Methods for automatic cohort selection in epidemiologic studies and clinical trials

1. A system for selecting a cohort for a clinical study, the system comprising:

a processor; and

a computer-readable medium having instructions thereon, wherein the instructions, when executed by the processor, cause the processor to:

receive a universal graph;

access an unstructured electronic health record for each patient in a population of patients;

for each patient in the population of patients, transform, based on the universal graph, the associated unstructured electronic health records of the patient into a patient graph, the patient graph representing a set of clinical concepts and corresponding semantic roles for the patient;

receive a first set of inclusion and exclusion criteria;

transform, based on the universal graph, the first set of inclusion and exclusion criteria into a first target graph, the first target graph representing a first set of target clinical concepts for the clinical study;

receive a second set of inclusion and exclusion criteria;

transform, based on the universal graph, the first set of inclusion and exclusion criteria and the second set of inclusion and exclusion criteria into a second target graph for the clinical study; and

for each patient in the population of patients, in response to alignment between the patient graph of the patient and the second target graph, append the patient to a first subpopulation of patients.

2. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to enroll a particular patient of the first subpopulation of patients in the clinical study.

3. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to render an indication of patient eligibility via a point-of-care interface.

4. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to ingest a corpus of medical data and generate the universal graph based on the corpus of medical data.

5. The system of claim 4 , wherein the instructions, when executed by the processor, cause the processor to generate the universal graph based on the corpus of medical data by generating a set of context-specific universal graphs, each context-specific universal graph in the set of context-specific universal graphs representing a distinct clinical context.

6. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to, for each of the patients of the population of patients, append the patient graph to a set of patient graphs.

7. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

for each patient in the population of patients, in response to alignment between the patient graph of the patient and the first target graph, append the patient to a second subpopulation of patients; and

render a representation of the second subpopulation of patients within a clinical research interface.

8. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to render a representation of the first subpopulation of patients within a clinical research interface.

9. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

record a selection of a potential clinical cohort from the first subpopulation of patients;

in response to access of a particular electronic health record of a particular patient included in a potential clinical cohort at a point-of-care interface, render a visual indicator of the eligibility of the particular patient for the clinical study within the point-of-care interface;

record a first interaction with the visual indicator; and

in response to recording the first interaction with the visual indicator, enroll at least one patient of the first subpopulation of patients in the clinical study.

10. The system of claim 9 , wherein the instructions, when executed by the processor, cause the processor to render the visual indicator by rendering the visual indicator within a point-of-care application displaying an electronic health record of the particular patient.

11. The system of claim 9 , wherein the instructions, when executed by the processor, cause the processor to, in response to recording the interaction with the visual indicator, enroll the particular patient in the clinical study by:

rendering the first set of inclusion and exclusion criteria and the second set of inclusion and exclusion criteria applicable to the particular patient;

rendering an option icon for enrolling the particular patient in the clinical study; and

in response to recording an interaction with the option icon, enrolling the particular patient in the clinical study.

12. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

for each patient in the population of patients, index the patient graph of the patient within the universal graph;

for each patient in the population of patients, detect alignment between the first target graph and the patient graph of the patient by accessing a first index corresponding to the first target graph within the universal graph; and

for each patient in the population of patients, detect alignment between the second target graph and the patient graph of the patient by accessing a second index corresponding to the second target graph.

13. The system of claim 12 , wherein the instructions, when executed by the processor, cause the processor to index the patient graph of the patient within the universal graph by:

identifying an isomorphic subgraph of the universal graph isomorphic with the patient graph; and

listing the patient of the patient graph in an index corresponding to the isomorphic subgraph.

14. The system of claim 12 , wherein the instructions, when executed by the processor, cause the processor to index the patient graph of the patient within the universal graph by:

identifying a set of morphologically similar subgraphs of the universal graphs morphologically similar to the patient graph; and

listing the patient of the patient graph in a set of indices corresponding to the set of morphologically similar subgraphs.

15. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to receive the first set of inclusion and exclusion criteria by:

receiving a selection of a file representing the clinical study; and

extracting the first set of inclusion and exclusion criteria based on the file representing the clinical study.

16. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to, for each inclusion criterion and exclusion criterion in the first set of inclusion and exclusion criteria and in the second set of inclusion and exclusion criteria:

generate a modified target graph without the criterion;

for each patient in the population of patients, in response to alignment between the patient graph of the patient and the modified target graph, append the patient to a modified subpopulation of patients;

calculate a difference in population between the first subpopulation of patients and the modified subpopulation of patients; and

render a visual indicator of the difference in population within a clinical research interface.

17. The system of claim 1 , wherein the instructions, when executed by the processor, cause the processor to:

monitor an unstructured electronic health record of the particular patient;

in response to detecting a change in the unstructured electronic health record of the patient, generate a second patient graph for the particular patient; and

in response to detecting that the second patient graph does not match the second target graph, remove the particular patient from the first subpopulation of patients.

18. The system of claim 1 , wherein the system comprises an electronic health record database.

19. A method for selecting a cohort for a clinical study, the method comprising:

receiving, by a processor of a computing device, a universal graph;

accessing, by the processor, an unstructured electronic health record for each patient in a population of patients;

for each patient in the population of patients, transforming, by the processor, based on the universal graph, the associated unstructured electronic health records of the patient into a patient graph, the patient graph representing a set of clinical concepts and corresponding semantic roles for the patient;

receiving, by the processor, a first set of inclusion and exclusion criteria;

transforming, by the processor, based on the universal graph, the first set of inclusion and exclusion criteria into a first target graph, the first target graph representing a first set of target clinical concepts for the clinical study;

receiving, by the processor, a second set of inclusion and exclusion criteria;

transforming, by the processor, based on the universal graph, the first set of inclusion and exclusion criteria and the second set of inclusion and exclusion criteria into a second target graph for the clinical study; and

for each patient in the population of patients, in response to alignment between the patient graph of the patient and the second target graph, appending, by the processor, the patient to a subpopulation of patients.