Collaborative artificial intelligence method and system
A method and system of audibly broadcasting responses to a user based on user queries about a specific patient molecular report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration device, identifying at least one intent associated with the audible query, identifying at least one data operation associated with the at least one intent, associating each of the at least one data operations with a first set of data presented on the molecular report, executing each of the at least one data operations on a second set of data to generate response data, generating an audible response file associated with the response data and providing the audible response file for broadcasting via a speaker coupled to the collaboration device.
1. A method of audibly broadcasting responses to a user based on user queries about a specific patient's molecular report information, the method for use with a collaboration device that includes a processor and a microphone and a speaker linked to the processor, the method comprising:
(i) storing molecular report information for a plurality of patients in a system database;
(ii) receiving an audible query answerable in part by reference to a genomic biomarker from the user via the microphone;
(iii) identifying at least one intent associated with the audible query, the at least one intent including at least one qualifying entity, the at least one intent identified by a machine learning module recognizing the audible query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module;
(iv) identifying at least one parameter value associated with the entity in the audible query corresponding to the at least one qualifying entity;
(v) identifying at least one first data operation associated with the at least one intent, the at least one first data operation associated with the at least one qualifying entity;
(vi) identifying at least one second data operation associated with the genomic biomarker;
(vii) executing (a) at least one of the identified at least one first data operations and (b) at least one of the identified at least one second data operations on a first set of data in the system database, the first set of data comprising a genomic biomarker from the specific patient's molecular report information, to generate a first set of response data;
(viii) using the first set of response data to generate an audible response file; and
(ix) broadcasting the audible response file via the speaker.
2. The method of claim 1 wherein at least one of the qualifying parameter values includes a patient identity.
3. The method of claim 1 wherein at least one of the qualifying parameter values includes a patient's disease state.
4. The method of claim 1 wherein at least one of the qualifying parameter values includes a genetic mutation.
5. The method of claim 1 wherein at least one of the qualifying parameter values includes a procedure type.
6. The method of claim 1 further including the step of storing a general knowledge database in the system database that includes non-patient specific data about specific topics, wherein the first data operation is associated with the specific patient's molecular report information and the second data operation is associated with the general knowledge database.
7. The method of claim 6 wherein the second data operation associated with the general knowledge database is executed first to generate second data operation results, the second data operation results are used to define the first data operation and the first data operation associated with the specific patient's molecular report information is executed second to generate the first set of response data.
8. The method of claim 6 wherein the first data operation associated with the specific patient's molecular report information is executed first to generate first data operation results, the first data operation results are used to define the second data operation and the second data operation associated with the general knowledge database is executed second to generate the first set of response data.
9. The method of claim 1 wherein the step of identifying at least one intent includes determining that the audible query is associated with the specific patient, accessing the specific patient's molecular report information, determining the specific patient's cancer state from the molecular report information and then selecting an intent from a pool of cancer state related intents.
10. The method of claim 9 further including the step of storing a general knowledge database in the system database that includes non-patient specific data about specific topics, the method further including the steps of, upon determining that the audible query is not associated with any specific patient, selecting an intent that is associated with the general knowledge database.
11. The method of claim 1 wherein the collaboration device includes a portable wireless device that includes a wireless transceiver.
12. The method of claim 11 wherein the collaboration device is a handheld device.
13. The method of claim 11 wherein the collaboration device includes at least one visual indicator, the processor linked to the visual indicator and controllable to change at least some aspect of the appearance of the visual indicator to indicate different states of the collaboration device.
14. The method of claim 1 wherein the processor is programmed to monitor microphone input to identify a “wake up” phrase, the processor monitoring for the audible query after the wake up phrase is detected.
15. The method of claim 1 wherein a series of audible queries are received via the microphone, the at least one of the identified first data operations including identifying a subset of data that is usable with subsequent audio queries to identify intents associated with the subsequent queries.
16. The method of claim 1 further including the steps of, based on at least one audible query received via the microphone and related data in a system database, identifying at least one activity that a collaboration device user may want to perform and initiating the at least one activity.
17. The method of claim 16 wherein the step of initiating the at least one activity includes generating a second audible response file and broadcasting the second audible response file to the user seeking verification that the at least one activity should be performed and monitoring the microphone for an affirmative response and, upon receiving an affirmative response, initiating the at least one activity.
18. The method of claim 16 , wherein the at least one activity includes periodically capturing health information from electronic health records included in the system database.
19. The method of claim 16 wherein the at least one activity includes checking status of an existing clinical or lab order.
20. The method of claim 16 , wherein the at least one activity includes ordering a new clinical or lab order.
21. The method of claim 1 , wherein the collaboration device is one of a smartphone, a tablet computer, a laptop computer, a desktop computer, or an Amazon Echo.
22. The method of claim 16 wherein the step of initiating the at least one activity includes automatically initiating the at least one activity without any initiating input from the user.
23. The method of claim 1 further including storing and maintaining a general cancer knowledge database, persistently updating the specific patient's molecular report information, automatically identifying at least one intent and associated data operation related to the general cancer knowledge database based on the specific patient's molecular report information, persistently executing the associated data operation on the general cancer knowledge database to generate a new set of response data not previously generated and, upon generating a new set of response data, using the new set of response data to generate another audible response file and broadcasting the another audible response file via the speaker.
24. The method of claim 1 also for use with an electronic health records system that maintains health records associated with a plurality of patients including the specific patient, the method further including identifying a third data operation associated with the at least one intent and executing the third data operation on the specific patient's health record to generate additional response data.
25. The method of claim 24 wherein the step of using the first set of response data to generate an audible response file includes using the first set of response data and the additional response data to generate the audible response file.
26. A method of audibly broadcasting responses to a user based on user queries about a specific patient's molecular report information, the method for use with a collaboration device that includes a processor and a microphone and a speaker linked to the processor, the method comprising:
(i) storing separate molecular report information for each of a plurality of patients in a system database;
(ii) storing a general cancer knowledge database that includes non-patient specific data about cancer topics;
(iii) receiving an audible query answerable in part by reference to a genomic biomarker from the user via the microphone;
(iv) identifying at least one intent associated with the audible query, the at least one intent including at least one qualifying entity, the at least one intent identified by a machine learning module recognizing the audible query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module;
(v) identifying at least one parameter value associated with the entity in the audible query corresponding to the at least one qualifying entity;
(vi) identifying at least a first data operation associated with the at least one intent, the at least one first data operation associated with the at least one qualifying entity and the specific patient's molecular report information;
(vii) identifying at least a second data operation associated with the at least one intent the at least one second data operation associated with the at least one qualifying entity and the general cancer knowledge database;
(viii) identifying at least one third data operation associated with the genomic biomarker;
(ix) executing the at least a first data operation and at least one of the at least one third data operations on a first set of data in the system database, the first set of data comprising a genomic biomarker from the specific patient's molecular report information, to generate a first set of response data;
(x) executing the at least a second data operation and at least one of the at least one third data operations on the general cancer knowledge database, the general cancer knowledge database comprising genomic alteration knowledge, to generate a second set of response data;
(xi) using at least one of the first and second sets of response data to generate an audible response file; and
(xii) broadcasting the audible response file via the speaker.
27. A method of audibly broadcasting responses to a user based on user queries about a specific patient's molecular report information, the method for use with a collaboration device that includes a processor and a microphone and a speaker linked to the processor, the method comprising:
(i) storing molecular report information for a plurality of patients in a system database;
(ii) receiving an audible query answerable in part by reference to a genomic biomarker from the user via the microphone;
(iii) determining that the audible query is associated with the specific patient;
(iv) accessing the specific patient's molecular report information;
(v) determining the specific patient's cancer state from the molecular report information;
(vi) identifying at least one intent from a pool of intents related to the specific patient's cancer state and the audible query, the at least one intent including at least qualifying entity, the at least one intent identified by a machine learning module recognizing the audible query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module;
(vii) identifying at least one parameter value associated with the entity in the audible query corresponding to the at least one qualifying entity;
(viii) identifying at least one first data operation associated with the at least one intent the at least one first data operation associated with the at least one qualifying entity;
(ix) identifying at least one second data operation associated with the genomic biomarker;
(x) executing (a) at least one of the identified at least one first data operations and (b) at least one of the identified at least one second data operations on a first set of data in the system database, the first set of data comprising a genomic biomarker from the specific patient's molecular report information, to generate a first set of response data;
(xi) using the first set of response data to generate an audible response file; and
(xii) broadcasting the audible response file via the speaker.
28. A method of audibly broadcasting responses to a user based on user queries about a patient, the method for use with a collaboration device that includes a processor and a microphone and a speaker linked to the processor, the method comprising:
(i) storing health record information for a plurality of patients in a system database and storing a general cancer knowledge database;
(ii) receiving an audible query answerable in part by reference to a genomic biomarker from the user via the microphone;
(iii) identifying a specific patient associated with the audible query;
(iv) accessing the health record information for the specific patient;
(v) identifying cancer related data in the specific patient's health record information;
(vi) identifying at least one intent related to the identified cancer related data, the at least one intent including at least one qualifying entity, the at least one intent identified by a machine learning module recognizing the audible query as sufficiently corresponding to an intent phrase provided to or generated by the machine learning module;
(vii) identifying at least one parameter value associated with the entity in the cancer related data corresponding to the at least one qualifying entity;
(viii) identifying at least one first data operation related to the at least one intent, the at least one first data operation associated with the at least one qualifying entity;
(ix) identifying at least one second data operation associated with the genomic biomarker;
(x) executing (a) at least one of the at least one first data operations and (b) at least one of the at least one second data operations on the general cancer knowledge database, the general cancer knowledge database comprising genomic biomarker knowledge, to generate a first set of response data;
(xi) using the first set of response data to generate an audible response file; and
(xii) broadcasting the audible response file via the speaker.
29. The method of claim 1 , wherein the genomic biomarker is a TMB biomarker.
30. The method of claim 1 , wherein the genomic biomarker is a fusion biomarker.