Evidence based medical record

1. A method of providing a confidence-estimation-based inference, the method comprising:

receiving a query concerning a patient from a user;

accessing an electronic health record (EHR) for the patient, the EHR including a first component regarding the patient;

querying the user, using a conversational interface, for a second component regarding the patient;

receiving the second component regarding the patient in response to the query;

calculating a first probability density function using the first component, and a second probability density function using the second component;

combining the first and second probability density functions using a Gaussian mixture model;

calculating at least one conditional probability table using the Gaussian mixture model; and

providing the confidence-estimation-based inference based on the at least one conditional probability table.

2. The method of claim 1 , wherein the inference is one of a medical diagnosis or a medical prognosis.

3. The method of claim 1 , wherein the at least one computing device is further configured to perform actions including:

storing the received second component in the EHR.

4. The method of claim 1 , wherein the at least one computing device is further configured to perform actions including:

prior to determining the inference, determining whether the calculated at least one conditional probability table includes a probability datum that exceeds a threshold;

querying a user for a third component regarding the patient in response to determining that the at least one conditional probability table does not include the probability datum that exceeds the threshold;

receiving the third component in response to the querying for the third component;

calculating a third probability density function using the third component;

combining the first, second and third probability density functions using a Gaussian mixture model;

calculating at least one second conditional probability table using the Gaussian mixture model; and

providing a second confidence-estimation-based inference based on the at least one second conditional probability table.

5. The method of claim 1 , wherein the second component is in a natural language information form, the method further comprising extracting at least one feature from the natural language information by applying a natural language processing (NLP) algorithm to the natural language information.

6. The method of claim 1 , further comprising:

extracting at least one feature from a multimedia datum from the EHR by a feature extraction module.

7. The method of claim 1 , wherein the user is one of a health care professional, the patient, or a non-human system.

8. The method of claim 1 , wherein the at least one computing device is further configured to perform actions including:

assigning a first weight to a source of the first component;

assigning a second weight to a source of the second component, wherein the

weights sum to one hundred percent; and

mathematically combining the weight for the first source with the first probability density function and mathematically combining the weight for the second source with the second probability density function.

9. A system comprising:

at least one computing device configured to determine a confidence-estimation-based inference by performing actions including:

receiving a query concerning a patient from a user;

accessing an electronic health record (EHR) for the patient, the EHR including a first component regarding the patient;

querying the user, using a conversational interface, for a second component regarding the patient;

receiving the second component regarding the patient in response to the query;

calculating a first probability density function using the first component, and a second probability density function using the second component;

combining the first and second probability density functions using a Gaussian mixture model;

calculating at least one conditional probability table using the Gaussian mixture model; and

providing the confidence-estimation-based inference based on the at least one conditional probability table.

10. The system of claim 9 , wherein the inference is one of a medical diagnosis or a medical prognosis.

11. The system of claim 9 , wherein the at least one computing device is further configured to perform actions including:

storing the received second component in the EHR.

12. The system of claim 9 , wherein the at least one computing device is further configured to perform actions including:

prior to determining the inference, determining whether the calculated at least one conditional probability table includes a probability datum that exceeds a threshold;

querying a user for a third component regarding the patient in response to determining that the at least one conditional probability table does not include the probability datum that exceeds the threshold;

receiving the third component in response to the querying for the third component;

calculating a third probability density function using the third component;

combining the first, second and third probability density functions using a Gaussian mixture model;

calculating at least one second conditional probability table using the Gaussian mixture model; and

providing a second confidence-estimation-based inference based on the at least one second conditional probability table.

13. The system of claim 9 , wherein the second component is in a natural language information form, wherein the at least one computing device is further configured to perform actions including:

extracting at least one feature from the natural language information by applying a natural language processing (NLP) algorithm to the natural language information; and

extracting at least one feature from a multimedia datum from the EHR by a feature extraction module.

14. The system of claim 9 , wherein the user is one of a health care professional, the patient, or a non-human system.

15. The system of claim 9 , wherein the at least one computing device is further configured to perform actions including:

assigning a first weight by a user, to a source of the first component;

assigning a second weight, by a user, to a source of the second component, wherein the weights sum to one hundred percent; and

mathematically combining the weight for the first source with the first probability density function and mathematically combining the weight for the second source with the second probability density function.

16. A computer program product comprising program code stored on a non-transitory computer-readable medium, which when executed by at least one computing device, enables the at least one computing device to implement a method of providing a confidence-estimation-based inference by performing actions including:

receiving a query concerning a patient from a user;

accessing an electronic health record (EHR) for the patient, the EHR including a first component regarding the patient;

querying the user, using a conversational interface, for a second component regarding the patient;

receiving the second component regarding the patient in response to the query;

storing the received second component in the EHR;

calculating a first probability density function using the first component, and a second probability density function using the second component;

combining the first and second probability density functions using a Gaussian mixture model;

calculating at least one conditional probability table using the Gaussian mixture model; and

providing the confidence-estimation-based inference based on the at least one conditional probability table.

17. The computer program product of claim 16 , wherein the inference is one of a medical diagnosis or a medical prognosis.

18. The computer program product of claim 16 , wherein the program code causes the at least one computing device to further perform actions including:

prior to determining the inference, determining whether the calculated at least one conditional probability table includes a probability datum that exceeds a threshold;

querying a user for a third component regarding the patient in response to determining that the at least one conditional probability table does not include the probability datum that exceeds the threshold;

receiving the third component in response to the querying for the third component;

calculating a third probability density function using the third component;

combining the first, second and third probability density functions using a Gaussian mixture model;

calculating at least one second conditional probability table using the Gaussian mixture model; and

providing a second confidence-estimation-based inference based on the at least one second conditional probability table.

19. The computer program product of claim 16 , wherein the second component is in a natural language information form, wherein the program code causes the at least one computing device to further perform actions including:

extracting at least one feature from the natural language information by applying a natural language processing (NLP) algorithm to the natural language information; and

extracting at least one feature from a multimedia datum from the EHR by a feature extraction module.

20. The computer program product of claim 16 , wherein the program code causes the at least one computing device to further perform actions including:

assigning a first weight by a user, to a source of the first component;

assigning a second weight, by a user, to a source of the second component, wherein the weights sum to one hundred percent; and

mathematically combining the weight for the first source with the first probability density function and mathematically combining the weight for the second source with the second probability density function.