US2023092558A1PendingUtilityA1
Automated clinical documentation system and method
Est. expiryMar 5, 2038(~11.6 yrs left)· nominal 20-yr term from priority
G10L 15/26G16H 10/60G16H 15/00G16H 40/20
61
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
A method, computer program product, and computing system for: receiving an initial portion of an encounter record; processing the initial portion of the encounter record to generate initial content for a medical report; receiving one or more additional portions of the encounter record; and processing the one or more additional portions of the encounter record to modify the medical report.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A computer implemented method, executed on a computing device, comprising:
receiving an initial portion of an encounter record of a patient encounter, wherein the encounter record includes a machine-generated encounter transcript; processing the initial portion of the encounter record to generate initial content for a medical report from the machine-generated encounter transcript; generating the medical report to include the initial content, wherein the medical report is generated after the processing the initial portion; receiving the one or more additional portions of the encounter record; and processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter, wherein processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter includes:
identifying an occurrence of the one or more additional portions of the encounter record, wherein the one or more additional portions of the encounter record are identified as having been defined by at least one attribute, wherein the at least one attribute includes at least one of a time interval of the machine-generated encounter transcript, a word quantity of the machine-generated encounter transcript, a storage size of the one or more additional portions of the encounter record, an identity of who is speaking in the one or more additional portions of the encounter record, and a topic discussed in the one or more additional portions of the encounter record;
processing the one or more additional portions of the encounter record to generate additional content for the medical report with the machine-generated encounter transcript of the one or more additional portions of the encounter record,
appending the medical report to include the additional content during the patient encounter, and
regenerating the medical report based, at least in part, upon a combination of the one or more additional portions of the encounter record and the initial portion of an encounter record, and further based upon identifying the occurrence of the one or more additional portions of the encounter record as having been defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record, wherein a model used in the regeneration of the medical report includes by thresholding soft-alignment from attention weights.
2 . The computer implemented method of claim 1 wherein the additional content for the medical report is based upon, at least in part, transcript-report pairs used to populate the medical report from the machine-generated encounter transcript.
3 . The computer implemented method of claim 2 wherein the medical report is regenerated incrementally using the transcript-report pairs each time an additional portion of the one or more additional portions of the encounter record is identified as having been being defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record.
4 . The computer implemented method of claim 1 wherein the model used in the regeneration of the medical report includes inter-encoder-decoder attention scores and hard alignment.
5 . 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:
receiving an initial portion of an encounter record of a patient encounter, wherein the encounter record includes a machine-generated encounter transcript; processing the initial portion of the encounter record to generate initial content for a medical report from the machine-generated encounter transcript; generating the medical report to include the initial content, wherein the medical report is generated after the processing the initial portion; receiving the one or more additional portions of the encounter record; and processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter, wherein processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter includes:
identifying an occurrence of the one or more additional portions of the encounter record, wherein the one or more additional portions of the encounter record are identified as having been defined by at least one attribute, wherein the at least one attribute includes at least one of a time interval of the machine-generated encounter transcript, a word quantity of the machine-generated encounter transcript, a storage size of the one or more additional portions of the encounter record, an identity of who is speaking in the one or more additional portions of the encounter record, and a topic discussed in the one or more additional portions of the encounter record;
processing the one or more additional portions of the encounter record to generate additional content for the medical report with the machine-generated encounter transcript of the one or more additional portions of the encounter record,
appending the medical report to include the additional content during the patient encounter, and
regenerating the medical report based, at least in part, upon a combination of the one or more additional portions of the encounter record and the initial portion of an encounter record, and further based upon identifying the occurrence of the one or more additional portions of the encounter record as having been defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record, wherein a model used in the regeneration of the medical report includes by thresholding soft-alignment from attention weights.
6 . The computer program product of claim 5 wherein the additional content for the medical report is based upon, at least in part, transcript-report pairs used to populate the medical report from the machine-generated encounter transcript.
7 . The computer program product of claim 6 wherein the medical report is regenerated incrementally using the transcript-report pairs each time an additional portion of the one or more additional portions of the encounter record is identified as having been being defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record.
8 . The computer program product of claim 5 wherein the model used in the regeneration of the medical report includes inter-encoder-decoder attention scores and hard alignment.
9 . A computing system including a processor and memory configured to perform operations comprising:
receiving an initial portion of an encounter record of a patient encounter, wherein the encounter record includes a machine-generated encounter transcript; processing the initial portion of the encounter record to generate initial content for a medical report from the machine-generated encounter transcript; generating the medical report to include the initial content, wherein the medical report is generated after the processing the initial portion; receiving the one or more additional portions of the encounter record; and processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter, wherein processing the one or more additional portions of the encounter record to modify the medical report during the patient encounter includes:
identifying an occurrence of the one or more additional portions of the encounter record, wherein the one or more additional portions of the encounter record are identified as having been defined by at least one attribute, wherein the at least one attribute includes at least one of a time interval of the machine-generated encounter transcript, a word quantity of the machine-generated encounter transcript, a storage size of the one or more additional portions of the encounter record, an identity of who is speaking in the one or more additional portions of the encounter record, and a topic discussed in the one or more additional portions of the encounter record;
processing the one or more additional portions of the encounter record to generate additional content for the medical report with the machine-generated encounter transcript of the one or more additional portions of the encounter record,
appending the medical report to include the additional content during the patient encounter, and
regenerating the medical report based, at least in part, upon a combination of the one or more additional portions of the encounter record and the initial portion of an encounter record, and further based upon identifying the occurrence of the one or more additional portions of the encounter record as having been defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record, wherein a model used in the regeneration of the medical report includes by thresholding soft-alignment from attention weights.
10 . The computing system of claim 9 wherein the additional content for the medical report is based upon, at least in part, transcript-report pairs used to populate the medical report from the machine-generated encounter transcript.
11 . The computing system of claim 6 wherein the medical report is regenerated incrementally using the transcript-report pairs each time an additional portion of the one or more additional portions of the encounter record is identified as having been being defined by at least one of the word quantity of the machine-generated encounter transcript, the storage size of the one or more additional portions of the encounter record, the identity of who is speaking in the one or more additional portions of the encounter record, and the topic discussed in the one or more additional portions of the encounter record.
12 . The computing system of claim 9 wherein the model used in the regeneration of the medical report includes inter-encoder-decoder attention scores and hard alignment.Join the waitlist — get patent alerts
Track US2023092558A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.