examiner(s): Kanaan, Maroun P
• Application Number:
  US14/613,174
• Publication Number:
  US 20160055302A1
• Time in Patent Office: 1,456 Days
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

The present teaching relates to medical suggestion searching. In one example, data related to a medication drug are obtained. One or more candidate prescription strings are identified from the obtained data. Each of the candidate prescription strings is associated with a plurality of attributes. Each of the one or more candidate prescription strings is automatically processed based on at least one model to generate one or more prescription strings each with an associated ranking. At least some of the generated one or more prescription strings and the associated rankings are stored for future use.

Claims

1. A method, implemented on at least one computing device having at least one processor, storage, and a communication platform connected to a network for providing medical suggestion, the method comprising:

receiving one or more dimensions, each of the one or more dimensions relating to an attribute of a patient or an attribute of a physician;

identifying, for each of the one or more dimensions, at least one medical suggestion from a data map associating medical suggestions with dimensions, wherein each dimension-medical suggestion pair in the data map has an associated confidence score indicative of a degree of match between the medical suggestion and the dimension, the degree of match being based on statistical analysis of medical transaction data identified as relevant to the dimension-medical suggestion pair;

calculating, for each medical suggestion, an aggregated confidence score based on an aggregation of the associated confidence scores for the medical suggestion with respect to each of the one or more dimensions;

providing, for selection, at least some of the medical suggestions based on the aggregated confidence score of each medical suggestion;

receiving a selection of a first medical suggestion of the at least some of the medical suggestions provided; and

boosting confidence scores for the dimension-medical suggestion pairs associated with the one or more dimensions and the first medical suggestion responsive to the selection, the boosted confidence score of a dimension-medical suggestion pair being used in calculating the aggregated confidence score for the medical suggestion responsive to a subsequent receipt of the dimension.

2. The method of claim 1, wherein medical suggestion includes at least one of:

a medication drug;

a physical therapy;

a diet;

a lab test;

or

a radiology test.

3. The method of claim 1, wherein the one or more dimensions include:

doctor specialty;

disease diagnosis;

synonyms;

or

patient profile.

4. The method of claim 1, where the statistical analysis is performed by a statistic model applied to a medical transaction database.

5. The method of claim 4, wherein the statistic model considers at least one of:

number of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database;

frequency of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database;

or

recency of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database.

6. The method of claim 1, wherein the aggregated confidence score for each medical suggestion is calculated by weighted summation of each confidence score of the medical suggestion with respect to each dimension.

7. The method of claim 1, wherein the medical suggestions are ranked based on the aggregated confidence score of each medical suggestion.

8. The method of claim 1, wherein the medical suggestion includes a medication drug and the method further comprises:

identifying at least one prescription string stored previously, each of which matches the medication drugs; and

providing the at least one prescription string as a recommendation.

9. The method of claim 1, further comprising:

obtaining data related to medical transactions;

mapping the obtained data into one or more dimensions;

identifying one or more candidate medical suggestions from the mapped data in each dimension;

in each dimension, automatically processing the mapped data based on at least one model to generate confidence scores for each of the candidate medical suggestions; and

storing, in the data map, at least some of the candidate medical suggestions and the confidence scores thereof in each dimension.

10. A system for providing medical suggestion, comprising:

a dimension information identifying unit configured to receive one or more dimensions, each of the one or more dimensions relating to an attribute of a patient or an attribute of a physician;

a medical suggestion fetching unit configured to identify, for each of the one or more dimensions, at least one medical suggestion from a data map associating medical suggestions with dimensions, wherein each dimension-medical suggestion pair in the data map has an associated confidence score indicative of a degree of match between the medical suggestion and the dimension the degree of match being based on statistical analysis of medical transaction data identified as relevant to the dimension-medical suggestion pair;

a medical suggestion scoring unit configured to automatically calculate, for each medical suggestion, an aggregated confidence score based on an aggregation of the associated confidence scores for the medical suggestion with respect to each of the one or more dimensions; and

a medical suggestion ranking unit configured to provide at least some of the identified medical suggestions based on the aggregated confidence score of each medical suggestion, to receive a selection of a first medical suggestion of the at least some of the medical suggestions provided, and to boost the confidence scores for the dimension-medical suggestion pairs associated with the one or more dimensions and the first medical suggestion, the boosted confidence score of a dimension-medical suggestion pair being used in calculating the aggregated confidence score for the medical suggestion responsive to a subsequent receipt of the dimension.

11. The system of claim 10, wherein medical suggestion includes at least one of:

a medication drug;

a physical therapy;

a diet;

a lab test;

or

a radiology test.

12. The system of claim 10, wherein the one or more dimensions include:

doctor specialty;

disease diagnosis;

synonyms;

or

patient profile.

13. The system of claim 10, where the statistical analysis is performed by a statistic model applied to a medical transaction database.

14. The system of claim 13, wherein the statistic model considers at least one of:

number of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database;

frequency of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database; and

recency of occurrence of the medical suggestion in data related to medical transactions in the medical transaction database.

15. The system of claim 10, wherein the aggregated confidence score for each medical suggestion is calculated by weighted summation of each confidence score of the medical suggestion with respect to each dimension.

16. The system of claim 10, wherein the identified medical suggestions are ranked based on the aggregated confidence score of each medical suggestion.

17. The system of claim 10, wherein the at least one medical suggestion is a medication drug and the system further comprises a prescription string recommending module configured to:

identify at least one prescription string stored previously, each of which matches the medication drug; and

provide the at least one prescription string as recommendation.

18. The system of claim 10, further comprising an analytic engine configured to:

obtain data related to medical transactions;

map the obtained data into one or more dimensions;

identify one or more candidate medical suggestions from the mapped data in each dimension;

in each dimension, automatically process the mapped data based on at least one model to generate confidence scores for each of the candidate medical suggestions; and

store at least some of the candidate medical suggestions and the confidence scores thereof in each dimension.

19. A non-transitory machine readable medium having information recorded thereon for providing medical suggestion, wherein the information, when read by a machine, causes the machine to perform the steps of:

receiving one or more dimensions, each of the one or more dimensions relating to an attribute of a patient or an attribute of a physician;

identifying, for each of the one or more dimensions, at least one medical suggestion from a data map associating medical suggestions with dimensions, wherein each dimension-medical suggestion pair in the data map has an associated confidence score indicative of a degree of match between the medical suggestion and the dimension, the degree of match being based on statistical analysis of medical transaction data identified as relevant to the dimension-medical suggestion pair;

calculating, for each of the at least one medical suggestion, an aggregated confidence score based on an aggregation of the associated confidence scores for the medical suggestion with respect to each of the one or more dimensions; and

providing at least some of the identified medical suggestions based on the aggregated confidence score of each medical suggestion;

receiving a selection of a first medical suggestion of the at least some of the medical suggestions provided; and

boosting confidence scores for the dimension-medical suggestion pairs associated with the one or more dimensions and the first medical suggestion responsive to the selection, the boosted confidence score of a dimension-medical suggestion pair being used in calculating the aggregated confidence score for the medical suggestion responsive to a subsequent receipt of the dimension.

20. A method, implemented on at least one computing device having at least one processor, storage, and a communication platform connected to a network for generating medical suggestion, the method comprising:

obtaining data related to medical transactions;

mapping the obtained data into one or more dimensions, each of the one or more dimensions relating to an attribute of a patient or an attribute of a physician;

identifying one or more medical suggestions from the mapped data;

pairing each of the one or more dimensions with each of the one or more medical suggestions;

for each dimension-medical suggestion pair, generating a confidence score representing a degree of match based on statistical analysis of the medical suggestion in medical transaction data;

storing at least some of the dimension-medical suggestion pairs with respective confidence scores in a data map;

providing a first medical suggestion from the data map in response to a query that specifies one or more dimensions based on the respective confidence scores;

receiving a selection of the first medical suggestion of the at least some of the medical suggestions provided; and

boosting confidence scores for the dimension-medical suggestion pairs associated with the one or more dimensions and the first medical suggestion responsive to the selection, the boosted confidence score of a dimension-medical suggestion pair being used in calculating the aggregated confidence score for the medical suggestion responsive to a subsequent receipt of the dimension.