Mmodal IP LLC

Multimodal Technologies, LLC

3m Innovative Properties Company

Juergen Fritsch

Detlef Koll

Michael Finke

Girija Yegnanarayanan

Monika Woszczyna

Lambert Leo Mathias

Kjell Schubert

Vasudevan Jagannathan

Koll Detlef

Jonathan Alan Handler

Anoop Deoras

Anna Abovyan

Christopher Scott

Christopher Currivan

An automated system updates electronic medical records (EMRs) based on dictated reports, without requiring manual data entry into on-screen forms. A dictated report is transcribed by an automatic speech recognizer, and facts are extracted from the report and stored in encoded form. Information from a patient's report is also stored in encoded form. The resulting encoded information from the report and EMR are reconciled with each other, and changes to be made to the EMR are identified based on the reconciliation. The identified changes are made to the EMR automatically, without requiring manual data entry into the EMR.

Clinical data reconciliation as part of a report generation solution

A graphical user interface, referred to herein as a virtual whiteboard, that provides both: (1) an automatically prioritized display of information related to a particular patient that is tailored to the current user of the system, and (2) a 'scratch pad' area in which multiple users of the system may input free-form text and other data for sharing with other users of the system. When each user of the system accesses the virtual whiteboard, the system: (1) automatically prioritizes the patient information based on characteristics of the user and displays the automatically prioritized patient information to that user, and (2) displays the contents of the scratch pad to the user. As a result, the whiteboard displays both information that is tailored to the current user and information that is common to all users (i.e., not tailored to any particular user).

Collaborative synthesis-based clinical documentation

An automated system updates electronic medical records (EMRs) based on dictated reports, without requiring manual data entry into on-screen forms. A dictated report is transcribed by an automatic speech recognizer, and facts are extracted from the report and stored in encoded form. Information from a patient's report is also stored in encoded form. The resulting encoded information from the report and EMR are reconciled with each other, and changes to be made to the EMR are identified based on the reconciliation. The identified changes are made to the EMR automatially, without requiring manual data entry into the EMR.

A system includes a data record (such as an Electronic Medical Record (EMR)) and a user interface for modifying (e.g., storing data in) the data record. The data record includes both free-form text elements and discrete data elements. The user interface includes user interface elements for receiving free-form text data. In response to receiving free-form text data via the free-form text user interface elements, a suggested action is identified, such as a suggested action to take in connection with one of the discrete data elements of the data record. Output is generated representing the suggested action. A user provides input indicating acceptance or rejection of the suggested action. The suggested action may be performed in response to the user input.

Maintaining a discrete data representation that corresponds to information contained in free-form text

An automatic speech recognizer is used to produce a structured document representing the contents of human speech. A best practice is applied to the structured document to produce a conclusion, such as a conclusion that required information is missing from the structured document. Content is inserted into the structured document based on the conclusion, thereby producing a modified document. The inserted content may be obtained by prompting a human user for the content and receiving input representing the content from the human user.

Document extension in dictation-based document generation workflow

Non-verbalized tokens, such as punctuation, are automatically predicted and inserted into a transcription of speech in which the tokens were not explicitly verbalized. Token prediction may be integrated with speech decoding, rather than performed as a post-process to speech decoding.

Decoding-time prediction of non-verbalized tokens

Embodiments of the present invention are directed to computer systems for implementing dynamic, data-driven workflows within healthcare and other environments. Such a system may include a computer-processable definition of one or more workflows. Each workflow definition may define various aspects of the corresponding workflow, such as the data required by the workflow, a process for extracting such data from a variety of structured and/or unstructured data sources, a set of process steps to be performed within the workflow, and a condition for triggering the workflow. The system may use the workflow definition to extract the data required by the workflow and to perform the workflow's process steps on the extracted data in response to determining that the workflow's trigger condition has been satisfied. The workflow may change in response to changes in data extracted by the workflow.

Automated clinical evidence sheet workflow

A system includes a document corpus containing structured documents, which contain both text and annotations of the text. The system also includes a search engine which is adapted to perform structured searches of the structured documents. As new types of annotations are added to the system, the search engine is updated automatically to become capable of performing structured searches for the new types of annotations. For example, if a new natural language processing (NLP) component, adapted to generate annotations of a new type, is added to the system, then the system automatically updates a query language to include a definition of the new type of annotation. The search engine may then immediately be capable of processing structured queries which refer to the new type of annotation.

Structured searching of dynamic structured document corpuses

A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Document transcription system training

A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Discriminative training of document transcription system

A dataset is searched using inclusion set criteria to produce an inclusion set and exclusion set criteria to produce an exclusion set. A set of unique content elements is identified from the inclusion set and the exclusion set. Metrics are derived from the inclusion set, exclusion set, and set of unique content elements, such as a measure, for each unique content element, of the absolute value of the difference between the percentage of records in the inclusion set containing the unique content element and the percentage of records in the exclusion set containing the unique content element. The unique content element set may be sorted and displayed in decreasing order of the above-referenced absolute value. The content element set may be filtered. Individual content elements may be excluded from the content set. A predictive model may be generated based on the resulting version of the content element set.

User interface for predictive model generation

Techniques are disclosed for facilitating the process of proofreading draft transcripts of spoken audio streams. In general, proofreading of a draft transcript is facilitated by playing back the corresponding spoken audio stream with an emphasis on those regions in the audio stream that are highly relevant or likely to have been transcribed incorrectly. Regions may be emphasized by, for example, playing them back more slowly than regions that are of low relevance and likely to have been transcribed correctly. Emphasizing those regions of the audio stream that are most important to transcribe correctly and those regions that are most likely to have been transcribed incorrectly increases the likelihood that the proofreader will accurately correct any errors in those regions, thereby improving the overall accuracy of the transcript.

Growing community of inventors

Pittsburgh, PA, United States of America

Juergen Fritsch