Identifying potential patient candidates for clinical trials

1. A computer-implemented method for matching clinical trial openings with candidates from a patient population, the method comprising:

identifying a first clinical trial description;

generating, based on natural language processing techniques including Unstructured Information Management Architecture, annotations of the first clinical trial description, the natural language processing techniques including one or more annotators;

generating a first trial feature vector based on the annotations of the first clinical trial description, the first trial feature vector comprising a first array of values, each value of the first array of values representing a clinical feature;

generating a comparison value based on the first trial feature vector and a first patient feature vector, the first patient feature vector comprising a second array of values, wherein the first patient feature vector is generated using annotations of a first patient record of a plurality of stored patient records, the annotations of the patient record generated by applying the natural language processing techniques, including the one or more annotators, to the patient record;

displaying information about a patient associated with the patient record to a user based on the comparison value;

retrieving the first patient record and other patient records stored in a collection database, using a crawler, based on similarities between the annotations of the clinical trial description and contents of the patient records;

applying the natural language processing techniques, including one or more annotators, to the first patient record to generate annotations of the first patient record;

generating the first patient feature vector based on the annotations of the first patient record, the first patient feature vector comprising the second array of values, each representing a clinical feature;

determining the first patient record has been annotated and subsequently modified;

retrieving, in response to determining the first patient record has been annotated and subsequently modified, the subsequently modified first patient record, using a crawler, to generate updated annotations of the subsequently modified first patient record;

generating an updated first patient feature vector based on the updated annotations of the subsequently modified first patient record, the updated first patient feature vector comprising an updated second array of values, each representing a clinical feature;

generating an updated comparison value based on the first trial feature vector and the updated first patient feature vector; and

displaying updated information to the user based on the updated comparison value.

2. The method of claim 1 , further comprising:

determining that a first value in the first array of values should be prioritized; and

transforming the first value into a weighted vector value, wherein the weighted vector value is used when generating the first trial feature vector.

3. The method of claim 1 , wherein the displaying information about the patient associated with the patient record to a user based on the comparison value occurs through an interactive user interface, and wherein the information about the patient is displayed with information about other patients based on a plurality of comparison values generated from a plurality of patient records associated with the other patients, the method further comprising:

receiving, through the interactive user interface, a threshold comparison value from the user; and

displaying, via the interactive user interface, information about a set of patients, the set of patients associated with comparison values that meet the threshold comparison value.

4. The method of claim 1 , wherein the information displayed to the user based on comparison value includes the comparison value.

5. The method of claim 1 , wherein the information displayed to the user based on comparison value includes an identification of the patient.

6. The method of claim 1 , wherein the information displayed to the user based on comparison value includes contact information for the patient.

7. The method of claim 3 , wherein the interactive user interface allows the user to sort the information about the patient and the information about other patients based on comparison values.

8. The method of claim 3 , wherein the interactive user interface allows the user to sort the information displayed based on patient name.

9. The method of claim 3 , wherein the interactive user interface allows the user to sort the information displayed based on patient contact information.

10. The method of claim 1 , wherein the comparison value represents a logical distance between the clinical trial feature vector and the patient feature vector.

11. The method of claim 1 , wherein similarities among patient records are used to generate the annotators.

12. A system for matching clinical trial openings with candidates from a patient population, the system comprising:

a memory with program instructions stored thereon; and

a processor in communication with the memory, wherein the system is configured to perform a method, the method comprising:

identifying a first clinical trial description;

generating, based on natural language processing techniques including Unstructured Information Management Architecture, annotations of the first clinical trial description, the natural language processing techniques including one or more annotators;

generating a first trial feature vector based on the annotations of the first clinical trial description, the first trial feature vector comprising a first array of values, each value of the first array of values representing a clinical feature;

generating a comparison value based on the first trial feature vector and a first patient feature vector, the first patient feature vector comprising a second array of values, wherein the first patient feature vector is generated using annotations of a first patient record of a plurality of stored patient records, the annotations of the patient record generated by applying the natural language processing techniques, including the one or more annotators, to the patient record;

displaying information about a patient associated with the patient record to a user based on the comparison value;

retrieving the first patient record and other patient records stored in a collection database, using a crawler, based on similarities between the annotations of the clinical trial description and contents of the patient records;

applying the natural language processing techniques, including one or more annotators, to the first patient record to generate annotations of the first patient record;

generating the first patient feature vector based on the annotations of the first patient record, the first patient feature vector comprising the second array of values, each representing a clinical feature;

determining the first patient record has been annotated and subsequently modified;

retrieving, in response to determining the first patient record has been annotated and subsequently modified, the subsequently modified first patient record, using a crawler, to generate updated annotations of the subsequently modified first patient record;

generating an updated first patient feature vector based on the updated annotations of the subsequently modified first patient record, the updated first patient feature vector comprising an updated second array of values, each representing a clinical feature;

generating an updated comparison value based on the first trial feature vector and the updated first patient feature vector; and

displaying updated information to the user based on the updated comparison value.

13. The system of claim 12 , wherein the method further comprises:

determining that a first value in the first array of values should be prioritized; and

in response to the determination that a first value in the first array of values should be prioritized, assigning a vector weight value to the first value, wherein the vector weight value is used when generating the comparison value.

14. The system of claim 12 , wherein the displaying information about the patient associated with the patient record to a user based on the comparison value occurs through an interactive user interface, and wherein the information about the patient is displayed with information about other patients based on a plurality of comparison values generated from a plurality of patient records associated with the other patients, the method further comprising:

receiving, through the interactive user interface, a threshold comparison value from the user; and

displaying, via the interactive user interface, a set of comparison values that meet the threshold comparison value.

15. A computer program product for matching clinical trial openings with candidates from a patient population, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:

identify a first clinical trial description;

generate, based on natural language processing techniques including Unstructured Information Management Architecture, annotations of the first clinical trial description, the natural language processing techniques including one or more annotators;

generate a first trial feature vector based on the annotations of the first clinical trial description, the first trial feature vector comprising a first array of values, each value of the first array of values representing a clinical feature;

generate a comparison value based on the first trial feature vector and a first patient feature vector, the first patient feature vector comprising a second array of values, wherein the first patient feature vector is generated using annotations of a first patient record of a plurality of stored patient records, the annotations of the patient record generated by applying the natural language processing techniques, including the one or more annotators, to the patient record;

display information about a patient associated with the patient record to a user based on the comparison value;

retrieve the first patient record and other patient records stored in a collection database, using a crawler, based on similarities between the annotations of the clinical trial description and contents of the patient records;

apply the natural language processing techniques, including one or more annotators, to the first patient record to generate annotations of the first patient record;

generate the first patient feature vector based on the annotations of the first patient record, the first patient feature vector comprising the second array of values, each representing a clinical feature;

determine the first patient record has been annotated and subsequently modified;

retrieve, in response to determining the first patient record has been annotated and subsequently modified, the subsequently modified first patient record, using a crawler, to generate updated annotations of the subsequently modified first patient record;

generate an updated first patient feature vector based on the updated annotations of the subsequently modified first patient record, the updated first patient feature vector comprising an updated second array of values, each representing a clinical feature;

generate an updated comparison value based on the first trial feature vector and the updated first patient feature vector; and

display updated information to the user based on the updated comparison value.

16. The computer program product of claim 15 , wherein the program instructions further cause the device to:

determine that a first value in the first array of values should be prioritized; and

assign a vector weight value to the first value, wherein the vector weight value is used when generating the comparison value.

17. The computer program product of claim 15 , wherein the displaying information about the patient associated with the patient record to a user based on the comparison value occurs through an interactive user interface, and wherein the information about the patient is displayed with information about other patients based on a plurality of comparison values generated from a plurality of patient records associated with the other patients, wherein the program instructions further cause the device to:

receive, through the interactive user interface, a threshold comparison value from the user; and

display, via the interactive user interface, a set of comparison values that meet the threshold comparison value.