Methods and apparatus for presenting alternative hypotheses for medical facts

1. A method comprising:

identifying, using at least one statistical model applied by at least one processor to a portion of text documenting a patient encounter, a plurality of alternative hypotheses for a medical fact to be extracted from at least one word or phrase in the portion of the text documenting the patient encounter, each of the plurality of alternative hypotheses representing a different potential semantic meaning of the at least one word or phrase in the portion of the text;

determining at least two hypotheses of the plurality of alternative hypotheses to be presented to a user, wherein determining the at least two hypotheses of the plurality of alternative hypotheses comprises:

determining which of the plurality of alternative hypotheses satisfies at least one criteria, and

selecting, from the plurality of alternative hypotheses, the at least two hypotheses that each satisfies the at least one criteria as hypotheses to be presented to the user; and

outputting the determined at least two hypotheses for presentation to the user as hypotheses for the medical fact to be extracted from the at least one word or phrase of the portion of the text, wherein one of the determined at least two hypotheses accurately represents an intended semantic meaning of the at least one word or phrase in the portion of the text.

2. The method of claim 1 , further comprising:

in response to a selection by the user of the one of the determined at least two hypotheses that accurately represents the intended semantic meaning of the at least one word or phrase in the portion of the text, updating the at least one word or phrase to reflect the selected hypothesis.

3. The method of claim 1 , wherein outputting the determined at least two hypotheses for presentation comprises outputting a first hypothesis and a second hypotheses for presentation via a graphical user interface, wherein the graphical user interface comprises a first indicator linking the first hypothesis to the at least one word or phrase in the portion of the text and a second indicator linking the second hypothesis to the at least one word or phrase in the portion of the text.

4. The method of claim 1 , wherein the plurality of alternative hypotheses comprises a first fact representing a first concept and a second fact representing a second concept, wherein the first concept is a parent of the second concept.

5. The method of claim 1 , further comprising:

receiving an indication of a selection by the user of a fact from among the determined at least two hypotheses; and

designating the fact chosen by the user as accurately representing the intended semantic meaning of the at least one word or phrase in the portion of the text.

6. The method of claim 1 , wherein the determining which of the plurality of alternative hypotheses satisfies at least one criteria comprises:

determining, for each of the plurality of alternative hypotheses, a likelihood that the respective hypothesis accurately represents the intended semantic meaning of the at least one word or phrase in the portion of the text; and

wherein the selecting comprises selecting the at least two hypotheses whose determined likelihoods are greater than a threshold.

7. The method of claim 1 , wherein the determining the at least two hypotheses comprises determining at least a first hypothesis and a second hypothesis of the plurality of alternative hypotheses, and wherein the outputting the determined at least two hypotheses for presentation comprises:

outputting for presentation the first hypothesis to the user; and

in response to a selection by the user of the first hypothesis, outputting for presentation the second hypothesis to the user.

8. The method of claim 1 ,

wherein the determining which of the plurality of alternative hypotheses satisfies at least one criteria comprises:

determining, for each of the plurality of alternative hypotheses, a likelihood that the respective hypothesis accurately represents the intended semantic meaning of the at least one word or phrase in the portion of the text, and

determining a first hypothesis having a highest determined likelihood and at least one additional hypothesis; and

wherein the outputting the determined at least two hypotheses for presentation comprises:

outputting for presentation the first hypothesis in association with the portion of the text, and

in response to a selection by the user of the portion of the text and/or of the first hypothesis, presenting the at least one additional hypothesis.

9. Apparatus comprising:

at least one processor; and

at least one memory storing processor-executable instructions that, when executed by the at least one processor, perform a method comprising:

identifying, using at least one statistical model applied to a portion of text documenting a patient encounter, a plurality of alternative hypotheses for a medical fact to be extracted from at least one word or phrase in the portion of the text documenting the patient encounter, each of the plurality of alternative hypotheses representing a different potential semantic meaning of the at least one word or phrase in the portion of the text;

selecting at least two hypotheses of the plurality of alternative hypotheses, wherein the selecting comprises:

determining which of the plurality of alternative hypotheses satisfies at least one criteria, and

selecting, from the plurality of alternative hypotheses, the at least two hypotheses that each satisfies the at least one criteria as hypotheses to be presented to a user documenting the patient encounter; and

outputting the selected at least two hypotheses for presentation to the user, wherein one of the selected at least two hypotheses accurately represents an intended semantic meaning of the at least one word or phrase in the portion of the text.

10. The apparatus of claim 9 , wherein the method further comprises:

in response to a selection by the user of the one of the selected at least two hypotheses that accurately represents the intended semantic meaning of the at least one word or phrase in the portion of the text, updating the at least one word or phrase to reflect the selected hypothesis.

11. The apparatus of claim 9 , wherein outputting the selected at least two hypotheses for presentation comprises outputting a first hypothesis and a second hypotheses for presentation via a graphical user interface, wherein the graphical user interface comprises a first indicator linking the first hypothesis to the at least one word or phrase in the portion of the text and a second indicator linking the second hypothesis to the at least one word or phrase in the portion of the text.

12. The apparatus of claim 9 , wherein the plurality of alternative hypotheses comprises a first fact representing a first concept and a second fact representing a second concept, wherein the first concept is a parent of the second concept.

13. The apparatus of claim 9 , wherein the method further comprises:

receiving an indication of a selection by the user of a fact from among the selected at least two hypotheses; and

designating the fact chosen by the user as accurately representing the intended semantic meaning of the at least one word or phrase in the portion of the text.

14. The apparatus of claim 9 , wherein the selecting comprises selecting at least a first hypothesis and a second hypothesis of the plurality of alternative hypotheses, and wherein the outputting the selected at least two hypotheses for presentation comprises:

outputting for presentation the first hypothesis to the user; and

in response to a selection by the user of the portion of the text and/or of the first hypothesis, outputting for presentation the second hypothesis to the user.

15. At least one non-transitory computer-readable storage medium encoded with computer-executable instructions that, when executed, perform a method comprising:

identifying, using at least one statistical model applied to a portion of text documenting a patient encounter, a plurality of alternative hypotheses for a medical fact to be extracted from at least one word or phrase in the portion of the text documenting the patient encounter, each of the plurality of alternative hypotheses representing a different potential semantic meaning of the at least one word or phrase in the portion of the text;

selecting at least two hypotheses of the plurality of alternative hypotheses, wherein the selecting comprises:

determining which of the plurality of alternative hypotheses satisfies at least one criteria, and

selecting, from the plurality of alternative hypotheses, the at least two hypotheses that each satisfies the at least one criteria as hypotheses to be presented to a user documenting the patient encounter; and

outputting the selected at least two hypotheses for presentation to the user, wherein one of the selected at least two hypotheses accurately represents an intended semantic meaning of the at least one word or phrase in the portion of the text.

16. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:

in response to a selection by the user of the one of the selected at least two hypotheses that accurately represents the intended semantic meaning of the at least one word or phrase in the portion of the text, updating the at least one word or phrase to reflect the selected hypothesis.

17. The at least one non-transitory computer-readable storage medium of claim 15 , wherein outputting the selected at least two hypotheses for presentation comprises outputting a first hypothesis and a second hypotheses for presentation via a graphical user interface, wherein the graphical user interface comprises a first indicator linking the first hypothesis to the at least one word or phrase in the portion of the text and a second indicator linking the second hypothesis to the at least one word or phrase in the portion of the text.

18. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the plurality of alternative hypotheses comprises a first fact representing a first concept and a second fact representing a second concept, wherein the first concept is a parent of the second concept.

19. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:

receiving an indication of a selection by the user of a fact from among the selected at least two hypotheses; and

designating the fact chosen by the user as accurately representing the intended semantic meaning of the at least one word or phrase in the portion of the text.

20. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the selecting comprises selecting at least a first hypothesis and a second hypothesis of the plurality of alternative hypotheses, and wherein the outputting the selected at least two hypotheses for presentation comprises:

outputting for presentation the first hypothesis to the user; and

in response to a selection by the user of the portion of the text and/or of the first hypothesis, outputting for presentation the second hypothesis to the user.