# US 10,319,004 B2 · User and engine code handling in medical coding system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,319,004 B2 - Document ID: US10319004B2 - Status: Granted - Kind: B2 - Application number: 14/296,303 - Filed: 2014-06-04 - Published: 2015-12-10 - Granted: 2019-06-11 - Earliest claimed: 2014-06-04 - Assignees: Nuance Communications, Inc. - Applicants: Nuance Communications, Inc. - Inventors: Gregory Reiser; Howard D'Souza; Aparna Subramanian; Regina Spitznagel - Web page: https://patentgrep.com/patent/US10319004B2 ## CPC - G06Q 30/04: Billing or invoicing - G06F 40/10: Text processing (natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40) - G06Q 10/00: Administration; Management - G06Q 10/10: Office automation; Time management - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06Q 40/08: Insurance - G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Techniques for medical coding include applying a natural language understanding (NLU) engine to a free-form text documenting a clinical patient encounter, to derive a first set of one or more medical billing codes for the clinical patient encounter and a link between each code in the first set and a corresponding portion of the free-form text. The first set of codes may be compared to a second set of one or more medical billing codes approved by one or more human users for the patient encounter, to identify at least one code in the first set that overlaps with at least one code in the second set. The code in the second set approved by the one or more human users may be retained instead of the overlapping code in the first set derived by the NLU engine. ## Claims ### Claim 1 A method comprising: (a) outputting for presentation to one or more human users, via a user interface implemented using at least one processor, a set of one or more medical billing codes derived from first documentation for a clinical patient encounter by a natural language understanding (NLU) engine, the NLU engine being an automated language processing component implemented by the at least one processor; (b) receiving user input, that was input via the user interface, to approve at least one of the one or more medical billing codes derived by the NLU engine, and/or to manually input one or more codes, resulting in a set of one or more user-approved medical billing codes for the clinical patient encounter; (c) after the act (b), applying the NLU engine, implemented by the at least one processor, to a free-form text that relates to the clinical patient encounter and is not part of the first documentation documenting the clinical patient encounter, to derive a first engine-derived medical billing code for the clinical patient encounter and a first link between the first engine-derived medical billing code and a corresponding first portion of the free-form text and a second engine-derived medical billing code for the clinical patient encounter and a second link between the second engine-derived medical billing code and a corresponding second portion of the free-form text; (d) automatically determining whether the first engine-derived medical billing code and the second engine-derived medical billing code overlap with at least one user-approved medical billing code of the set of user-approved medical billing codes; (e) in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the at least one user-approved medical billing code instead of the first engine-derived medical billing code; (f) in response to automatically determining that the second engine-derived medical billing code does not overlap with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the second engine-derived medical billing code; (g) generating a finalized sequence of medical billing codes for the clinical patient encounter, the finalized sequence of medical billing codes including the retained at least one user-approved medical billing code and the second engine-derived medical billing code; and (h) training the NLU engine based on training data including the finalized sequence of medical billing codes for the clinical patient encounter, the training comprising providing the training data as input to one or more models associated with the automated language processing component. ### Claim 2 (depends on 1) The method of claim 1, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same diagnosis code as the at least one user-approved medical billing code. ### Claim 3 (depends on 1) The method of claim 1, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same procedure code as the at least one user-approved medical billing code, and that the patient did not undergo the same procedure twice. ### Claim 4 (depends on 1) The method of claim 1, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a less specific version of the at least one user-approved medical billing code. ### Claim 5 (depends on 1) The method of claim 1, wherein the act (e) comprises presenting the retained at least one user-approved medical billing code via the user interface, and suppressing presentation of the first engine-derived medical billing code. ### Claim 6 (depends on 1) The method of claim 1, wherein the act (e) comprises in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, generating a link between the retained at least one user-approved medical billing code and the first portion of the free-form text corresponding to the first engine-derived medical billing code. ### Claim 7 (depends on 6) The method of claim 6, further comprising, in response to user selection of the retained at least one user-approved medical billing code via the user interface, providing an indicator of the linked first portion of the free-form text corresponding to the first engine-derived medical billing code. ### Claim 8 At least one computer-readable storage medium storing computer-executable instructions that, when executed, perform a method comprising: (a) outputting for presentation to one or more human users, via a user interface, a set of one or more medical billing codes derived from first documentation for a clinical patient encounter by a natural language understanding (NLU) engine, the NLU engine being an automated language processing component implemented by at least one processor; (b) receiving user input, that was input via the user interface, to approve at least one of the one or more medical billing codes derived by the NLU engine, and/or to manually input one or more codes, resulting in a set of one or more user-approved medical billing codes for the patient encounter; (c) after the act (b), applying the NLU engine to a free-form text that relates to the clinical patient encounter and is not part of the first documentation documenting the clinical patient encounter, to derive a first engine-derived medical billing code for the clinical patient encounter and a first link between the first engine-derived medical billing code and a corresponding first portion of the free-form text and a second engine-derived medical billing code for the clinical patient encounter and a second link between the second engine-derived medical billing code and a corresponding second portion of the free-form text; (d) automatically determining whether the first engine-derived medical billing code and the second engine-derived medical billing code overlap with at least one user-approved medical billing code of the set of user-approved medical billing codes; (e) in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the at least one user-approved medical billing code instead of the first engine-derived medical billing code; (f) in response to automatically determining that the second engine-derived medical billing code does not overlap with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the second engine-derived medical billing code; (g) generating a finalized sequence of medical billing codes for the clinical patient encounter, the finalized sequence of medical billing codes including the retained at least one user-approved medical billing code and the second engine-derived medical billing code; and (h) training the NLU engine based on training data including the finalized sequence of medical billing codes for the clinical patient encounter, the training comprising providing the training data as input to one or more models associated with the automated language processing component. ### Claim 9 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same diagnosis code as the at least one user-approved medical billing code. ### Claim 10 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same procedure code as the at least one user-approved medical billing code, and that the patient did not undergo the same procedure twice. ### Claim 11 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a less specific version of the at least one user-approved medical billing code. ### Claim 12 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the act (e) comprises presenting the retained at least one user-approved medical billing code via the user interface, and suppressing presentation of the first engine-derived medical billing code. ### Claim 13 (depends on 8) The at least one computer-readable storage medium of claim 8, wherein the act (e) comprises in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, generating a link between the retained at least one user-approved medical billing code and the first portion of the free-form text corresponding to the first engine-derived medical billing code. ### Claim 14 (depends on 13) The at least one computer-readable storage medium of claim 13, wherein the method further comprises, in response to user selection of the retained at least one user- approved medical billing code via the user interface, providing an indicator of the linked first portion of the free-form text corresponding to the first engine-derived medical billing code. ### Claim 15 Apparatus comprising: at least one processor; and at least one storage medium storing processor-executable instructions that, when executed by the at least one processor, perform a method comprising: (a) outputting for presentation to one or more human users, via a user interface, a set of one or more medical billing codes derived from first documentation for a clinical patient encounter by a natural language understanding (NLU) engine, the NLU engine being an automated language processing component; (b) receiving user input, that was input via the user interface, to approve at least one of the one or more medical billing codes derived by the NLU engine, and/or to manually input one or more codes, resulting in a set of one or more user-approved medical billing codes for the patient encounter; (c) after the act (b), applying the NLU engine to a free-form text that relates to the clinical patient encounter and is not part of the first documentation documenting the clinical patient encounter, to derive a first engine-derived medical billing code for the clinical patient encounter and a first link between the engine-derived medical billing code and a corresponding first portion of the free-form text and a second engine-derived medical billing code for the clinical patient encounter and a second link between the second engine-derived medical billing code and a corresponding second portion of the free-form text; (d) automatically determining whether the first engine-derived medical billing code and the second engine-derived medical billing code overlap with at least one user-approved medical billing code of the set of user-approved medical billing codes; (e) in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the at least one user-approved medical billing code instead of the first engine-derived medical billing code; (f) in response to automatically determining that the second engine-derived medical billing code does not overlap with the at least one user-approved medical billing code of the set of user-approved medical billing codes, retaining the second engine-derived medical billing code; (g) generating a finalized sequence of medical billing codes for the clinical patient encounter, the finalized sequence of medical billing codes including the retained at least one user-approved medical billing code and the second engine-derived medical billing code; and (h) training the NLU engine based on training data including the finalized sequence of medical billing codes for the clinical patient encounter, the training comprising providing the training data as input to one or more models associated with the automated language processing component. ### Claim 16 (depends on 15) The apparatus of claim 15, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same diagnosis code as the at least one user-approved medical billing code. ### Claim 17 (depends on 15) The apparatus of claim 15, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a same procedure code as the at least one user-approved medical billing code, and that the patient did not undergo the same procedure twice. ### Claim 18 (depends on 15) The apparatus of claim 15, wherein the act (d) comprises determining whether the first engine-derived medical billing code or the second engine-derived medical billing code is a less specific version of the at least one user-approved medical billing code. ### Claim 19 (depends on 15) The apparatus of claim 15, wherein the act (e) comprises presenting the retained at least one user-approved medical billing code via the user interface, and suppressing presentation of the first engine-derived medical billing code. ### Claim 20 (depends on 15) The apparatus of claim 15, wherein the act (e) comprises in response to automatically determining that the first engine-derived medical billing code overlaps with the at least one user-approved medical billing code of the set of user-approved medical billing codes, generating a link between the retained at least one user-approved medical billing code and the first portion of the free-form text corresponding to the first engine-derived medical billing code.