Methods and apparatus for presenting alternative hypotheses for medical facts
Techniques for presenting alternative hypotheses for medical facts may include identifying, using at least one statistical fact extraction model, a plurality of alternative hypotheses for a medical fact to be extracted from a portion of text documenting a patient encounter. At least two of the alternative hypotheses may be selected, and the selected hypotheses may be presented to a user documenting the patient encounter.
1. A computer-implemented method comprising:
determining a clinical fact from a text documenting an encounter with a patient, the text comprising an abstract concept, the abstract concept comprising a shared concept within a formal ontology of standard medical terms;
determining, based on an analysis of the clinical fact, whether a potential opportunity to increase specificity of the clinical fact exists; and
in response to a determination that the potential opportunity to increase specificity of the clinical fact exists:
identifying additional information that provides additional specificity to the clinical fact;
based on the identified additional information, replacing the clinical fact with a more specific clinical fact, the more specific clinical fact being ascertained from the encounter with the patient; and
generating, by a fact review system, an alert about the additional information that provides the additional specificity to the clinical fact.
2. The computer-implemented method of claim 1 , wherein determining the clinical fact comprises:
determining, using a statistical model, the clinical fact from the text documenting the encounter with the patient.
3. The computer-implemented method of claim 1 , wherein the clinical fact specifies a condition associated with the patient, and the additional information indicates a more specific version of the condition.
4. The computer-implemented method of claim 1 , wherein the determining whether the potential opportunity to increase specificity of the clinical fact exists and the generating the alert are performed before a clinician approves the clinical fact for the encounter.
5. The computer-implemented method of claim 1 , wherein the alert is a visual alert, and the method further comprises:
presenting the visual alert including the additional information to a user.
6. The computer-implemented method of claim 5 , wherein presenting the visual alert comprises:
presenting an option for providing the additional specificity to the clinical fact.
7. The computer-implemented method of claim 1 , wherein identifying the additional information that provides the additional specificity to the clinical fact comprises identifying information that is not documented in the text documenting the encounter with the patient.
8. The computer-implemented method of claim 1 , wherein the text comprises a free-form narration of the encounter with the patient.
9. A system comprising:
a processor; and
a memory storing processor-executable instructions that, when executed by the processor, perform a method comprising:
determining a clinical fact from a text documenting an encounter with a patient, the text comprising an abstract concept, the abstract concept comprising a shared concept within a formal ontology of standard medical terms;
determining, based on an analysis of the clinical fact, whether a potential opportunity to increase specificity of the clinical fact exists; and
in response to a determination that the potential opportunity to increase specificity of the clinical fact exists:
identifying additional information that provides additional specificity to the clinical fact;
based on the identified additional information, replacing the clinical fact with a more specific clinical fact, the more specific clinical fact being ascertained from the encounter with the patient; and
generating an alert about the additional information that provides the additional specificity to the clinical fact.
10. The system of claim 9 , wherein determining the clinical fact comprises:
determining, using a statistical model, the clinical fact from the text documenting the encounter with the patient.
11. The system of claim 9 , wherein the clinical fact specifies a condition associated with the patient, and the additional information indicates a more specific version of the condition.
12. The system of claim 9 , wherein the determining whether the potential opportunity to increase specificity of the clinical fact exists and the generating the alert are performed before a clinician approves the clinical fact for the encounter.
13. The system of claim 9 , wherein the alert is a visual alert, and the method further comprises:
presenting the visual alert including the additional information to a user.
14. The system of claim 13 , wherein presenting the visual alert comprises:
presenting an option for providing the additional specificity to the clinical fact.
15. The system of claim 9 , wherein identifying the additional information that provides the additional specificity to the clinical fact comprises identifying information that is not documented in the text documenting the encounter with the patient.
16. The system of claim 9 , wherein the text comprises a free-form narration of the encounter with the patient.
17. A non-transitory computer-readable storage medium comprising computer-executable instructions that, when executed by a processor, cause the at least one processor to perform a method comprising:
determining a clinical fact from a text documenting an encounter with a patient, the text comprising an abstract concept, the abstract concept comprising a shared concept within a formal ontology of standard medical terms;
determining, based on an analysis of the clinical fact, whether a potential opportunity to increase specificity of the clinical fact exists; and
in response to a determination that the potential opportunity to increase specificity of the clinical fact exists:
identifying additional information that provides additional specificity to the clinical fact;
based on the identified additional information, replacing the clinical fact with a more specific clinical fact, the more specific clinical fact being ascertained from the encounter with the patient; and
generating an alert about the additional information that provides the additional specificity to the clinical fact.
18. The non-transitory computer-readable storage medium of claim 17 , wherein determining the clinical fact comprises:
determining, using a statistical model, the clinical fact from the text documenting the encounter with the patient.
19. The non-transitory computer-readable storage medium of claim 17 , wherein the fact specifies a condition associated with the patient, and the additional information indicates a more specific version of the condition.
20. The non-transitory computer-readable storage medium of claim 17 , wherein the determining whether the potential opportunity to increase specificity of the clinical fact exists and the generating the alert are performed before a clinician approves the clinical fact for the encounter.