# US 2018/0322110 A1 · Methods for improving natural language processing with enhanced automated screening for automated generation of a clinical summarization report and devices thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0322110 A1 - Document ID: US20180322110A1 - Status: Published application - Kind: A1 - Application number: 15/584,764 - Filed: 2017-05-02 - Published: 2018-11-08 - Earliest claimed: 2017-05-02 - Assignees: Ehealth Technologies - Applicants: eHealth Technologies - Inventors: Colin Rhodes; Chad Malone; Ken Rosenfeld - Web page: https://patentgrep.com/patent/US20180322110A1 ## CPC - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G06F 16/3344: {using natural language analysis} - G06F 40/186: Templates - G06F 40/258: Heading extraction; Automatic titling; Numbering - G06F 40/279: Recognition of textual entities - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods, non-transitory computer readable media, and devices that convert into a common electronic format a plurality electronic medical records retrieved in response to a request with identification data. A natural language processing algorithm is applied to obtain a subset of summarization data from each of the converted medical electronic record based on medical information data in the received request. The algorithm screens the initial subset of summarization data based on one or more factors to generate a reduced subset of summarization data for each of the converted medical electronic records. At least a portion of the reduced subset of summarization data is populated into data fields within one of a plurality of templates identified for each of the converted electronic medical records from the reduced subset of summarization data. A clinical summarization record is generated based on at least the populated summarization data in each of the identified ones of the plurality of templates. The clinical summarization record is provided in response to the received request. ## Claims ### Claim 1 A method for improving natural language processing with screening for automated generation of a clinical summarization report implemented by a clinical summary management computing system comprising one or more clinical summary management computing apparatuses, client devices, or server devices, the method comprising: converting into a common electronic format a plurality of different types of electronic medical records retrieved in response to a received request with patient identification data; applying a natural language processing algorithm to obtain a subset of summarization data from each of the converted medical electronic record based on medical information data in the received request, wherein the natural language processing algorithm improves utilization of one or more computing resources including memory and/or one or more processing cycles by screening the initial subset of summarization data based on one or more stored factors to generate a reduced subset of summarization data for each of the converted medical electronic records; populating at least a portion of the reduced subset of summarization data into a plurality of data fields within one of a plurality of templates identified for each of the converted electronic medical records from the reduced subset of summarization data for each of the converted medical electronic records; generating a clinical summarization record based on the at least a portion of the reduced subset of summarization data populated in the identified ones of the plurality of templates; and providing the clinical summarization record in response to the received request. ### Claim 2 (depends on 1) The method as set forth in claim 1 wherein the one or more factors comprise frequency of a term, concurrence of terms, and stored weight of a term in the subset of data, wherein the natural language processing algorithm removes one or more terms from the subset of data which occur at a rate below a stored threshold frequency, adds one or more terms from the subset of data with an identified concurrence based on a stored concurrence relationship, and removes one or more terms from the subset of data with a stored weight below a stored threshold weight. ### Claim 3 (depends on 1) The method as set forth in claim 1 further comprising separating the converted electronic medical records data based on type of visit data into one or more sections and organizing the converted electronic medical records in each of the one or more sections based on the recorded visit date data obtained from each of the converted electronic medical records. ### Claim 4 (depends on 3) The method as set forth in claim 3 further comprising: generating an overall indexed document of the retrieved electronic medical records based on the one or more sections with the generated clinical summarization with one or more hyperlinks from at least a portion of the reduced subset of summarization data in the generated clinical summarization to a corresponding source of the at least a portion of the reduced subset of summarization data in the overall indexed document; and providing the generated overall indexed document in a response to the received request. ### Claim 5 (depends on 4) The method of claim 4, wherein the generating the overall indexed document further comprises organizing each of the retrieved one or more electronic medical records within each of the one or more sections in reverse chronological order. ### Claim 6 (depends on 1) The method of claim 1, wherein the one or more factors for the identifying one of a plurality of templates for each of the converted electronic medical records comprise an institution associated with the received request, a department associated with the received request, one or more diagnosis codes associated with the retrieved request or in the converted electronic medical record, or a disease type identified in the converted electronic medical records. ### Claim 7 (depends on 1) The method of claim 1, wherein the generating a clinical summarization record further comprises generating at least two different types of summaries comprising a combined extractive and indicative summarization and an abstract clinical summarization. ### Claim 8 An electronic medical records computing apparatus, comprising memory comprising programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to: convert into a common electronic format a plurality of different types of electronic medical records retrieved in response to a received request with patient identification data; apply a natural language processing algorithm to obtain a subset of summarization data from each of the converted medical electronic record based on medical information data in the received request, wherein the natural language processing algorithm improves utilization of one or more computing resources including memory and/or one or more processing cycles by screening the initial subset of summarization data based on one or more stored factors to generate a reduced subset of summarization data for each of the converted medical electronic records; populate at least a portion of the reduced subset of summarization data into a plurality of data fields within one of a plurality of templates identified for each of the converted electronic medical records from the reduced subset of summarization data for each of the converted medical electronic records; generate a clinical summarization record based on the at least a portion of the reduced subset of summarization data populated in the identified ones of the plurality of templates; and provide the clinical summarization record in response to the received request. ### Claim 9 (depends on 8) The apparatus as set forth in claim 8 wherein the one or more factors comprise frequency of a term, concurrence of terms, and stored weight of a term in the subset of data, wherein the natural language processing algorithm removes one or more terms from the subset of data which occur at a rate below a stored threshold frequency, adds one or more terms from the subset of data with an identified concurrence based on a stored concurrence relationship, and removes one or more terms from the subset of data with a stored weight below a stored threshold weight. ### Claim 10 (depends on 8) The apparatus as set forth in claim 8 wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to separate the converted electronic medical records data based on type of visit data into one or more sections and organizing the converted electronic medical records in each of the one or more sections based on the recorded visit date data obtained from each of the converted electronic medical records. ### Claim 11 (depends on 10) The apparatus as set forth in claim 10 wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to: generate an overall indexed document of the retrieved electronic medical records based on the one or more sections with the generated clinical summarization with one or more hyperlinks from at least a portion of the reduced subset of summarization data in the generated clinical summarization to a corresponding source of the at least a portion of the reduced subset of summarization data in the overall indexed document; and provide the generated overall indexed document in a response to the received request. ### Claim 12 (depends on 11) The apparatus of claim 11, wherein the generate the overall indexed document further comprises organizing each of the retrieved one or more electronic medical records within each of the one or more sections in reverse chronological order. ### Claim 13 (depends on 8) The apparatus of claim 8, wherein the one or more factors for the identifying one of a plurality of templates for each of the converted electronic medical records comprise an institution associated with the received request, a department associated with the received request, one or more diagnosis codes associated with the retrieved request or in the converted electronic medical record, or a disease type identified in the converted electronic medical records. ### Claim 14 (depends on 8) The apparatus of claim 8, wherein the generate a clinical summarization record further comprises generate at least two different types of summaries comprising a combined extractive and indicative summarization and an abstract clinical summarization. ### Claim 15 A non-transitory computer readable medium having stored thereon instructions improving natural language processing with enhanced automated screening for automated generation of a clinical summarization report comprising executable code which when executed by one or more processors, causes the one or more processors to: convert into a common electronic format a plurality of different types of electronic medical records retrieved in response to a received request with patient identification data; apply a natural language processing algorithm to obtain a subset of summarization data from each of the converted medical electronic record based on medical information data in the received request, wherein the natural language processing algorithm improves utilization of one or more computing resources including memory and/or one or more processing cycles by screening the initial subset of summarization data based on one or more stored factors to generate a reduced subset of summarization data for each of the converted medical electronic records; populate at least a portion of the reduced subset of summarization data into a plurality of data fields within one of a plurality of templates identified for each of the converted electronic medical records from the reduced subset of summarization data for each of the converted medical electronic records; generate a clinical summarization record based on the at least a portion of the reduced subset of summarization data populated in the identified ones of the plurality of templates; and provide the clinical summarization record in response to the received request. ### Claim 16 (depends on 15) The medium as set forth in claim 15 wherein the one or more factors comprise frequency of a term, concurrence of terms, and stored weight of a term in the subset of data, wherein the natural language processing algorithm removes one or more terms from the subset of data which occur at a rate below a stored threshold frequency, adds one or more terms from the subset of data with an identified concurrence based on a stored concurrence relationship, and removes one or more terms from the subset of data with a stored weight below a stored threshold weight. ### Claim 17 (depends on 15) The medium as set forth in claim 15 wherein the executable code when executed by the one or more processors further causes the one or more processors to: separate the converted electronic medical records data based on type of visit data into one or more sections and organizing the converted electronic medical records in each of the one or more sections based on the recorded visit date data obtained from each of the converted electronic medical records. ### Claim 18 (depends on 17) The medium as set forth in claim 17 wherein the executable code when executed by the one or more processors further causes the one or more processors to: generate an overall indexed document of the retrieved electronic medical records based on the one or more sections with the generated clinical summarization with one or more hyperlinks from at least a portion of the reduced subset of summarization data in the generated clinical summarization to a corresponding source of the at least a portion of the reduced subset of summarization data in the overall indexed document; and provide the generated overall indexed document in a response to the received request. ### Claim 19 (depends on 18) The medium of claim 18, wherein the generate the overall indexed document further comprises organizing each of the retrieved one or more electronic medical records within each of the one or more sections in reverse chronological order. ### Claim 20 (depends on 15) The medium of claim 15, wherein the one or more factors for the identifying one of a plurality of templates for each of the converted electronic medical records comprise an institution associated with the received request, a department associated with the received request, one or more diagnosis codes associated with the retrieved request or in the converted electronic medical record, or a disease type identified in the converted electronic medical records. ### Claim 21 (depends on 11) The medium of claim 11, wherein the generate a clinical summarization record further comprises generate at least two different types of summaries comprising a combined extractive and indicative summarization and an abstract clinical summarization.