Automated clinical documentation system and method
A method, computer program product, and computing system for source separation is executed on a computing device and includes obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information obtained from a first encounter participant and at least a second audio encounter information obtained from at least a second encounter participant. The first audio encounter information and the at least a second audio encounter information are processed to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information.
1. A computer-implemented method for source separation, executed on a computing device, comprising:
obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information and first machine vision encounter information obtained from a first encounter participant and at least a second audio encounter information and at least a second machine vision encounter information obtained from at least a second encounter participant; and
processing the first audio encounter information, first multidimensional data that includes image and tensor data of the first machine vision encounter information, the at least a second audio encounter information, and second multidimensional data that includes image and tensor data of the at least a second machine vision encounter information to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information, wherein eliminating the audio interference between the first audio encounter information and the at least a second audio encounter information includes identifying, from the encounter information of a patient encounter, source signals of the first audio encounter information and the at least a second audio encounter information that are probabilistically one of minimally correlated and maximally independent based upon, at least in part, the first multidimensional data and the second multidimensional data, and wherein a time dimension is not included when identifying the source signals to eliminate the audio interference.
2. The computer-implemented method of claim 1 wherein obtaining encounter information of the patient encounter includes:
steering a first audio recording beam toward the first encounter participant; and
steering at least a second audio recording beam toward the at least a second encounter participant.
3. The computer-implemented method of claim 1 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing an echo cancellation process on the first audio encounter information and the at least a second audio encounter information.
4. The computer-implemented method of claim 1 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing a blind source process on the first audio encounter information and the at least a second audio encounter information.
5. The computer-implemented method of claim 1 wherein the audio interference between the first audio encounter information and the at least a second audio encounter information includes:
crosstalk between the first audio encounter information and the at least a second audio encounter information, wherein the crosstalk includes active listening in the audio interference that is eliminated between the first audio encounter information and the at least a second audio encounter information.
6. The computer-implemented method of claim 1 further comprising:
processing the encounter information to generate an encounter transcript.
7. The computer-implemented method of claim 6 further comprising:
processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.
8. The computer-implemented method of claim 1 wherein the at least one constraint includes a structural constraint.
9. The computer-implemented method of claim 1 wherein the audio interference between the first audio encounter information and the at least a second audio encounter information that is eliminated by imposing the at least one constraint includes one of:
the at least a second audio encounter information eliminated from the first audio encounter information obtained by a first audio recording beam pointing to the first encounter participant; and
the first audio encounter information eliminated from the at least a second audio encounter information obtained by a second audio recording beam pointing to the at least a second encounter participant.
10. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information and first machine vision encounter information obtained from a first encounter participant and at least a second audio encounter information and at least a second machine vision encounter information obtained from at least a second encounter participant; and
processing the first audio encounter information, first multidimensional data that includes image and tensor data of the first machine vision encounter information, the at least a second audio encounter information, and second multidimensional data that includes image and tensor data of the at least a second machine vision encounter information to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information, wherein eliminating the audio interference between the first audio encounter information and the at least a second audio encounter information includes identifying, from the encounter information of a patient encounter, source signals of the first audio encounter information and the at least a second audio encounter information that are probabilistically one of minimally correlated and maximally independent based upon, at least in part, the first multidimensional data and the second multidimensional data, and wherein a time dimension is not included when identifying the source signals to eliminate the audio interference.
11. The computer program product of claim 10 wherein obtaining encounter information of the patient encounter includes:
steering a first audio recording beam toward the first encounter participant; and
steering at least a second audio recording beam toward the at least a second encounter participant.
12. The computer program product of claim 10 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing an echo cancellation process on the first audio encounter information and the at least a second audio encounter information.
13. The computer program product of claim 10 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing a blind source process on the first audio encounter information and the at least a second audio encounter information.
14. The computer program product of claim 10 wherein the audio interference between the first audio encounter information and the at least a second audio encounter information includes:
crosstalk between the first audio encounter information and the at least a second audio encounter information, wherein the crosstalk includes active listening in the audio interference that is eliminated between the first audio encounter information and the at least a second audio encounter information.
15. The computer program product of claim 10 further comprising:
processing the encounter information to generate an encounter transcript.
16. The computer program product of claim 15 further comprising:
processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.
17. A computing system including a processor and memory configured to perform operations comprising:
obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information and first machine vision encounter information obtained from a first encounter participant and at least a second audio encounter information and at least a second machine vision encounter information obtained from at least a second encounter participant; and
processing the first audio encounter information, first multidimensional data that includes image and tensor data of the first machine vision encounter information, the at least a second audio encounter information, and second multidimensional data that includes image and tensor data of the at least a second machine vision encounter information to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information, wherein eliminating the audio interference between the first audio encounter information and the at least a second audio encounter information includes identifying, from the encounter information of a patient encounter, source signals of the first audio encounter information and the at least a second audio encounter information that are probabilistically one of minimally correlated and maximally independent based upon, at least in part, the first multidimensional data and the second multidimensional data, and wherein a time dimension is not included when identifying the source signals to eliminate the audio interference.
18. The computing system of claim 17 wherein obtaining encounter information of the patient encounter includes:
steering a first audio recording beam toward the first encounter participant; and
steering at least a second audio recording beam toward the at least a second encounter participant.
19. The computing system of claim 17 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing an echo cancellation process on the first audio encounter information and the at least a second audio encounter information.
20. The computing system of claim 17 wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:
executing a blind source process on the first audio encounter information and the at least a second audio encounter information.
21. The computing system of claim 17 wherein the audio interference between the first audio encounter information and the at least a second audio encounter information includes:
crosstalk between the first audio encounter information and the at least a second audio encounter information, wherein the crosstalk includes active listening in the audio interference that is eliminated between the first audio encounter information and the at least a second audio encounter information.
22. The computing system of claim 17 further comprising:
processing the encounter information to generate an encounter transcript.
23. The computing system of claim 22 further comprising:
processing at least a portion of the encounter transcript to populate at least a portion of a medical record associated with the patient encounter.