US20140316772A1 - Verification of Extracted Data - Google Patents

Verification of Extracted Data Download PDF

Info

Publication number
US20140316772A1
US20140316772A1 US14317323 US201414317323A US2014316772A1 US 20140316772 A1 US20140316772 A1 US 20140316772A1 US 14317323 US14317323 US 14317323 US 201414317323 A US201414317323 A US 201414317323A US 2014316772 A1 US2014316772 A1 US 2014316772A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
coding
text
rendering
example
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US14317323
Inventor
Detlef Koll
Michael Finke
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MModal IP LLC
Original Assignee
MModal IP LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Family has litigation

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/20Handling natural language data
    • G06F17/21Text processing
    • G06F17/211Formatting, i.e. changing of presentation of document
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/20Handling natural language data
    • G06F17/27Automatic analysis, e.g. parsing
    • G06F17/2785Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F19/00Digital computing or data processing equipment or methods, specially adapted for specific applications
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/22Social work
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/22Social work
    • G06Q50/24Patient record management
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/02Feature extraction for speech recognition; Selection of recognition unit
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

Facts are extracted from speech and recorded in a document using codings. Each coding represents an extracted fact and includes a code and a datum. The code may represent a type of the extracted fact and the datum may represent a value of the extracted fact. The datum in a coding is rendered based on a specified feature of the coding. For example, the datum may be rendered as boldface text to indicate that the coding has been designated as an “allergy.” In this way, the specified feature of the coding (e.g., “allergy”-ness) is used to modify the manner in which the datum is rendered. A user inspects the rendering and provides, based on the rendering, an indication of whether the coding was accurately designated as having the specified feature. A record of the user's indication may be stored, such as within the coding itself.

Description

    BACKGROUND
  • It is desirable in many contexts to generate a structured textual document based on human speech. In the legal profession, for example, transcriptionists transcribe testimony given in court proceedings and in depositions to produce a written transcript of the testimony. Similarly, in the medical profession, transcripts are produced of diagnoses, prognoses, prescriptions, and other information dictated by doctors and other medical professionals. Transcripts in these and other fields typically need to be highly accurate (as measured in terms of the degree of correspondence between the semantic content (meaning) of the original speech and the semantic content of the resulting transcript) because of the reliance placed on the resulting transcripts and the harm that could result from an inaccuracy (such as providing an incorrect prescription drug to a patient).
  • It may be difficult to produce an initial transcript that is highly accurate for a variety of reasons, such as variations in: (1) features of the speakers whose speech is transcribed (e.g., accent, volume, dialect, speed); (2) external conditions (e.g., background noise); (3) the transcriptionist or transcription system (e.g., imperfect hearing or audio capture capabilities, imperfect understanding of language); or (4) the recording/transmission medium (e.g., paper, analog audio tape, analog telephone network, compression algorithms applied in digital telephone networks, and noises/artifacts due to cell phone channels).
  • The first draft of a transcript, whether produced by a human transcriptionist or an automated speech recognition system, may therefore include a variety of errors. Typically it is necessary to proofread and edit such draft documents to correct the errors contained therein. Transcription errors that need correction may include, for example, any of the following: missing words or word sequences; excessive wording; mis-spelled, -typed, or -recognized words; missing or excessive punctuation; and incorrect document structure (such as incorrect, missing, or redundant sections, enumerations, paragraphs, or lists).
  • In some circumstances, however, a verbatim transcript is not desired. In fact, transcriptionists may intentionally introduce a variety of changes into the written transcription. A transcriptionist may, for example, filter out spontaneous speech effects (e.g., pause fillers, hesitations, and false starts), discard irrelevant remarks and comments, convert data into a standard format, insert headings or other explanatory materials, or change the sequence of the speech to fit the structure of a written report.
  • Furthermore, formatting requirements may make it necessary to edit even phrases that have been transcribed correctly so that such phrases comply with the formatting requirements. For example, abbreviations and acronyms may need to be fully spelled out. This is one example of a kind of “editing pattern” that may need to be applied even in the absence of a transcription error.
  • Such error correction and other editing is often performed by human proofreaders and can be tedious, time-consuming, costly, and itself error-prone. In some cases, attempts are made to detect and correct errors using automatically-generated statistical measures of the uncertainty of the draft-generation process. For example, both natural language processors (NLPs) and automatic speech recognizers (ASRs) produce such “confidence measures.” These confidence measures, however, are often unreliable, thereby limiting the usefulness of the error detection and correction techniques that rely on them.
  • Furthermore, it may be desirable for a report or other structured document to include not only text but data. In such a case the goal is not merely to capture spoken words as text, but also to extract data from those words, and to include the data in the report. The data, although included in the report, may or may not be explicitly displayed to the user when the document is rendered. Even if not displayed to the user, the computer-readable nature of the data makes it useful for various kinds of processing which would be difficult or impossible to perform on bare text.
  • Consider, for example, a draft report generated from the free-form speech of a doctor. Such a draft report may include both: (1) a textual transcript of the doctor's speech, and (2) codes (also referred to as “tags” or “annotations”) that annotate the transcribed speech. Such codes may, for example, take the form of XML tags.
  • The doctor's speech may be “free-form” in the sense that the structure of the speech may not match the desired structure of the written report. When dictating, doctors (and other speakers) typically only hint at or imply the structure of the final report. Such “structure” includes, for example, the report's sections, paragraphs, and enumerations. Although an automated system may attempt to identify the document structured implied by the speech, and to create a report having that structure, such a process is error prone. The system may, for example, put the text corresponding to particular speech in the wrong section of the report.
  • Similarly, the system may incorrectly classify such text as describing an allergy rather than as text corresponding to some other kind of data. Such an error would be reflected in the document by an incorrect coding being applied to the text. Consider, for example, the sentence fragment “penicillin causes hives.” This text may be coded incorrectly by, for example, coding the text “penicillin” as a current medication rather than as an allergen.
  • When data are extracted from speech, it is desirable that such data be coded accurately. Some existing systems which extract data from speech to produce structured documents, however, do not provide a mechanism for the accuracy of the extracted data to be human-verified, thereby limiting the confidence with which the accuracy of such documents may be relied upon.
  • Some systems allow the accuracy of extracted data to be verified, but only do so as a separate work step after the textual content of the document has been verified for speech recognition errors. This data verification process involves displaying the extracted codes themselves, which makes the verification process difficult due to the complexities of the coding systems, such as the Controlled Medical Vocabulary (CMV) coding system, that are commonly used to encode data in documents. Such existing techniques for verifying extracted data are therefore of limited utility.
  • What is needed, therefore, are improved techniques for verifying the correctness of data extracted from speech into documents.
  • SUMMARY
  • Facts are extracted from speech and recorded in a document using codings. Each coding represents an extracted fact and includes a code and a datum. The code may represent a type of the extracted fact and the datum may represent a value of the extracted fact. The datum in a coding is rendered based on a specified feature of the coding. For example, the datum may be rendered as boldface text to indicate that the coding has been designated as an “allergy.” In this way, the specified feature of the coding (e.g., “allergy”-ness) is used to modify the manner in which the datum is rendered. A user inspects the rendering and provides, based on the rendering, an indication of whether the coding was accurately designated as having the specified feature. A record of the user's indication may be stored, such as within the coding itself.
  • For example, one embodiment of the present invention is a computer-implemented method comprising: (A) identifying a document including a first coding having a first feature, the first coding being associated with a first code, the first code having first data; (B) rendering the first data based on the first feature; (C) identifying a first indication by a user of a verification status of the rendering; and (D) identifying, based on the verification status of the rendering, a verification status of the first feature, comprising: (D)(1) if the verification status of the rendering indicates that the rendering is accurate, then identifying a verification status of the first feature indicating that the first feature is accurate; (D)(2) otherwise, identifying a verification status of the first feature indicating that the first feature is inaccurate; and (E) identifying, based on the verification status of the first feature, a verification status of the first coding.
  • Another embodiment of the present invention is an apparatus comprising: document identification means for identifying a document including a first coding having a first feature, the first coding being associated with a first code, the first code having first data; rendering means for rendering the first data based on the first feature; user indication means for identifying a first indication by a user of a verification status of the rendering; and first feature verification status identification means for identifying, based on the verification status of the rendering, a verification status of the first feature, the first feature verification status identification means comprising: means for identifying a verification status of the first feature indicating that the first feature is accurate if the verification status of the rendering indicates that the rendering is accurate; and means for identifying a verification status of the first feature indicating that the first feature is inaccurate otherwise. The apparatus may further include first coding verification status identification means for identifying, based on the verification status of the first feature, a verification status of the first coding.
  • Another embodiment of the present invention is a computer-implemented method comprising: (A) identifying a document including a first coding, the first coding being associated with a first code and a second code, the first code having first data; (B) rendering the first data based on the second code; (C) identifying a first indication by a user of a verification status of the rendering; and (D) identifying, based on the verification status of the rendering, a verification status of the second code, comprising: (D)(1) if the verification status of the rendering indicates that the rendering is accurate, then identifying a verification status of the second code indicating that the second code is accurate; and (D)(2) otherwise, identifying a verification status of the second code indicating that the second code is inaccurate.
  • Another embodiment of the present invention is a computer-implemented method comprising: (A) identifying a document including a first coding having a first feature and a second coding, the first coding being associated with a first code and a first verification status record indicating a first verification status of the first coding, the second coding being associated with a second code and a second verification status record indicating a second verification status of the second coding; (B) rendering the first data based on the first feature to produce a first rendering of the first data; (C) identifying a first indication by a user of a modification to the first verification status of the first coding; and (D) modifying the first verification status record to reflect the first indication by the user, whereby the modified first verification status differs from the second verification status.
  • Another embodiment of the present invention is an apparatus comprising: document identification means for identifying a document including a first coding having a first feature and a second coding, the first coding being associated with a first code and a first verification status record indicating a first verification status of the first coding, the second coding being associated with a second code and a second verification status record indicating a second verification status of the second coding; rendering means for rendering the first data based on the first feature to produce a first rendering of the first data; user indication means for identifying a first indication by a user of a modification to the first verification status of the first coding; and record modification means for modifying the first verification status record to reflect the first indication by the user, whereby the modified first verification status differs from the second verification status.
  • Other features and advantages of various aspects and embodiments of the present invention will become apparent from the following description and from the claims.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 is a dataflow diagram of a system for verifying data extracted from speech according to one embodiment of the present invention;
  • FIG. 2 is a flowchart of a method performed by the system of FIG. 1 according to one embodiment of the present invention;
  • FIG. 3A illustrates a first rendering of a transcript according to one embodiment of the present invention;
  • FIG. 3B illustrates a second rendering of the same transcript rendered in FIG. 3A according to one embodiment of the present invention;
  • FIG. 4A illustrates text representing words spoken in the spoken audio stream of FIG. 1 according to one embodiment of the present invention;
  • FIG. 4B illustrates a rendering of a transcription of the spoken audio stream of FIG. 1 according to one embodiment of the present invention;
  • FIG. 4C illustrates a structured XML document representing the transcription rendered in FIG. 4B according to one embodiment of the present invention; and
  • FIG. 5 is a diagram of one of the codings of FIG. 1 in more detail according to one embodiment of the present invention.
  • DETAILED DESCRIPTION
  • Referring to FIG. 1, a dataflow diagram is shown of a system 100 for verifying codings of data extracted from speech according to one embodiment of the present invention. Referring to FIG. 2, a flowchart is shown of a method 200 performed by the system 100 of FIG. 1 according to one embodiment of the present invention.
  • A transcription system 104 transcribes a spoken audio stream 102 to produce a draft transcript 106 (step 202). The spoken audio stream 102 may, for example, be dictation by a doctor describing a patient visit. The spoken audio stream 102 may take any form. For example, it may be a live audio stream received directly or indirectly (such as over a telephone or IP connection), or an audio stream recorded on any medium and in any format.
  • The transcription system 104 may produce the draft transcript 106 using, for example, an automated speech recognizer or a combination of an automated speech recognizer and human transcriptionist. The transcription system 104 may, for example, produce the draft transcript 106 using any of the techniques disclosed in the above-referenced patent application entitled “Automated Extraction of Semantic Content and Generation of a Structured Document from Speech.” As described therein, the draft transcript 106 may include text 116 that is either a literal (verbatim) transcript or a non-literal transcript of the spoken audio stream 102. As further described therein, although the draft transcript 106 may be a plain text document, the draft transcript 106 may also, for example, in whole or in part be a structured document, such as an XML document which delineates document sections and other kinds of document structure. Various standards exist for encoding structured documents, and for annotating parts of the structured text with discrete facts (data) that are in some way related to the structured text. Examples of existing techniques for encoding medical documents include the HL7 CDA v2 XML standard (ANSI-approved since May 2005), SNOMED CT, LOINC, CPT, ICD-9 and ICD-10, and UMLS.
  • As shown in FIG. 1, the draft transcript 106 includes one or more codings 108, each of which encodes a “concept” extracted from the spoken audio stream 102. The term “concept” is used herein as defined in the above-referenced patent application entitled “Automated Extraction of Semantic content and Generation of a Structured Document from Speech.” Reference numeral 108 is used herein to refer generally to all of the codings within the draft transcript 106. Although in FIG. 1 only two codings, designated 108 a and 108 b, are shown, the draft transcript 106 may include any number of codings.
  • In the context of a medical report, each of the codings 108 may, for example, encode an allergy, prescription, diagnosis, or prognosis. In general, each of the codings 108 includes a code and corresponding data. For example, coding 108 a includes code 110 a and corresponding data 112 a. Similarly, coding 108 b includes code 110 b and corresponding data 112 b.
  • The code 110 a may, for example, indicate the type of coding (such as whether the coding 108 a represents an allergy rather than a prescription), while the data 112 a may represent the value of the coding 108 a (such as “penicillin” for an “allergy” type coding). Examples of techniques which may be used to generate the codings 108 from speech may be found in the above-referenced patent application entitled “Automated Extraction of Semantic content and Generation of a Structured Document from Speech.”
  • For purposes of the following discussion, an example will be used in which the spoken audio stream 102 represents dictation by a doctor of a patient visit for a patient who reports two allergies. Referring to FIG. 4A, text 400 is shown representing the exact words spoken in the audio stream 102 in this example. As shown in FIG. 4A, the doctor has stated in the spoken audio stream 102 that the patient has an allergy to Penicillin and had a prior allergic reaction to peanut butter.
  • Referring to FIG. 4B, a rendering 410 of a transcription of the spoken audio stream 102 is shown. The rendering 410 may, for example, be a rendering of the draft transcript 106. In FIG. 4B, the rendering 410 appears as a formatted report including a section heading 412 (“Allergies”) derived from the words “new paragraph allergies colon” in the speech 400; a first allergy description 414 derived from the words “the patient has an allergy to Penicillin that causes hives” in the speech 400; and a second allergy description 416 derived from the words “the patient also reports prior allergic reaction to peanut butter” in the speech 400.
  • Referring to FIG. 4C, a structured document 420 in XML is shown representing the transcription that produced the rendering 410 in FIG. 4B. The structured document 420 will be used herein for purposes of explanation as an example of the draft transcript 106.
  • Returning to the codings 108 in FIG. 1, the coding 108 a may, for example, represent the patient's allergy to Penicillin that causes hives. The coding 108 a may, for example, be implemented as the XML element 422 a shown in FIG. 4C. Within the coding 108 a, the code 110 a may be implemented as XML element 424 a, the data 112 a may be implemented as XML element 426 a, and a link 114 a to the corresponding linked text 118 a may be implemented as XML element 428 a.
  • Similarly, the coding 108 b may represent the patient's prior allergenic reaction to peanut butter, implemented as the XML element 422 b shown in FIG. 4C. Within the coding 108 b, the code 110 b may be implemented as XML element 424 b, the data 112 b may be implemented as XML element 426 b, and a link 114 b to the corresponding linked text 118 b may be implemented as XML element 428 b.
  • When the transcription system 104 identifies text representing data to be encoded without the aid of a human and creates a coding as a result, the transcription system 104 may tag the coding as “automatically derived.” For example, the coding 108 a may include a derivation type field 502 a, as shown in FIG. 5, which illustrates the coding 108 a in more detail according to one embodiment of the present invention. In one embodiment, the derivation type field 502 a has permissible values of “manually derived” and “automatically derived.” If the coding 108 a is created without the aid of a human, the value of the derivation type field 502 a may be set to “automatically derived.”
  • In the example shown in FIG. 1, the codings 108 a-b include links 114 a-b pointing to the text 118 a-b corresponding to the codings 108 a-b. The degree of correspondence between the codings 108 and particular text in the draft transcript 106 may vary, however, and the draft transcript 106 may or may not include an express indication (e.g., links 114 a-b) of the correspondence between the codings 108 and particular text in the draft transcript 106. Consider again the example of FIGS. 4A-4C, in which the draft transcript 106 describes an allergy to Penicillin that causes hives, and in which the coding 108 a was derived from the text “the patient has an allergy to Penicillin that causes hives” in the draft transcript 106. In this example, there is a direct correlation between the coding 108 a and the corresponding text. Such a correlation may be indicated in the coding 108 a itself. For example, the coding 108 a may include an XML element 428 a which links to the corresponding text.
  • The data 112 a in the coding 108 a may, however, be implied by or otherwise derived more indirectly from text 116 in the draft transcript 106. For example, the coding 108 a may encode an alternative to Penicillin for use in treatment, even though the alternative is not expressly recited in the text of the draft transcript 106. Furthermore, the data 112 a in the coding 108 a may represent information that does not have any correspondence with the text in the draft transcript 106 or the spoken audio stream 102 from which the draft transcript 106 was derived.
  • As a result, even if the coding 108 a includes link 114 a, such a link does not necessarily indicate semantic equivalence of the linked text 118 a with the data 112 a, but rather represents an informal notion of correspondence of the data 112 a to some of the evidence that led to their extraction. For example, the coded data 112 a could represent a general category of the corresponding text (e.g., the text “allergic to Penicillin” could be annotated with the code for drug allergy), or could contain additional information that was derived from the context of the corresponding text without explicitly linking to such context. For example, in a “Physical Examination” section of a medical report, the text “temperature 37.2 C” could be coded as a current body temperature measurement of the patient. Note that the context of the text, i.e., the fact that it occurs in a “Physical Examination” section, contains content that is required for the correct interpretation, without being explicitly referenced in the text/fact correspondence.
  • At this stage of the report generation process, both the textual content of the draft transcript 106 and the codings 108 a-b are unreliable. In a conventional speech recognition-supported transcription workflow, a human editor (such as a medical language specialist or a dictating physician) would review the draft transcript 106 and correct errors in the text 116. Embodiments of the present invention further enable errors in the codings 108 to be corrected. Examples of techniques will now be described which allow the accuracy of both the codings 108 and the text 116 to be verified using an integrated review process.
  • Terms such as the “accuracy” or “correctness” of a coding refer generally herein to the degree of semantic equivalence between the coding and its associated text. For example, coding 108 a may be said to be “accurate” or “correct” if the code 110 a and data 112 a in the coding 108 a correspond to the content of the linked text 118 a. For example, the coding 108 a is accurate if the code 110 is an “allergy” or “allergen” code and the data represents an allergic reaction to Penicillin, because the corresponding linked text 118 a states that “the patient has an allergy to Penicillin.” In particular applications, correctness of the coding 108 a may not require that both the code 110 a and the data 112 a be correct. For example, in particular applications the coding 108 a may be considered accurate if the code 110 a is correct, and without reference to the data 112 a.
  • More generally, a coding's correctness/accuracy may be determined by reference to a “feature” of the coding. For example, Penicillin may be encoded as a substance using a “substance” coding having a code of “<substance>” and a datum of “Penicillin.” This Penicillin coding may further be encoded as an allergen using an “allergen” coding having a code of “<allergen>” and having the Penicillin coding as a datum. In XML, such an XML coding may be represented as “<allergen><substance>Penicillin</substance></allergen>.” In this simplified example, the fact that the Penicillin coding has been further encoded as an allergen is a “feature” of the Penicillin coding, as the term “feature” is used herein. If the corresponding text (e.g., “the patient has an allergy to Penicillin”) describes Penicillin as an allergen, then the “allergen-ness” feature of the allergen coding is said to be “correct” or “accurate.” Examples of techniques will be described below for verifying such features of codings, i.e., determining whether such features are accurate.
  • Although in the example just described, a coding has a “feature” by virtue of being included within another coding, this is not a limitation of the present invention. Rather, features may be represented in documents in other ways. As another example, a Penicillin coding may have the feature of representing an allergen using a representation having the form of “Penicillin is A allergen,” where “Penicillin,” “is A,” and “allergen” are each represented by a corresponding coding or other data structure. In this example, the Penicillin coding has the feature of representing an allergen even though the allergen coding does not contain the Penicillin coding, i.e., even though the allergen coding and the Penicillin coding are disjoint.
  • A feature of a coding, therefore, may be a relationship between the coding and another coding, such as an “is A” relationship, an “isGeneralizationOf” relationship, or an “overlaps” relationship. As in the case of features, a relationship may be said to be “correct” or “accurate” if the corresponding text describes the relationship.
  • The accuracy of the codings 108 may, for example, be verified as follows. Returning to FIGS. 1 and 2, a feature selector 138 selects a feature 140 to be verified (step 204). For example, the feature 140 may be “allergy-ness,” i.e., whether the codings 108 a-b encode an allergy. The method 200 may identify the feature 140 to be verified in any of a variety of ways. For example, the user 130 may specify the feature 140 before commencement of the method 200. Alternatively, for example, the feature 140 may be specified by a system administrator or other person at the time of installation or initial configuration of the system 100. In this case, the user 130 would not need to (and might be prohibited from) specify the feature 140 to be verified. Furthermore, although the method 200 shown in FIG. 2 only verifies one feature 140, multiple features may be verified sequentially or in parallel.
  • The method 200 uses a renderer 124 to produce a rendering 126 of the draft transcript 106. The rendering 126 includes renderings 128 a-b of the codings 108 a-b, respectively.
  • More specifically, the renderer 124 enters a loop over each coding C in the draft transcript 106 (step 206). Assume for the remainder of the discussion that the method 200 operates on the first coding 108 a.
  • The system 100 includes a visual characteristic selector 120 which selects a visual characteristic 122 a based on a determination of whether the coding 108 a has the feature 140 identified in step 204 (step 206). Examples of visual characteristics, and techniques that may be used to select a visual characteristic based on the coding 108 a, will be provided below. In general, however, the visual characteristic 122 a may be selected as any visual characteristic which provides a visual indication of whether the coding 108 a has the identified feature 140 without displaying the code 110 a from the coding 108 a.
  • The renderer 124 renders the coding 108 a to produce a rendering 128 a of the coding 108 a within the rendering 126 of the transcript 106 (step 210). The renderer 124 renders the coding 108 a based on the selected visual characteristic 122 a such that the coding rendering 128 a has the selected visual characteristic 122 a. Rendering the coding 108 a may include rendering the corresponding linked text 118 a and/or any combination of the elements of the coding 108 a.
  • The visual characteristic 122 a should be selected such that it clearly indicates its meaning to the user 130. For example, if the visual characteristic 122 a is boldfacing of text, then the renderer 124 should be configured to boldface only that text which represents codings having the selected feature 140. Otherwise, it would not be clear to the user 130 whether any particular instance of boldface text in the rendering 126 was boldfaced to indicate a coding having the selected feature 140, or to represent emphasis or for some other reason. Boldfacing, however, is only one example of a way in which the visual characteristic 122 a may be selected to provide the user 130 with an unambiguous indication of whether the corresponding portion of the rendering represents a coding having the selected feature 140.
  • The method 200 repeats steps 208-210 for the remaining codings in the transcript 106 (step 212), thereby selecting visual characteristics 122 a-b and producing coding renderings 128 a-b corresponding to all of the codings 108 a-b in the transcript 106.
  • Examples of techniques for selecting visual characteristics 122 a-b (step 206) and for rendering the codings 108 a-b based on the visual characteristics 122 a-b (step 210) will now be described. Referring to FIG. 3A, an example rendering 300 is shown of the example transcript 420 of FIG. 4C, which in turn is an example of the draft transcript 106.
  • In the rendering 300 shown in FIG. 3A, the two codings 108 a-b are rendered in a table format. The table includes five columns 302 a-e for purposes of example: column 302 a for allergy type, column 302 b for allergen, column 302 c for allergic reaction, column 302 d for the corresponding (linked) text, and column 302 e for use by a user 130 to indicate whether the codings underlying the rendering 300 are correct. The table includes two rows 304 a-b: one row 304 a for the first coding 108 a (representing the Penicillin allergy) and one row 304 b for the second coding 108 b (representing the peanut butter allergy).
  • In this example, the feature 140 is an “allergy” feature, and the renderer 124 only renders a coding in the table 300 in the table 300 if the coding encodes an allergy, i.e., if the coding has the “allergy” feature 140. In the particular example shown in FIGS. 1-3B, both of the codings 108 a-b represent allergies, and as a result the renderer 124 has included renderings 304 a-b of both of the codings 108 a-b. If, however, one of the codings 108 a-b did not represent an allergy, then the renderer 124 would not provide a rendering of that coding in the table 300.
  • Therefore, for the example illustrated in FIG. 3A, the visual characteristic selector 120 (FIG. 1) operates as follows. If the visual characteristic selector 120 encounters a coding having the selected feature 140, then the visual characteristic selector 120 specifies that the coding is to be rendered by the renderer 124 using the format of the rows 304 a-b shown in FIG. 3A. For example, in the case of coding 108 a, the visual characteristic selector 120 specifies that the coding 108 is to be rendered using a label (“Drug”) in the “Allergy Type” column 302 a. Note that this label (“Drug”) is not the same as the text of the code 110 a in the coding 108 a itself, as evidenced by the text of XML element 424 a (FIG. 4C) representing the code 110 a in this example. As a result, the coding 108 a representing the Penicillin allergy is rendered in step 210 by displaying the contents of the row 304 a, without displaying the code 110 a (e.g., XML element 424 a) itself. Note that the rendering 300 shown in FIG. 3A may be rendered within a rendering of the text 116 of the transcript 116.
  • If the visual characteristic selector 120 encounters a coding that does not have the selected feature 140, then the visual characteristic selector 120 specifies that the coding is not to be rendered by the renderer 124.
  • Referring to FIG. 3B, another example of a rendering 310 of the same two codings 108 a-b is shown. In the rendering 310 shown in FIG. 3B, the two codings 108 a-b are rendered using formatted text. The text includes a heading 312 (“Adverse Reactions”) which indicates the beginning of a section describing adverse reactions of the patient who is the subject of the transcript 106. The heading 312 may be part of the text 116 within the draft transcript 106. The heading 312 may be a transcription of speech in the spoken audio stream 102. The heading 312 may, however, be created by the transcription system 104 in response to detecting text corresponding to adverse reactions.
  • The rendering 310 also includes a rendering 314 of the source text from which the two codings 108 a-b were derived. Text representing allergens of positive allergic reactions are rendered in boldface in the rendering 314. In this example, therefore, boldface and non-boldface are examples of visual characteristics selected by the visual characteristic selector 120 based on whether the codings 108 a-b have the selected feature 140. More specifically, the rendering 314 includes a rendering 316 of the first coding 108 a (which represents the Penicillin allergy). The rendering 316 displays the linked text 118 a, in which the word “penicillin” has been rendered as boldfaced text 318, thereby indicating that the corresponding coding 108 a has been encoded as an allergy. This is an example of modifying the rendering of the linked text 118 a (i.e., “penicillin”) based on whether the coding 108 a has the selected feature 140.
  • Note again that the resulting rendering 318 of the text “penicillin” does not include the code 110 a (e.g., XML element 424 a) itself. As a result, the coding 108 a representing the Penicillin allergy is rendered in step 210 by displaying the boldfaced text “Penicillin” and without displaying the code 110 a itself. The same is true of the rendering 322 of the text “peanut butter” within the rendering 320 of the linked text 118 b, with respect to its corresponding code 110 b.
  • Once the transcript 106 has been rendered, the rendering 300 or 310 may be used to verify the correctness of features of one or more of the codings 108 a-b, and/or to verify one or more of the codings 108 a-b in their entireties. For example, a user 130 may provide one or more indications of a verification status of one or more of the renderings 128 of the codings 108 to a verification subsystem 132 (FIG. 2, step 214).
  • The user 130 may provide this indication in any of a variety of ways. The user 130 may, for example, provide explicit input 134 to the verification subsystem 132 indicating the verification status of the rendering 128 a of coding 108 a. The verification subsystem 132 may, for example, prompt the user 130 to indicate whether the rendering of each of the codings 108 a-b is correct. Such a prompt may be provided, for example, by displaying the rendering 128 a of the coding 108 a and simultaneously displaying the corresponding linked text 118 a, and/or simultaneously playing back the portion of the spoken audio stream 102 from which the linked text 118 a was derived. The user 130 may use these cues to determine whether the coding 108 a accurately encodes the corresponding linked text 118 a and/or spoken audio.
  • The user 130 may provide the verification input 134 in any of a variety of ways, such as by pressing a key on a keyboard or pressing a button in a graphical user interface. Certain input values (such as “Y”) may indicate that the user 130 considers the rendering 128 a of coding 108 a is correct, while other input values (such as “N”) may indicate that the rendering 128 a of coding 108 a is incorrect. Each such input value may indicate a different “verification status” of the rendering 128 a.
  • With respect to the example rendering 300 shown in FIG. 3A, checkboxes 302 e may be displayed within the rows 304 a-b. In such an example, the user 130 may provide the verification input 134 for each of the renderings 128 a-b by checking the corresponding checkbox to indicate a verification status of “correct” (i.e., “verified”) or leaving the checkbox unchecked to indicate a verification status of “incorrect.”
  • With respect to the example rendering 310 shown in FIG. 3B, the user 130 may be instructed to verify that: (1) all text describing allergic reactions is to be included in the “Adverse Reactions” section; (2) all text describing allergens of positive allergic reactions are to be boldfaced; and (3) no other text in the “adverse reactions” section is to be bold-faced (e.g., especially not negative findings like “not allergic to peanut butter”).
  • In this example, the user 130 may then provide the verification input 134 by leaving boldfaced text as boldfaced or by leaving non-boldfaced text as non-boldfaced (thereby verifying (accepting) the corresponding codings), or by changing boldfaced text into non-boldfaced text (thereby rejecting (disconfirming) the corresponding codings). Note that the user 130 performs such verification implicitly in the sense that the underlying codes 110 a-b (e.g., XML elements 422 a-b) are not directly displayed to the user 130, and in that the user 130 does not directly edit the codes 110 a-b, but rather views and edits a rendering of the data 112 a-b and/or linked text 118 a-b that has been modified based on the codes 110 a-b.
  • Once the user 130 has provided the verification input 134 indicating the verification statuses of the renderings 128 a-b of the codings 108 a-b, the verification subsystem 132 identifies verification statuses of the selected feature 140 of the codings 108 a-b, based on the verification input 134 provided by the user 130 (step 216). For example, the verification subsystem 132 identifies a verification status of the feature 140 of coding 108 a based on the verification status of the rendering 128 a of coding 108 a.
  • For example, if the user 130 decides that the text “Penicillin” does not represent a coding of an allergy, the user 130 may select the text “Penicillin” 318 within the rendering 310 and change the formatting of that text to non-boldfaced. The verification subsystem 132 (in step 216) may interpret this input (which directly verifies rendering 128 a) as an indication by the user 130 that the verification status of the “allergen” feature of coding 108 a is “incorrect,” and that the underlying Penicillin coding therefore should not be encoded as an allergen. In response to such disconfirmation of the original coding of Penicillin as an allergen, the system 100 may sever the relationship between the Penicillin coding and the corresponding allergen coding, such as by removing the Penicillin coding from the allergen coding.
  • Similarly, if the text “Penicillin” 318 had not been displayed as boldfaced text in the rendering 310, the user 130 may select the text “Penicillin” 318 and change the formatting of that text to boldfaced. In response, the verification subsystem 132 (in step 216) may determine that the verification status of the “allergen” feature of coding 108 a is “incorrect,” and that the underlying Penicillin coding therefore should be encoded as an allergen. In response, the system 100 may encode the Penicillin coding as an allergen.
  • In both of these examples, the system 100 enables the user 130 to verify certain features of codings which are particularly prone to being initially encoded incorrectly using automatic encoding techniques, such as the “allergen” feature of an “allergy” coding. Prompting the user 130 to verify such features, and enabling the user 130 to correct the encoding of such features if they are incorrect, increases the overall accuracy of the codings 108.
  • Furthermore, these techniques may be used to infer the correctness or incorrectness of one feature of a coding based on the user's verification of another feature of the coding. More generally, these techniques may be used to infer the correctness of an entire coding based on the user's verification of one feature of the coding. For example, as shown in FIG. 2, in step 218 the verification subsystem 132 may identify verification statuses of the codings 108 based on the verification statuses of the renderings 128 (identified in step 214) and/or the verification statuses of the feature 140 of the codings 108 (identified in step 216).
  • For example, if the user 130 does not change the formatting of the boldfaced text 318 (“Penicillin”) to non-boldfaced text, the user 130 thereby verifies a first feature of the underlying coding 108 a, namely that the underlying “Penicillin” coding has been correctly encoded as an allergen. The system 100 may assume that a second feature of the coding 108 a is also correct, namely that Penicillin (which may be encoded in a <substance> coding), rather than some other substance, is the correct allergen. The system 100 may infer, from the verification of the first feature and the assumption that the second feature is correct, that the entire underlying allergy coding 108 a is correct.
  • The verification status indication provided by the user 130 in step 214 need not take the form of explicit input provided by the user 130. Rather, the verification subsystem 132 may interpret a lack of input by the user 130 as an indication of the verification status. For example, as described above with respect to the rendering 300 in FIG. 3A, if the user 130 determines that the rendering 304 a of the Penicillin allergy coding 108 a is not correct, the user 130 may simply leave the corresponding checkbox 302 e unchecked. The verification subsystem 132 may interpret this inaction by the user 130 as an indication by the user 130 of a verification status of “incorrect” or “unverified.” Similarly, the user's decision not to change the boldfaced status of text in the rendering 310 of FIG. 3B may be interpreted by the verification subsystem 132 that the codings 108 a-b are correct.
  • The indication provided by the user 130 may contain information in addition to the verification status of the rendering 128 a. For example, the input 134 may include information that the verification subsystem 132 uses to modify the contents of the coding 108 a. Consider an example in which the spoken audio stream 102 includes a recording of the words “thirty-seven point two degrees Celsius,” but this was incorrectly transcribed in the linked text 118 a as “35.2 C”. Assume further that the data 112 a in the coding 108 a therefore includes the data value 35.2 C. If the user 130 edits the text “35.2 C” in the rendering 128 a by replacing it with the text “37.2 C”, the verification subsystem 132 may both replace the linked text 118 a with the text “37.2 C” and replace the data 112 a with the data value 37.2 C. As this example illustrates, the verification input 134 may include input indicating not only a verification status of the data 112 a, but also a modification to be made to the data 112 a. The same applies to any of the other elements of the coding 108 a, such as any of the elements shown in FIG. 5.
  • Once the verification subsystem 132 has identified the verification status of the selected feature 140 of the coding 108 a and/or of the entire coding 108 a, the verification subsystem 132 may store a record 136 a of that verification status (step 220). In the example illustrated in FIG. 1, the verification subsystem 132 stores the record 136 a in the transcript 106 itself, within the coding 108 a (as illustrated further in FIG. 5).
  • For example, once the verification process 200 has been performed for all codings 108 a-b in the transcript 106, the codings in the document 106 that code for allergens, and which were boldfaced during the review process 200 and not edited by the user 130 may be assumed to be correct and human-verified. For such codings, the verification subsystem 132 may store the value of “correct, human-verified” in the verification status field 136. As this example illustrates, the verification status field 136 a may store not merely a binary value of “correct” or “incorrect,” but additional information about the verification status of the coding 108 a, such as whether the coding 108 a was verified by a human or by an automated procedure.
  • The verification subsystem 132 may record additional information about the verification of the codings 108. For example, the verification subsystem 132 may store a record 504 a (FIG. 5) of the type of verification indication provided by the user 130. For example, the record 504 a may indicate whether the user 130 verified the coding 108 a by performing an action in the form of an express input 134 (such as a mouse click), or whether the verification subsystem 132 inferred the verification status 136 a from the user's inaction (e.g., the user's decision not to change the formatting of text 314 in the rendering 310 of FIG. 3B).
  • Furthermore, although in certain examples disclosed herein the user 130 verifies the codings 108 implicitly based on renderings 128 a-b of the codings 108, the system 100 may display the codings 108 a-b (including the codes 110 a-b) to the user 130 and allow the user 130 to verify the codings 108 a-b explicitly. For example, the rendering 126 may include a side-by-side display of the structured document 420 shown in FIG. 4C and a corresponding rendering, such as one of the renderings 300 and 310 shown in FIGS. 3A and 3B. The user 130 may then choose whether to verify the codings 108 by editing the document 420 directly, or by using the renderings as described above. The verification subsystem 132 may store a record 506 a (FIG. 5) in the coding 108 a indicating which of these methods the user 130 used to verify the coding 108 a. For example, the record 506 a may include a value of “explicit” if the user 130 verified the coding 108 a by editing the document 420 (FIG. 4C), or a value of “implicit” if the user 130 verified the coding 108 a based on a rendering of the document 420 (e.g., the renderings 300 and 310 in FIGS. 3A and 3B).
  • Furthermore, verifying one coding may imply that another coding has been verified. For example, verifying a specific coding at one level of generality may imply that a coding at a lower level of generality (i.e., higher degree of specificity) has also been verified. For example, verifying that a coding of the text “Penicillin causes hives” has been correctly encoded as a (general) “drug allergy” may imply that the coding also correctly encodes a (more specific) “Penicillin allergy.” Therefore, if the user 130 verifies a general coding which encompasses a more specific coding, the verification subsystem 132 may infer that the more specific coding has also been human-verified, and store a record of that verification status for the specific coding. Even more generally, the verification status of one coding may be used to derive a verification status for another coding, with the nature of the derivation depending on the relationship between the two codings.
  • The verification status 136 a of the coding 108 a, therefore, may have been generated based on an inference drawn from the verification status (and/or other features) of one or more other codings forming a chain. The verification subsystem 132 may store a record (e.g., record 508 a) of the chain of codings from which the verification status 136 a for the coding 108 a was derived. For example, if the coding 108 a is a coding for a drug allergy which was inferred to be verified based on the user's direct verification of a coding for a Penicillin allergy (or vice versa), the verification subsystem 132 may store a pointer to the Penicillin coding in the verification chain 508 a record of the coding 108 a. If the user 130 verified the coding 108 a directly (i.e., if the verification status 136 a of the coding 108 a was not inferred from any other coding), then the verification chain record 508 a may contain a null value.
  • At the conclusion of the verification process 200, different ones of the codings 108 may have different verification states. For example, some of the codings may have been human-verified based on a rendering of the codings, while others may have been human-verified based on the codings themselves. As has just been described, these and other aspects of the manner in which the codings 108 have been verified may be recorded within the codings 108 themselves (as illustrated in FIG. 5) and/or elsewhere in the transcript 106. This information may be used for a variety of purposes.
  • Once the verification process 200 is complete for all of the codings 108 a-b, it may further be assumed that all text in the transcript 106 which describes allergens is now written in boldfaced text. For those allergens that were detected by the transcription system 106 but subsequently edited by the user 130, or that were added by the user 130 by bolding previously unbolded text, the verification subsystem 130 may attach a code for “allergen of adverse reaction” but not attach the code for the specific allergen without further human review. If the user 130 unbolded text corresponding to a coding 108, the verification subsystem 132 may, in response, remove the corresponding coding from the transcript 106.
  • As a result, once the verification process 200 is complete: (1) all allergens for positive allergic reactions are coded in some form in the transcript 106 (at least with the generic code “allergen of adverse reaction”); (2) none but those allergens are coded in this manner (i.e., no false positives); and (3) most allergens are annotated with a specific allergen code (those that were detected by the system); the lack of this specific coding is explicit and thus can be added as needed for others. When using the rendering 300 shown in FIG. 3A, the classification of allergies as either “food allergy” or “drug allergy” is verified, while when using the rendering 310 shown in FIG. 3B, the classification of allergies as “food allergy” or “drug allergy” remains unverified.
  • Among the advantages of the invention are one or more of the following. In general, enabling the codings 108 a-b to be verified by a human enables the document 106 to be relied upon with a higher degree of confidence than documents which are verified using traditional automated techniques based on statistically-derived confidence measures. Techniques disclosed herein facilitate the verification process, by enabling the codings 108 to be verified without displaying the codes 110 a-b themselves to the user 130. Instead, the codings 108 are used to modify the manner in which the corresponding linked text 118 a-b is rendered. The user 130 then verifies features of the codings 108 based on the rendering 126, which is designed to be easily understandable to non-technically trained users, such as medical transcriptionists who are not trained to understand the codes 110 a-b themselves. In addition to facilitating verification of the codes 110 a-b, this process increases the reliability of the resulting verification statuses because verifications performed by human users are generally more reliable than those produced automatically by software based on statistically-derived confidence measures.
  • Another advantage of embodiments of the present invention is that they enable the codings 108 and the text 116 of the transcript 106 to be verified by an integrated process, rather than in separate steps. As described above, for example, the user 130 may verify the accuracy of the coding 108 a at the same time as the user 130 verifies the accuracy of the corresponding linked text 118 a. The system 100 may, for example, play back the spoken audio stream 102 to the user 130, in response to which the user 130 may verify both the accuracy of the text 116 (by comparing the text 116 to the words in the spoken audio stream 102) and the accuracy of the codings 108 a-b. This results in a more efficient verification process, and may enable verification of the codings 108 to be integrated with existing transcription workflows at low cost. The verification status indicated by the user 130 for the text 116 may be stored in the transcript 106, in a manner similar to that in which the verification statuses of the codings 108 are stored in the codings 108.
  • Note that a single indication (e.g., action or inaction) may be used to verify both a coding and the coding's corresponding linked text. For example, the decision by the user 130 not to edit, or change the format of, text in the rendering 126 of the transcript, may be interpreted by the verification subsystem 132 as an indication both that the text is an accurate transcription of the spoken audio stream 102 and that the corresponding coding accurately encodes the text.
  • A further advantage of embodiments of the present invention is that they enable the degree of trust that a coding is correct to be explicitly recorded in the coding itself, such as in the form of an XML element. Examples of such encodings of levels of trust are the derivation type field 502 a (indicating, for example, whether the code 110 a was automatically derived or manually derived), the indication type field 504 a (indicating, for example, whether the user 130 provided the verification status 136 a using express input or by lack of input), the verification type field 506 a (indicating, for example, whether the user 130 verified the coding 108 a directly by editing the coding 108 a or indirectly by verifying the rendering 128 a of the coding 108 a), and the verification chain field 508 a (indicating whether the coding 108 a through a deductive chain of verifications of other codings).
  • Such encodings may be interpreted to reflect levels of trust in a variety of ways. For example, automatically derived codings may be assigned a lower level of trust than manually derived codings; codings verified using express input may be assigned a higher level of trust than those verified by lack of input; codings verified by direct editing of their codes may be assigned a higher level of trust than those verified through renderings of the codings; and codes verified by deduction through a chain of codings may be assigned a lower level of trust than codings verified without deduction through a chain. These and other reflections of levels of trust in the accuracy of the codings 108 a-b may be stored and used, individually or in any combination, by applications to decide whether a particular coding, representing data extracted from the spoken audio stream 102, is suitable for use for the application's purposes. For example, applications which require data to be highly trustworthy may exclude data which is marked as having insufficiently high levels of trust.
  • More generally, documents which encode medical and other facts have a variety of applications (use cases). For example, data mining may be performed on collections of encoded documents. For example, the abstraction of synonym expressions for the same underlying fact (e.g., “lung inflammation” and “pneumonia”), and the correct scoping of negations and tense can significantly improve the quality of data mining results, and the ease of writing queries. For example, without using these techniques, it can be very difficult to write a text query which identifies all active smokers in a free-text database that contains entries like “does not smoke,” “patient smokes 2 packs a day,” and “patient used to smoke.”
  • Documents which encode facts may also be used to generate reporting/performance measures. For example, automatic or semi-automatic abstraction may be performed on such documents to fulfill reporting requirements for cancer and other registries, or data elements for treatment-related performance measures (as may be required, for example, by the government or payer).
  • Other examples of uses of encoded documents include clinical decision support (e.g., expert systems which support the physician at the point of care based on evidence taken from a medical report), billing coding, and electronic medical record data entry (e.g., populating discrete data elements of an EMR system from facts extracted from free form text).
  • It is to be understood that although the invention has been described above in terms of particular embodiments, the foregoing embodiments are provided as illustrative only, and do not limit or define the scope of the invention. Various other embodiments, including but not limited to the following, are also within the scope of the claims. For example, elements and components described herein may be further divided into additional components or joined together to form fewer components for performing the same functions. Although certain examples provided herein involve documents generated by a speech recognizer, this is not a requirement of the present invention. Rather, the techniques disclosed herein may be applied to any kind of document, regardless of how it was generated. Such techniques may, for example, be used in conjunction with documents typed using conventional text editors.
  • The spoken audio stream may be any audio stream, such as a live audio stream received directly or indirectly (such as over a telephone or IP connection), or an audio stream recorded on any medium and in any format. In distributed speech recognition (DSR), a client performs preprocessing on an audio stream to produce a processed audio stream that is transmitted to a server, which performs speech recognition on the processed audio stream. The audio stream may, for example, be a processed audio stream produced by a DSR client.
  • The invention is not limited to any of the described domains (such as the medical and legal fields), but generally applies to any kind of documents in any domain. Furthermore, documents used in conjunction with embodiments of the present invention may be represented in any machine-readable form. Such forms include plain text documents and structured documents represented in markup languages such as XML. Such documents may be stored in any computer-readable medium and transmitted using any kind of communications channel and protocol.
  • Although in certain examples described herein the manner in which the text 116 is rendered is described as being based on the codes 110 a, the text 116 may be rendered based on any combination of the codes 110 a and other elements of the coding 108 a (such as any of the elements shown in FIG. 5). For example, the manner in which the text 116 is rendered may be modified based on both the code 110 a and the data 112 a.
  • Although in the method 200 illustrated in FIG. 2 all of the codings 108 a-b are rendered and verified by the user 130, this is not required. For example, some of the codings 108 a-b may be for use within the transcript 106 only and need not be rendered to the user 130. Such codings may be left with a verification status of “unverified” after the verification process 200 is complete.
  • Although the spoken audio stream 102 may be played back to the user 130 to assist in verifying the codings 108, this is not required. The spoken audio stream 102 need not be used in the verification process 200, e.g., if the verification process is performed by the dictating author himself. Using the spoken audio stream 102 may, however, enable the accuracy of the codings 108 and the text 116 to be verified using an integrated process.
  • Not all text 116 need be encoded in the transcript 106. In other words, some of the text 116 may be “flat” text having no corresponding codes. Furthermore, multiple ones of the codes 108 may link to the same portions of the text 116.
  • Any element of the coding 108 a that is illustrated within the coding 108 a in FIG. 5 may alternatively be external to the coding 108 a and be referenced by the coding 108 a. For example, the verification status 136 a may be stored external to the coding 108 a and be referenced by the coding 108 a. Conversely, the linked text 118 a may be implemented within the coding 108 a itself rather than referenced by the coding 108 a. Various other ways of implementing the draft transcript 106, the codings 108, and the text 116 to perform the functions disclosed herein will be apparent to those having ordinary skill in the art and fall within the scope of the present invention.
  • The simple structures of the coding 108 a shown in FIGS. 1 and 5 are shown merely for purposes of example. The coding 108 a may have more complex structures. For example, the coding 108 a may include multiple data elements rather than the single data element 112 a. Furthermore, the coding 108 a may itself include and/or reference other codings. For example, a coding corresponding to the text “allergy to penicillin causing hives” may include/reference other codings for the allergen (Penicillin), for the kind of adverse reaction (hives), and for the concept that contains links to both the allergen and the reaction. As another example, a coding corresponding to the text “left shoulder pain” may include/reference a coding for the body part (left shoulder), the problem (pain), and the relationship between both (pain in left shoulder). This linking of codes is referred to as “post-coordination.”
  • Although in certain examples described herein the feature 140 whose accuracy is verified specifies a relationship with a single coding, this is not a limitation of the present invention. For example, a feature may be a relationship between one coding and two other codings. For example, a feature of coding A may be the relationship that A is A B is A C, where B and C are both codings.
  • Although certain references may be made herein to “data” in the plural (such as the data 112 a and 112 b), any such references should be understood to refer to single data elements as well. For example, data 112 a may be a single datum, as may data 112 b.
  • The techniques described above may be implemented, for example, in hardware, software, firmware, or any combination thereof. The techniques described above may be implemented in one or more computer programs executing on a programmable computer including a processor, a storage medium readable by the processor (including, for example, volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Program code may be applied to input entered using the input device to perform the functions described and to generate output. The output may be provided to one or more output devices.
  • Each computer program within the scope of the claims below may be implemented in any programming language, such as assembly language, machine language, a high-level procedural programming language, or an object-oriented programming language. The programming language may, for example, be a compiled or interpreted programming language.
  • Each such computer program may be implemented in a computer program product tangibly embodied in a machine-readable storage device for execution by a computer processor. Method steps of the invention may be performed by a computer processor executing a program tangibly embodied on a computer-readable medium to perform functions of the invention by operating on input and generating output. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, the processor receives instructions and data from a read-only memory and/or a random access memory. Storage devices suitable for tangibly embodying computer program instructions include, for example, all forms of non-volatile memory, such as semiconductor memory devices, including EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs. Any of the foregoing may be supplemented by, or incorporated in, specially-designed ASICs (application-specific integrated circuits) or FPGAs (Field-Programmable Gate Arrays). A computer can generally also receive programs and data from a storage medium such as an internal disk (not shown) or a removable disk. These elements will also be found in a conventional desktop or workstation computer as well as other computers suitable for executing computer programs implementing the methods described herein, which may be used in conjunction with any digital print engine or marking engine, display monitor, or other raster output device capable of producing color or gray scale pixels on paper, film, display screen, or other output medium.

Claims (1)

    What is claimed is:
  1. 1. A method performed by at least one computer processor executing computer program instructions tangibly stored on at least one non-transitory computer-readable medium, the method comprising:
    (A) identifying a document including a first coding having a first feature encoding a first concept, the first coding being associated with a first code;
    (B) associating first data with the first coding, the first data representing information that does not have a correspondence with the document;
    (C) rendering the first coding and the first data on an output device to have a visual characteristic that is based on the first feature, without rendering the first code;
    (D) receiving, via an input device, a first indication from a user of whether the rendering is accurate;
    (E) identifying, based on the first indication received from the user, a verification status of the first coding, wherein the verification status of the first coding indicates whether the first code represents the first concept, comprising:
    (E)(1) if the first indication indicates that the rendering is accurate, then identifying a verification status of the first coding indicating that the first coding is accurate; and
    (E)(2) otherwise, identifying a verification status of the first coding indicating that the first coding is inaccurate; and
    (F) if the verification status of the first coding indicates that the first coding is inaccurate, then modifying at least one of the first feature of the first coding and the first data.
US14317323 2006-06-22 2014-06-27 Verification of Extracted Data Abandoned US20140316772A1 (en)

Priority Applications (8)

Application Number Priority Date Filing Date Title
US81568906 true 2006-06-22 2006-06-22
US81568706 true 2006-06-22 2006-06-22
US81568806 true 2006-06-22 2006-06-22
US11766767 US7716040B2 (en) 2006-06-22 2007-06-21 Verification of extracted data
US12771193 US8321199B2 (en) 2006-06-22 2010-04-30 Verification of extracted data
US13563949 US8521514B2 (en) 2006-06-22 2012-08-01 Verification of extracted data
US13975833 US8768694B2 (en) 2006-06-22 2013-08-26 Verification of extracted data
US14317323 US20140316772A1 (en) 2006-06-22 2014-06-27 Verification of Extracted Data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US14317323 US20140316772A1 (en) 2006-06-22 2014-06-27 Verification of Extracted Data

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US13975833 Continuation US8768694B2 (en) 2006-06-22 2013-08-26 Verification of extracted data

Publications (1)

Publication Number Publication Date
US20140316772A1 true true US20140316772A1 (en) 2014-10-23

Family

ID=38834406

Family Applications (10)

Application Number Title Priority Date Filing Date
US11766767 Active US7716040B2 (en) 2006-06-22 2007-06-21 Verification of extracted data
US11766780 Abandoned US20070299665A1 (en) 2006-06-22 2007-06-21 Automatic Decision Support
US11766784 Active 2030-12-26 US8560314B2 (en) 2006-06-22 2007-06-21 Applying service levels to transcripts
US12771193 Active US8321199B2 (en) 2006-06-22 2010-04-30 Verification of extracted data
US13563949 Active US8521514B2 (en) 2006-06-22 2012-08-01 Verification of extracted data
US13888290 Active 2027-08-27 US9892734B2 (en) 2006-06-22 2013-05-06 Automatic decision support
US13975833 Active US8768694B2 (en) 2006-06-22 2013-08-26 Verification of extracted data
US14052005 Abandoned US20140039880A1 (en) 2006-06-22 2013-10-11 Applying Service Levels to Transcripts
US14317323 Abandoned US20140316772A1 (en) 2006-06-22 2014-06-27 Verification of Extracted Data
US15892876 Pending US20180166081A1 (en) 2006-06-22 2018-02-09 Automatic Decision Support

Family Applications Before (8)

Application Number Title Priority Date Filing Date
US11766767 Active US7716040B2 (en) 2006-06-22 2007-06-21 Verification of extracted data
US11766780 Abandoned US20070299665A1 (en) 2006-06-22 2007-06-21 Automatic Decision Support
US11766784 Active 2030-12-26 US8560314B2 (en) 2006-06-22 2007-06-21 Applying service levels to transcripts
US12771193 Active US8321199B2 (en) 2006-06-22 2010-04-30 Verification of extracted data
US13563949 Active US8521514B2 (en) 2006-06-22 2012-08-01 Verification of extracted data
US13888290 Active 2027-08-27 US9892734B2 (en) 2006-06-22 2013-05-06 Automatic decision support
US13975833 Active US8768694B2 (en) 2006-06-22 2013-08-26 Verification of extracted data
US14052005 Abandoned US20140039880A1 (en) 2006-06-22 2013-10-11 Applying Service Levels to Transcripts

Family Applications After (1)

Application Number Title Priority Date Filing Date
US15892876 Pending US20180166081A1 (en) 2006-06-22 2018-02-09 Automatic Decision Support

Country Status (5)

Country Link
US (10) US7716040B2 (en)
EP (3) EP2030197A4 (en)
JP (4) JP5167256B2 (en)
CA (3) CA2650816C (en)
WO (3) WO2007150004A3 (en)

Families Citing this family (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9710819B2 (en) * 2003-05-05 2017-07-18 Interactions Llc Real-time transcription system utilizing divided audio chunks
US20130304453A9 (en) * 2004-08-20 2013-11-14 Juergen Fritsch Automated Extraction of Semantic Content and Generation of a Structured Document from Speech
US7584103B2 (en) * 2004-08-20 2009-09-01 Multimodal Technologies, Inc. Automated extraction of semantic content and generation of a structured document from speech
US8335688B2 (en) * 2004-08-20 2012-12-18 Multimodal Technologies, Llc Document transcription system training
US7502741B2 (en) * 2005-02-23 2009-03-10 Multimodal Technologies, Inc. Audio signal de-identification
US7844464B2 (en) * 2005-07-22 2010-11-30 Multimodal Technologies, Inc. Content-based audio playback emphasis
US7640158B2 (en) 2005-11-08 2009-12-29 Multimodal Technologies, Inc. Automatic detection and application of editing patterns in draft documents
WO2007150004A3 (en) * 2006-06-22 2008-11-06 Multimodal Technologies Inc Verification of extracted data
US20080177623A1 (en) * 2007-01-24 2008-07-24 Juergen Fritsch Monitoring User Interactions With A Document Editing System
US8348839B2 (en) 2007-04-10 2013-01-08 General Electric Company Systems and methods for active listening/observing and event detection
US8019608B2 (en) 2008-08-29 2011-09-13 Multimodal Technologies, Inc. Distributed speech recognition using one way communication
US20100125450A1 (en) 2008-10-27 2010-05-20 Spheris Inc. Synchronized transcription rules handling
US20100145720A1 (en) * 2008-12-05 2010-06-10 Bruce Reiner Method of extracting real-time structured data and performing data analysis and decision support in medical reporting
US9082310B2 (en) 2010-02-10 2015-07-14 Mmodal Ip Llc Providing computable guidance to relevant evidence in question-answering systems
US20110282687A1 (en) * 2010-02-26 2011-11-17 Detlef Koll Clinical Data Reconciliation as Part of a Report Generation Solution
US20150279354A1 (en) * 2010-05-19 2015-10-01 Google Inc. Personalization and Latency Reduction for Voice-Activated Commands
US9613325B2 (en) * 2010-06-30 2017-04-04 Zeus Data Solutions Diagnosis-driven electronic charting
US8630842B2 (en) * 2010-06-30 2014-01-14 Zeus Data Solutions Computerized selection for healthcare services
US8463673B2 (en) 2010-09-23 2013-06-11 Mmodal Ip Llc User feedback in semi-automatic question answering systems
US8959102B2 (en) 2010-10-08 2015-02-17 Mmodal Ip Llc Structured searching of dynamic structured document corpuses
US8924394B2 (en) 2011-02-18 2014-12-30 Mmodal Ip Llc Computer-assisted abstraction for reporting of quality measures
US10032127B2 (en) 2011-02-18 2018-07-24 Nuance Communications, Inc. Methods and apparatus for determining a clinician's intent to order an item
CA2839266A1 (en) 2011-06-19 2012-12-27 Mmodal Ip Llc Document extension in dictation-based document generation workflow
US9286035B2 (en) 2011-06-30 2016-03-15 Infosys Limited Code remediation
US9021565B2 (en) * 2011-10-13 2015-04-28 At&T Intellectual Property I, L.P. Authentication techniques utilizing a computing device
EP2786339A4 (en) 2011-11-28 2015-06-24 Voicehit Electronic health record system and method for patient encounter transcription and documentation
US9679077B2 (en) * 2012-06-29 2017-06-13 Mmodal Ip Llc Automated clinical evidence sheet workflow
US9710431B2 (en) * 2012-08-18 2017-07-18 Health Fidelity, Inc. Systems and methods for processing patient information
CN103198220A (en) * 2013-04-08 2013-07-10 浙江大学医学院附属第二医院 Computer-aided antibacterial agent clinical application mid-diagnosis decision making system
US20140365232A1 (en) * 2013-06-05 2014-12-11 Nuance Communications, Inc. Methods and apparatus for providing guidance to medical professionals
US20150121456A1 (en) * 2013-10-25 2015-04-30 International Business Machines Corporation Exploiting trust level lifecycle events for master data to publish security events updating identity management
US20170199963A1 (en) * 2016-01-13 2017-07-13 Nuance Communications, Inc. Medical report coding with acronym/abbreviation disambiguation
US10043135B2 (en) * 2016-03-08 2018-08-07 InferLink Corporation Textual information extraction, parsing, and inferential analysis
US20180204645A1 (en) * 2017-01-17 2018-07-19 Mmodal Ip Llc Methods and systems for manifestation and transmission of follow-up notifications

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6915254B1 (en) * 1998-07-30 2005-07-05 A-Life Medical, Inc. Automatically assigning medical codes using natural language processing
US20070237427A1 (en) * 2006-04-10 2007-10-11 Patel Nilesh V Method and system for simplified recordkeeping including transcription and voting based verification

Family Cites Families (210)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62221775A (en) 1986-03-20 1987-09-29 Fujitsu Ltd Natural language processing system
US5329609A (en) 1990-07-31 1994-07-12 Fujitsu Limited Recognition apparatus with function of displaying plural recognition candidates
US5434962A (en) 1990-09-07 1995-07-18 Fuji Xerox Co., Ltd. Method and system for automatically generating logical structures of electronic documents
JPH0769921B2 (en) 1990-11-09 1995-07-31 株式会社日立製作所 Document logical structure generating method
WO1993007562A1 (en) * 1991-09-30 1993-04-15 Riverrun Technology Method and apparatus for managing information
JPH06168267A (en) 1992-11-30 1994-06-14 Itec:Kk Structural document preparing method and structural document preparation supporting device
CA2151371A1 (en) 1992-12-31 1994-07-21 Yen-Lu Chow Recursive finite state grammar
US5384892A (en) 1992-12-31 1995-01-24 Apple Computer, Inc. Dynamic language model for speech recognition
US7631343B1 (en) * 1993-03-24 2009-12-08 Endgate LLC Down-line transcription system using automatic tracking and revenue collection
US5594638A (en) 1993-12-29 1997-01-14 First Opinion Corporation Computerized medical diagnostic system including re-enter function and sensitivity factors
US6206829B1 (en) * 1996-07-12 2001-03-27 First Opinion Corporation Computerized medical diagnostic and treatment advice system including network access
US5809476A (en) * 1994-03-23 1998-09-15 Ryan; John Kevin System for converting medical information into representative abbreviated codes with correction capability
JPH07325597A (en) * 1994-05-31 1995-12-12 Fuji Xerox Co Ltd Information input method and device for executing its method
JP2618832B2 (en) * 1994-06-16 1997-06-11 日本アイ・ビー・エム株式会社 Analysis methods and systems of the logical structure of the document
US6061675A (en) 1995-05-31 2000-05-09 Oracle Corporation Methods and apparatus for classifying terminology utilizing a knowledge catalog
US5664109A (en) 1995-06-07 1997-09-02 E-Systems, Inc. Method for extracting pre-defined data items from medical service records generated by health care providers
US5701469A (en) 1995-06-07 1997-12-23 Microsoft Corporation Method and system for generating accurate search results using a content-index
JPH09106428A (en) * 1995-10-11 1997-04-22 Kitsusei Comtec Kk Finding preparing device
GB9525719D0 (en) * 1995-12-15 1996-02-14 Hewlett Packard Co Speech system
US6041292A (en) 1996-01-16 2000-03-21 Jochim; Carol Real time stenographic system utilizing vowel omission principle
US6684188B1 (en) * 1996-02-02 2004-01-27 Geoffrey C Mitchell Method for production of medical records and other technical documents
US5835893A (en) 1996-02-15 1998-11-10 Atr Interpreting Telecommunications Research Labs Class-based word clustering for speech recognition using a three-level balanced hierarchical similarity
US5870706A (en) 1996-04-10 1999-02-09 Lucent Technologies, Inc. Method and apparatus for an improved language recognition system
US5823948A (en) * 1996-07-08 1998-10-20 Rlis, Inc. Medical records, documentation, tracking and order entry system
JP4615629B2 (en) * 1996-07-12 2011-01-19 クリニカル ディシジョン サポート,エルエルシー Including access to the network, medical diagnosis and treatment advice system using computer
US5797123A (en) 1996-10-01 1998-08-18 Lucent Technologies Inc. Method of key-phase detection and verification for flexible speech understanding
US6182029B1 (en) * 1996-10-28 2001-01-30 The Trustees Of Columbia University In The City Of New York System and method for language extraction and encoding utilizing the parsing of text data in accordance with domain parameters
US6055494A (en) 1996-10-28 2000-04-25 The Trustees Of Columbia University In The City Of New York System and method for medical language extraction and encoding
US5839106A (en) * 1996-12-17 1998-11-17 Apple Computer, Inc. Large-vocabulary speech recognition using an integrated syntactic and semantic statistical language model
US6122613A (en) * 1997-01-30 2000-09-19 Dragon Systems, Inc. Speech recognition using multiple recognizers (selectively) applied to the same input sample
US5995936A (en) * 1997-02-04 1999-11-30 Brais; Louis Report generation system and method for capturing prose, audio, and video by voice command and automatically linking sound and image to formatted text locations
WO1998040835A1 (en) 1997-03-13 1998-09-17 First Opinion Corporation Disease management system
US5970449A (en) 1997-04-03 1999-10-19 Microsoft Corporation Text normalization using a context-free grammar
US6126596A (en) 1997-06-02 2000-10-03 Freedman; Joshua Apparatus and method for evaluating a client's condition and the concordance of a clinician's treatment with treatment guidelines
US6490561B1 (en) * 1997-06-25 2002-12-03 Dennis L. Wilson Continuous speech voice transcription
US5926784A (en) * 1997-07-17 1999-07-20 Microsoft Corporation Method and system for natural language parsing using podding
EP0903727A1 (en) 1997-09-17 1999-03-24 Istituto Trentino Di Cultura A system and method for automatic speech recognition
WO1999017223A1 (en) 1997-09-30 1999-04-08 Ihc Health Services, Inc. Aprobabilistic system for natural language processing
US6112168A (en) 1997-10-20 2000-08-29 Microsoft Corporation Automatically recognizing the discourse structure of a body of text
US6304870B1 (en) * 1997-12-02 2001-10-16 The Board Of Regents Of The University Of Washington, Office Of Technology Transfer Method and apparatus of automatically generating a procedure for extracting information from textual information sources
US6006183A (en) * 1997-12-16 1999-12-21 International Business Machines Corp. Speech recognition confidence level display
US6154722A (en) 1997-12-18 2000-11-28 Apple Computer, Inc. Method and apparatus for a speech recognition system language model that integrates a finite state grammar probability and an N-gram probability
US6782510B1 (en) 1998-01-27 2004-08-24 John N. Gross Word checking tool for controlling the language content in documents using dictionaries with modifyable status fields
DE19809563A1 (en) * 1998-03-05 1999-09-09 Siemens Ag Medical work station for treating patient
US6182039B1 (en) 1998-03-24 2001-01-30 Matsushita Electric Industrial Co., Ltd. Method and apparatus using probabilistic language model based on confusable sets for speech recognition
US7043426B2 (en) * 1998-04-01 2006-05-09 Cyberpulse, L.L.C. Structured speech recognition
US6778970B2 (en) * 1998-05-28 2004-08-17 Lawrence Au Topological methods to organize semantic network data flows for conversational applications
US6304848B1 (en) * 1998-08-13 2001-10-16 Medical Manager Corp. Medical record forming and storing apparatus and medical record and method related to same
US6064961A (en) 1998-09-02 2000-05-16 International Business Machines Corporation Display for proofreading text
US6064965A (en) 1998-09-02 2000-05-16 International Business Machines Corporation Combined audio playback in speech recognition proofreader
US6122614A (en) * 1998-11-20 2000-09-19 Custom Speech Usa, Inc. System and method for automating transcription services
US6249765B1 (en) * 1998-12-22 2001-06-19 Xerox Corporation System and method for extracting data from audio messages
US6278968B1 (en) 1999-01-29 2001-08-21 Sony Corporation Method and apparatus for adaptive speech recognition hypothesis construction and selection in a spoken language translation system
US6243669B1 (en) * 1999-01-29 2001-06-05 Sony Corporation Method and apparatus for providing syntactic analysis and data structure for translation knowledge in example-based language translation
WO2000054180A1 (en) 1999-03-05 2000-09-14 Cai Co., Ltd. System and method for creating formatted document on the basis of conversational speech recognition
JP2000259175A (en) 1999-03-08 2000-09-22 Mitsubishi Electric Corp Voice recognition device
US6526380B1 (en) * 1999-03-26 2003-02-25 Koninklijke Philips Electronics N.V. Speech recognition system having parallel large vocabulary recognition engines
US6609087B1 (en) * 1999-04-28 2003-08-19 Genuity Inc. Fact recognition system
US6611802B2 (en) 1999-06-11 2003-08-26 International Business Machines Corporation Method and system for proofreading and correcting dictated text
US6345249B1 (en) 1999-07-07 2002-02-05 International Business Machines Corp. Automatic analysis of a speech dictated document
US6865258B1 (en) * 1999-08-13 2005-03-08 Intervoice Limited Partnership Method and system for enhanced transcription
US20030195774A1 (en) 1999-08-30 2003-10-16 Abbo Fred E. Medical practice management system
US6963837B1 (en) * 1999-10-06 2005-11-08 Multimodal Technologies, Inc. Attribute-based word modeling
US6434547B1 (en) * 1999-10-28 2002-08-13 Qenm.Com Data capture and verification system
US7392185B2 (en) 1999-11-12 2008-06-24 Phoenix Solutions, Inc. Speech based learning/training system using semantic decoding
US7725307B2 (en) * 1999-11-12 2010-05-25 Phoenix Solutions, Inc. Query engine for processing voice based queries including semantic decoding
CN1254787C (en) * 1999-12-02 2006-05-03 汤姆森许可贸易公司 Method and device for speech recognition with disjoint language modules
US6535849B1 (en) 2000-01-18 2003-03-18 Scansoft, Inc. Method and system for generating semi-literal transcripts for speech recognition systems
CA2398823A1 (en) * 2000-02-14 2001-08-23 First Opinion Corporation Automated diagnostic system and method
JP3896760B2 (en) 2000-03-28 2007-03-22 富士ゼロックス株式会社 Interactive recording editing apparatus, method and a storage medium
US6738784B1 (en) * 2000-04-06 2004-05-18 Dictaphone Corporation Document and information processing system
WO2001084535A3 (en) 2000-05-02 2002-06-27 David Abrahams Error correction in speech recognition
US7447988B2 (en) 2000-05-10 2008-11-04 Ross Gary E Augmentation system for documentation
GB0011798D0 (en) * 2000-05-16 2000-07-05 Canon Kk Database annotation and retrieval
EP1305767B1 (en) * 2000-05-18 2014-03-19 Commwell, Inc. Method for remote medical monitoring incorporating video processing
US6662168B1 (en) * 2000-05-19 2003-12-09 International Business Machines Corporation Coding system for high data volume
US6636848B1 (en) 2000-05-31 2003-10-21 International Business Machines Corporation Information search using knowledge agents
US7031908B1 (en) * 2000-06-01 2006-04-18 Microsoft Corporation Creating a language model for a language processing system
US7490092B2 (en) * 2000-07-06 2009-02-10 Streamsage, Inc. Method and system for indexing and searching timed media information based upon relevance intervals
US6869018B2 (en) * 2000-07-31 2005-03-22 Reallegal, Llc Transcript management software and methods therefor
US6785651B1 (en) * 2000-09-14 2004-08-31 Microsoft Corporation Method and apparatus for performing plan-based dialog
US6435849B1 (en) * 2000-09-15 2002-08-20 Paul L. Guilmette Fluid pump
JP4108948B2 (en) 2000-09-25 2008-06-25 富士通株式会社 Apparatus and method for viewing a plurality of documents
EP1344119A4 (en) * 2000-11-07 2007-03-07 Antaeus Healthcom Inc System for the creation of database and structured information from verbal input
CN1443329A (en) * 2000-11-22 2003-09-17 里科尔公司 System and methods for documenting medical findings of physical examination
US20020077833A1 (en) 2000-12-20 2002-06-20 Arons Barry M. Transcription and reporting system
US6937983B2 (en) 2000-12-20 2005-08-30 International Business Machines Corporation Method and system for semantic speech recognition
US20020087311A1 (en) 2000-12-29 2002-07-04 Leung Lee Victor Wai Computer-implemented dynamic language model generation method and system
US20020087315A1 (en) 2000-12-29 2002-07-04 Lee Victor Wai Leung Computer-implemented multi-scanning language method and system
US6714939B2 (en) 2001-01-08 2004-03-30 Softface, Inc. Creation of structured data from plain text
US20020099717A1 (en) * 2001-01-24 2002-07-25 Gordon Bennett Method for report generation in an on-line transcription system
WO2002082318A3 (en) * 2001-02-22 2003-10-02 Volantia Holdings Ltd System and method for extracting information
US6754626B2 (en) 2001-03-01 2004-06-22 International Business Machines Corporation Creating a hierarchical tree of language models for a dialog system based on prompt and dialog context
US7346521B2 (en) 2001-03-05 2008-03-18 Ims Health Incorporated System and methods for generating physician profiles concerning prescription therapy practices
US7366979B2 (en) * 2001-03-09 2008-04-29 Copernicus Investments, Llc Method and apparatus for annotating a document
WO2002073451A3 (en) * 2001-03-13 2004-03-11 Intelligate Ltd Dynamic natural language understanding
JP2002272990A (en) 2001-03-21 2002-09-24 Heiwa Corp Pattern display method for game machine
US6834264B2 (en) * 2001-03-29 2004-12-21 Provox Technologies Corporation Method and apparatus for voice dictation and document production
US20020147616A1 (en) 2001-04-05 2002-10-10 Mdeverywhere, Inc. Method and apparatus for introducing medical necessity policy into the clinical decision making process at the point of care
US7188064B2 (en) * 2001-04-13 2007-03-06 University Of Texas System Board Of Regents System and method for automatic semantic coding of free response data using Hidden Markov Model methodology
US6973428B2 (en) * 2001-05-24 2005-12-06 International Business Machines Corporation System and method for searching, analyzing and displaying text transcripts of speech after imperfect speech recognition
US7519529B1 (en) 2001-06-29 2009-04-14 Microsoft Corporation System and methods for inferring informational goals and preferred level of detail of results in response to questions posed to an automated information-retrieval or question-answering service
JP2003022091A (en) 2001-07-10 2003-01-24 Nippon Hoso Kyokai <Nhk> Method, device, and program for voice recognition
DE10138408A1 (en) * 2001-08-04 2003-02-20 Philips Corp Intellectual Pty A method of supporting the proof-reading of a voice-recognized text with matched to the recognition reliability playback speed profile
JP2003058559A (en) 2001-08-17 2003-02-28 Hitachi Eng Co Ltd Document classification method, retrieval method, classification system, and retrieval system
US7529685B2 (en) 2001-08-28 2009-05-05 Md Datacor, Inc. System, method, and apparatus for storing, retrieving, and integrating clinical, diagnostic, genomic, and therapeutic data
US20030065503A1 (en) * 2001-09-28 2003-04-03 Philips Electronics North America Corp. Multi-lingual transcription system
US20030069760A1 (en) 2001-10-04 2003-04-10 Arthur Gelber System and method for processing and pre-adjudicating patient benefit claims
JP4434536B2 (en) * 2001-10-10 2010-03-17 株式会社東芝 Electronic medical record system
US6708148B2 (en) * 2001-10-12 2004-03-16 Koninklijke Philips Electronics N.V. Correction device to mark parts of a recognized text
CA2461214A1 (en) * 2001-10-18 2003-04-24 Yeong Kuang Oon System and method of improved recording of medical transactions
US20030083903A1 (en) 2001-10-30 2003-05-01 Myers Gene E. Method and apparatus for contemporaneous billing and documenting with rendered services
WO2003038808A1 (en) * 2001-10-31 2003-05-08 Koninklijke Philips Electronics N.V. Method of and system for transcribing dictations in text files and for revising the texts
US20030101054A1 (en) * 2001-11-27 2003-05-29 Ncc, Llc Integrated system and method for electronic speech recognition and transcription
US20030105638A1 (en) * 2001-11-27 2003-06-05 Taira Rick K. Method and system for creating computer-understandable structured medical data from natural language reports
JP2003202895A (en) * 2002-01-10 2003-07-18 Sony Corp Interaction device and interaction control method, storage medium, and computer program
US20030144885A1 (en) * 2002-01-29 2003-07-31 Exscribe, Inc. Medical examination and transcription method, and associated apparatus
US20050154690A1 (en) 2002-02-04 2005-07-14 Celestar Lexico-Sciences, Inc Document knowledge management apparatus and method
US20030154085A1 (en) * 2002-02-08 2003-08-14 Onevoice Medical Corporation Interactive knowledge base system
US20030163348A1 (en) * 2002-02-27 2003-08-28 Stead William W. Method and system for clinical action support
US7257531B2 (en) * 2002-04-19 2007-08-14 Medcom Information Systems, Inc. Speech to text system using controlled vocabulary indices
US7716072B1 (en) * 2002-04-19 2010-05-11 Greenway Medical Technologies, Inc. Integrated medical software system
US20110301982A1 (en) * 2002-04-19 2011-12-08 Green Jr W T Integrated medical software system with clinical decision support
US8738396B2 (en) 2002-04-19 2014-05-27 Greenway Medical Technologies, Inc. Integrated medical software system with embedded transcription functionality
US7197460B1 (en) 2002-04-23 2007-03-27 At&T Corp. System for handling frequently asked questions in a natural language dialog service
US7869998B1 (en) * 2002-04-23 2011-01-11 At&T Intellectual Property Ii, L.P. Voice-enabled dialog system
US7292975B2 (en) * 2002-05-01 2007-11-06 Nuance Communications, Inc. Systems and methods for evaluating speaker suitability for automatic speech recognition aided transcription
US7548847B2 (en) * 2002-05-10 2009-06-16 Microsoft Corporation System for automatically annotating training data for a natural language understanding system
US7028038B1 (en) * 2002-07-03 2006-04-11 Mayo Foundation For Medical Education And Research Method for generating training data for medical text abbreviation and acronym normalization
US20040073458A1 (en) 2002-07-31 2004-04-15 Aviacode Inc. Method and system for processing medical records
US20040230404A1 (en) * 2002-08-19 2004-11-18 Messmer Richard Paul System and method for optimizing simulation of a discrete event process using business system data
US20060041836A1 (en) * 2002-09-12 2006-02-23 Gordon T J Information documenting system with improved speed, completeness, retriveability and granularity
US7016844B2 (en) * 2002-09-26 2006-03-21 Core Mobility, Inc. System and method for online transcription services
US8606594B2 (en) 2002-10-29 2013-12-10 Practice Velocity, LLC Method and system for automated medical records processing
US6996520B2 (en) 2002-11-22 2006-02-07 Transclick, Inc. Language translation system and method using specialized dictionaries
US7725330B2 (en) 2002-12-03 2010-05-25 Siemens Medical Solutions Usa, Inc. Systems and methods for automated extraction and processing of billing information in patient records
US7444285B2 (en) * 2002-12-06 2008-10-28 3M Innovative Properties Company Method and system for sequential insertion of speech recognition results to facilitate deferred transcription services
US7774694B2 (en) * 2002-12-06 2010-08-10 3M Innovation Properties Company Method and system for server-based sequential insertion processing of speech recognition results
JP4415546B2 (en) 2003-01-06 2010-02-17 三菱電機株式会社 Voice interaction processing apparatus and its program
JP4249534B2 (en) * 2003-01-15 2009-04-02 株式会社京三製作所 Data processing apparatus, data verification method, and data verification program
US20040148170A1 (en) * 2003-01-23 2004-07-29 Alejandro Acero Statistical classifiers for spoken language understanding and command/control scenarios
US7958443B2 (en) * 2003-02-28 2011-06-07 Dictaphone Corporation System and method for structuring speech recognized text into a pre-selected document format
JP5025261B2 (en) * 2003-03-31 2012-09-12 ニュアンス コミュニケーションズ オーストリア ゲーエムベーハー System for correcting the results of the voice recognition according to the instruction of the confidence level
WO2004097664A3 (en) 2003-05-01 2005-11-24 Axonwave Software Inc A method and system for concept generation and management
US20040243545A1 (en) * 2003-05-29 2004-12-02 Dictaphone Corporation Systems and methods utilizing natural language medical records
US8095544B2 (en) * 2003-05-30 2012-01-10 Dictaphone Corporation Method, system, and apparatus for validation
US7383172B1 (en) 2003-08-15 2008-06-03 Patrick William Jamieson Process and system for semantically recognizing, correcting, and suggesting domain specific speech
US8311835B2 (en) 2003-08-29 2012-11-13 Microsoft Corporation Assisted multi-modal dialogue
US20050065774A1 (en) * 2003-09-20 2005-03-24 International Business Machines Corporation Method of self enhancement of search results through analysis of system logs
US7860717B2 (en) * 2003-09-25 2010-12-28 Dictaphone Corporation System and method for customizing speech recognition input and output
US20050120300A1 (en) * 2003-09-25 2005-06-02 Dictaphone Corporation Method, system, and apparatus for assembly, transport and display of clinical data
JP2005122128A (en) * 2003-09-25 2005-05-12 Fuji Photo Film Co Ltd Speech recognition system and program
JP4495431B2 (en) * 2003-09-26 2010-07-07 株式会社湯山製作所 Icd code applying apparatus and method
US20050144184A1 (en) * 2003-10-01 2005-06-30 Dictaphone Corporation System and method for document section segmentation
US7996223B2 (en) * 2003-10-01 2011-08-09 Dictaphone Corporation System and method for post processing speech recognition output
US20050102140A1 (en) * 2003-11-12 2005-05-12 Joel Davne Method and system for real-time transcription and correction using an electronic communication environment
JP2005149083A (en) 2003-11-14 2005-06-09 Hitachi Medical Corp Electronic medical record input support apparatus
US20050137910A1 (en) 2003-12-19 2005-06-23 Rao R. B. Systems and methods for automated extraction and processing of billing information in patient records
US7542971B2 (en) 2004-02-02 2009-06-02 Fuji Xerox Co., Ltd. Systems and methods for collaborative note-taking
US8005835B2 (en) 2004-03-15 2011-08-23 Yahoo! Inc. Search systems and methods with integration of aggregate user annotations
JP2005267358A (en) 2004-03-19 2005-09-29 Hitachi Medical Corp Electronic medical charge formation/management system for local health care, and operation method thereof
JP2005284834A (en) * 2004-03-30 2005-10-13 Toshiba Corp Document input system, document input program, recording medium with document input program recorded, and document input method
US7379946B2 (en) * 2004-03-31 2008-05-27 Dictaphone Corporation Categorization of information using natural language processing and predefined templates
WO2005103978A3 (en) 2004-04-15 2007-02-01 Artifical Medical Intelligence System and method for automatic assignment of medical codes to unformatted data
US20050273365A1 (en) * 2004-06-04 2005-12-08 Agfa Corporation Generalized approach to structured medical reporting
US20050288930A1 (en) * 2004-06-09 2005-12-29 Vaastek, Inc. Computer voice recognition apparatus and method
JP4653976B2 (en) 2004-07-09 2011-03-16 Hoya株式会社 camera
JP2008506188A (en) * 2004-07-09 2008-02-28 ジェスチャーラド インコーポレイテッド Gesture-based reporting method and system
US20060020886A1 (en) * 2004-07-15 2006-01-26 Agrawal Subodh K System and method for the structured capture of information and the generation of semantically rich reports
US20060020492A1 (en) * 2004-07-26 2006-01-26 Cousineau Leo E Ontology based medical system for automatically generating healthcare billing codes from a patient encounter
US20060020466A1 (en) * 2004-07-26 2006-01-26 Cousineau Leo E Ontology based medical patient evaluation method for data capture and knowledge representation
GB2432704B (en) * 2004-07-30 2009-12-09 Dictaphone Corp A system and method for report level confidence
KR20060016933A (en) 2004-08-19 2006-02-23 함정우 Apparatus and method for classification document
US8412521B2 (en) 2004-08-20 2013-04-02 Multimodal Technologies, Llc Discriminative training of document transcription system
US20130304453A9 (en) * 2004-08-20 2013-11-14 Juergen Fritsch Automated Extraction of Semantic Content and Generation of a Structured Document from Speech
US7584103B2 (en) * 2004-08-20 2009-09-01 Multimodal Technologies, Inc. Automated extraction of semantic content and generation of a structured document from speech
US7650628B2 (en) * 2004-10-21 2010-01-19 Escription, Inc. Transcription data security
US20060161460A1 (en) 2004-12-15 2006-07-20 Critical Connection Inc. System and method for a graphical user interface for healthcare data
US20060129435A1 (en) * 2004-12-15 2006-06-15 Critical Connection Inc. System and method for providing community health data services
US7502741B2 (en) * 2005-02-23 2009-03-10 Multimodal Technologies, Inc. Audio signal de-identification
JP2006302057A (en) * 2005-04-22 2006-11-02 Gifu Prefecture Medical audio information processing apparatus and medical audio information processing program
US7849048B2 (en) 2005-07-05 2010-12-07 Clarabridge, Inc. System and method of making unstructured data available to structured data analysis tools
US7844464B2 (en) * 2005-07-22 2010-11-30 Multimodal Technologies, Inc. Content-based audio playback emphasis
US20070055552A1 (en) * 2005-07-27 2007-03-08 St Clair David System and method for health care data integration and management
US20070043761A1 (en) * 2005-08-22 2007-02-22 The Personal Bee, Inc. Semantic discovery engine
US7640158B2 (en) * 2005-11-08 2009-12-29 Multimodal Technologies, Inc. Automatic detection and application of editing patterns in draft documents
US20090228299A1 (en) * 2005-11-09 2009-09-10 The Regents Of The University Of California Methods and apparatus for context-sensitive telemedicine
US7957968B2 (en) * 2005-12-22 2011-06-07 Honda Motor Co., Ltd. Automatic grammar generation using distributedly collected knowledge
US7610192B1 (en) * 2006-03-22 2009-10-27 Patrick William Jamieson Process and system for high precision coding of free text documents against a standard lexicon
US8731954B2 (en) * 2006-03-27 2014-05-20 A-Life Medical, Llc Auditing the coding and abstracting of documents
US8121838B2 (en) * 2006-04-11 2012-02-21 Nuance Communications, Inc. Method and system for automatic transcription prioritization
WO2007120904A3 (en) * 2006-04-14 2008-12-04 Fuzzmed Inc System, method, and device for personal medical care, intelligent analysis, and diagnosis
US20070282640A1 (en) * 2006-05-26 2007-12-06 Allmed Resources Llc Healthcare information accessibility and processing system
WO2007150004A3 (en) * 2006-06-22 2008-11-06 Multimodal Technologies Inc Verification of extracted data
US7844470B2 (en) * 2006-07-25 2010-11-30 Siemens Medical Solutions Usa, Inc. Treatment order processing system suitable for pharmacy and other use
EP2095363A4 (en) * 2006-11-22 2011-07-20 Multimodal Technologies Inc Recognition of speech in editable audio streams
US8356245B2 (en) * 2007-01-05 2013-01-15 International Business Machines Corporation System and method of automatically mapping a given annotator to an aggregate of given annotators
US20080228769A1 (en) 2007-03-15 2008-09-18 Siemens Medical Solutions Usa, Inc. Medical Entity Extraction From Patient Data
US7917355B2 (en) * 2007-08-23 2011-03-29 Google Inc. Word detection
US7383183B1 (en) 2007-09-25 2008-06-03 Medquist Inc. Methods and systems for protecting private information during transcription
EP2212772A4 (en) 2007-10-17 2017-04-05 VCVC lll LLC Nlp-based content recommender
US20090192822A1 (en) 2007-11-05 2009-07-30 Medquist Inc. Methods and computer program products for natural language processing framework to assist in the evaluation of medical care
US7933777B2 (en) * 2008-08-29 2011-04-26 Multimodal Technologies, Inc. Hybrid speech recognition
CA2680304C (en) * 2008-09-25 2017-08-22 Multimodal Technologies, Inc. Decoding-time prediction of non-verbalized tokens
US8290961B2 (en) 2009-01-13 2012-10-16 Sandia Corporation Technique for information retrieval using enhanced latent semantic analysis generating rank approximation matrix by factorizing the weighted morpheme-by-document matrix
US20100250236A1 (en) 2009-03-31 2010-09-30 Medquist Ip, Llc Computer-assisted abstraction of data and document coding
JP5687269B2 (en) 2009-05-14 2015-03-18 コレクシス・ホールディングス・インコーポレーテッド Methods and systems for knowledge discovery
US20110173153A1 (en) 2010-01-08 2011-07-14 Vertafore, Inc. Method and apparatus to import unstructured content into a content management system
US8924394B2 (en) 2011-02-18 2014-12-30 Mmodal Ip Llc Computer-assisted abstraction for reporting of quality measures
US9471878B2 (en) 2014-07-11 2016-10-18 International Business Machines Corporation Dynamic mathematical validation using data mining

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6915254B1 (en) * 1998-07-30 2005-07-05 A-Life Medical, Inc. Automatically assigning medical codes using natural language processing
US20070237427A1 (en) * 2006-04-10 2007-10-11 Patel Nilesh V Method and system for simplified recordkeeping including transcription and voting based verification

Also Published As

Publication number Publication date Type
US20070299651A1 (en) 2007-12-27 application
CA2650816C (en) 2015-10-27 grant
JP5385134B2 (en) 2014-01-08 grant
WO2007150005A3 (en) 2008-10-09 application
US8321199B2 (en) 2012-11-27 grant
EP2030198A4 (en) 2012-04-25 application
US20140149114A1 (en) 2014-05-29 application
WO2007150004A2 (en) 2007-12-27 application
EP2030196B1 (en) 2018-09-05 grant
WO2007150005A2 (en) 2007-12-27 application
JP2014197223A (en) 2014-10-16 application
US9892734B2 (en) 2018-02-13 grant
CA2652444A1 (en) 2007-12-27 application
US8560314B2 (en) 2013-10-15 grant
JP2010512561A (en) 2010-04-22 application
CA2652441A1 (en) 2007-12-27 application
EP2030197A2 (en) 2009-03-04 application
US7716040B2 (en) 2010-05-11 grant
EP2030196A4 (en) 2017-05-17 application
WO2007150004A3 (en) 2008-11-06 application
EP2030196A2 (en) 2009-03-04 application
US20100211869A1 (en) 2010-08-19 application
US8768694B2 (en) 2014-07-01 grant
JP2009541865A (en) 2009-11-26 application
US20070299665A1 (en) 2007-12-27 application
US20070299652A1 (en) 2007-12-27 application
CA2650816A1 (en) 2007-12-27 application
EP2030198B1 (en) 2018-08-29 grant
EP2030197A4 (en) 2012-04-04 application
US8521514B2 (en) 2013-08-27 grant
CA2652441C (en) 2014-09-23 grant
JP5167256B2 (en) 2013-03-21 grant
JP2009541800A (en) 2009-11-26 application
US20140039880A1 (en) 2014-02-06 application
EP2030198A2 (en) 2009-03-04 application
JP5964358B2 (en) 2016-08-03 grant
US20120296639A1 (en) 2012-11-22 application
US20180166081A1 (en) 2018-06-14 application
US20130346074A1 (en) 2013-12-26 application
WO2007150006A3 (en) 2008-10-09 application
WO2007150006A2 (en) 2007-12-27 application

Similar Documents

Publication Publication Date Title
Pasha et al. MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic.
US6182029B1 (en) System and method for language extraction and encoding utilizing the parsing of text data in accordance with domain parameters
US8032372B1 (en) Dictation selection
US7805299B2 (en) Method and apparatus for improving the transcription accuracy of speech recognition software
US7502741B2 (en) Audio signal de-identification
US7233938B2 (en) Systems and methods for coding information
US20030212544A1 (en) System for automatically annotating training data for a natural language understanding system
US20060074656A1 (en) Discriminative training of document transcription system
US20080201130A1 (en) Text Segmentation and Label Assignment with User Interaction by Means of Topic Specific Language Models and Topic-Specific Label Statistics
US7693717B2 (en) Session file modification with annotation using speech recognition or text to speech
US20060020493A1 (en) Ontology based method for automatically generating healthcare billing codes from a patient encounter
US7426468B2 (en) Method and apparatus for improving the transcription accuracy of speech recognition software
US20070271086A1 (en) Topic specific models for text formatting and speech recognition
US20060089857A1 (en) Transcription data security
US7379946B2 (en) Categorization of information using natural language processing and predefined templates
US7809565B2 (en) Method and apparatus for improving the transcription accuracy of speech recognition software
US20070244700A1 (en) Session File Modification with Selective Replacement of Session File Components
US20040243614A1 (en) Method, system, and apparatus for validation
US8041565B1 (en) Precision speech to text conversion
US20070033026A1 (en) System for speech recognition and correction, correction device and method for creating a lexicon of alternatives
US7668718B2 (en) Synchronized pattern recognition source data processed by manual or automatic means for creation of shared speaker-dependent speech user profile
US20090254345A1 (en) Intelligent Text-to-Speech Conversion
US7613610B1 (en) Transcription data extraction
US20140172417A1 (en) Vital text analytics system for the enhancement of requirements engineering documents and other documents
US8046226B2 (en) System and methods for reporting

Legal Events

Date Code Title Description
AS Assignment

Owner name: MMODAL IP LLC, TENNESSEE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KOLL, DETLEF;FINKE, MICHAEL;REEL/FRAME:034636/0171

Effective date: 20070621

AS Assignment

Owner name: MULTIMODAL TECHNOLOGIES, INC., PENNSYLVANIA

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE NAME AND ADDRESS OF THE ASSIGNEE PREVIOUSLY RECORDED ON REEL 034636 FRAME 0171. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT;ASSIGNORS:KOLL, DETLEF;FINKE, MICHAEL;REEL/FRAME:040517/0760

Effective date: 20070621

AS Assignment

Owner name: MMODAL IP LLC, TENNESSEE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MULTIMODAL TECHNOLOGIES, INC.;REEL/FRAME:040641/0117

Effective date: 20121026