ASTM E2364-04(2010)
(Guide)Standard Guide to Speech Recognition Technology Products in Health Care (Withdrawn 2019)
Standard Guide to Speech Recognition Technology Products in Health Care (Withdrawn 2019)
SIGNIFICANCE AND USE
This guide is intended to provide general guidelines toward the design and utilization of SRT products used for healthcare documentation. It is intended to recommend the essential elements required of SRT systems in healthcare.
This guide will not identify specific products or make recommendations regarding specific vendors or their products or services.
A well-edited SRT document may result in improved quality over current methods of documentation, that is, handwritten notes and improved productivity over traditional dictation and transcription.
Faster turnaround times.
Legible documentation over handwriting has many advantages:
Improved patient care communication.
Enhanced patient safety.
Reduced malpractice risks.
Facilitation of appropriate reimbursement.
For the medical transcriptionist and/or SRMTE, decreased repetitive stress injuries, such as neck, arm, wrist, and heel pain.
Facilitation of cost controls related to document completion.
Better utilization of medical language skills of MTs as productivity is not limited by keyboarding skills.
SCOPE
1.1 This guide identifies system types and describes various features of speech recognition technology (SRT) products used to create the healthcare record. This will assist users (health information professionals, medical report originators, administrators, medical transcriptionists, speech recognition medical transcription editors (SRMTEs), system integrators, support personnel, trainers, and others) to make informed decisions relating to the design and utilization of SRT systems.
1.2 This guide does not address the following items:
1.2.1 System and data (voice and text) security.
1.2.2 Administrative processes such as authentication of the document, productivity measurements, etc.
WITHDRAWN RATIONALE
This guide identifies system types and describes various features of speech recognition technology (SRT) products used to create the healthcare record.
Formerly under the jurisdiction of Committee E31 on Healthcare Informatics, this guide was withdrawn in January 2019 in accordance with section 10.6.3 of the Regulations Governing ASTM Technical Committees, which requires that standards shall be updated by the end of the eighth year since the last approval date.
General Information
Relations
Standards Content (Sample)
NOTICE: This standard has either been superseded and replaced by a new version or withdrawn.
Contact ASTM International (www.astm.org) for the latest information
Designation: E2364 − 04 (Reapproved 2010)
Standard Guide to
Speech Recognition Technology Products in Health Care
This standard is issued under the fixed designation E2364; the number immediately following the designation indicates the year of
original adoption or, in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. A
superscript epsilon (´) indicates an editorial change since the last revision or reapproval.
1. Scope E2185 Specification for Transferring Digital Voice Data
Between Independent Digital Dictation Systems and
1.1 This guide identifies system types and describes various
Workstations (Withdrawn 2010)
features of speech recognition technology (SRT) products used
E2344 GuideforDataCapturethroughtheDictationProcess
to create the healthcare record. This will assist users (health
2.2 Other Documents:
information professionals, medical report originators,
Resource Interchange File Format (RIFF) Standard
administrators, medical transcriptionists, speech recognition
medical transcription editors (SRMTEs), system integrators,
3. Terminology
support personnel, trainers, and others) to make informed
3.1 Definitions:
decisions relating to the design and utilization of SRT systems.
3.1.1 acoustic model, n—phoneme map of user.
1.2 This guide does not address the following items:
3.1.2 authentication, n—the process of confirming author-
1.2.1 System and data (voice and text) security.
ship of an entry or of a document, for example, by verifying
1.2.2 Administrative processes such as authentication of the
with a written signature, identifiable initials, computer key, or
document, productivity measurements, etc.
other methods.
1.3 This international standard was developed in accor-
3.1.3 author, n—person responsible for content of text file.
dance with internationally recognized principles on standard-
ization established in the Decision on Principles for the
3.1.4 back-end system, n—delayed processing for document
Development of International Standards, Guides and Recom- completion.
mendations issued by the World Trade Organization Technical
3.1.5 compound file, n—a file containing recorded voice
Barriers to Trade (TBT) Committee.
with its transcribed text.
3.1.6 context, n—a long list of vocabulary words and
2. Referenced Documents
phrases used for the particular subject matter, with their
2.1 ASTM Standards:
spellings and pronunciations, statistical information about
E1902 Specification for Management of the Confidentiality
usageofeachwordaloneandincombination.Forexample,the
and Security of Dictation, Transcription, and Transcribed
context may include the number of times that “right,”
Health Records (Withdrawn 2011)
“Wright,” “turn right,” “right turn,” “right hand,” and “Mr.
E1985 Guide for User Authentication and Authorization
Wright” occur in a body of text. It also includes grammar and
(Withdrawn 2017)
styleinformation.Languagemodel,lexicon,topic,andvocabu-
E2084 Specification for Authentication of Healthcare Infor-
lary are terms that are all used synonymously with context.
mation Using Digital Signatures (Withdrawn 2009)
3.1.7 digital signature, n—data associated with, or a cryp-
E2184 Specification for Healthcare Document Formats
tographic transformation of, a data unit that allows a recipient
(Withdrawn 2011)
to prove the source and integrity of the data unit and protect
against forgery, for example, by the recipient.
3.1.8 edit, v—to review the document while listening to the
This guide is under the jurisdiction of ASTM Committee E31 on Healthcare
originator’s recorded voice and reading the associated tran-
Informatics and is the direct responsibility of Subcommittee E31.15 on Healthcare
scribed text (compound file), checking for recognition errors
Information Capture and Documentation.
Current edition approved March 1, 2010. Published August 2010. Originally and correcting document formatting and other inconsistencies.
approved in 2004. Last previous edition approved in 2004 as E2364–04. DOI:
When the SRMTE is not the originator, the SRMTE may need
10.1520/E2364-04R10.
to flag the document for originator/author clarification of
For referenced ASTM standards, visit the ASTM website, www.astm.org, or
unclear content or intent.
contact ASTM Customer Service at service@astm.org. For Annual Book of ASTM
Standards volume information, refer to the standard’s Document Summary page on
3.1.9 encryption, n—the process of transforming plain text
the ASTM website.
(readable) into cipher text (unreadable) for the purpose of
The last approved version of this historical standard is referenced on
www.astm.org. security and privacy.
Copyright © ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959. United States
E2364 − 04 (2010)
3.1.10 front-end system, n—a system incorporating real- 3.1.31 voice enrollment, n—the process whereby a user
time recognition and may include real-time self-editing by the reads aloud selected text so the SRT software can map or
originator. record the user’s speech sound pattern (phonemes).
3.1.32 voice file, n—digitalized audio message representing
3.1.11 language model, n—context specific to medical
voice input.
specialty, user, or practice setting.
3.1.33 voice macros, n—stored keystrokes that are activated
3.1.12 lossless compression, n—a lossless compression re-
by a voice command.
duces the amount of data required to represent the original
voice file but has no impact on sound quality. The original file 3.1.34 WAV, n—voice file format.
can be replicated precisely at any time.
3.2 Acronyms:
3.1.13 lossy compression, n—a lossy compression loses 3.2.1 MT—medical transcriptionist
someinformation,resultingindegradationofthesoundquality
3.2.2 SRMTE—speech recognition medical transcription
inherent in the original voice file and an inability to precisely
editor
regenerate that original file.
3.2.3 RIFF—resource interchange file format
3.1.14 microphone, n—an instrument whereby sound waves
3.2.4 SRT—speech recognition technology
are caused to generate or modulate an electric current usually
forthepurposeoftransmittingorrecordingsound(asspeechor 4. Significance and Use
music).
4.1 This guide is intended to provide general guidelines
toward the design and utilization of SRT products used for
3.1.15 microphone element, n—the component within the
healthcare documentation. It is intended to recommend the
microphone that does the actual conversion from sound waves
essential elements required of SRT systems in healthcare.
to electrical signals.
4.2 This guide will not identify specific products or make
3.1.16 natural language processing, n—method used in
recommendations regarding specific vendors or their products
artificial intelligence to process and derive interpretation of
or services.
human language.
4.3 A well-edited SRT document may result in improved
3.1.17 networked system, n—system connected to a net-
quality over current methods of documentation, that is, hand-
work.
written notes and improved productivity over traditional dic-
3.1.18 “normal” dictation, n—routine phrases or para-
tation and transcription.
graphs.
4.3.1 Faster turnaround times.
3.1.19 originator, n—person who provides oral input or
4.3.2 Legible documentation over handwriting has many
dictation, not necessarily the person responsible for the con- advantages:
tent.
4.3.2.1 Improved patient care communication.
4.3.2.2 Enhanced patient safety.
3.1.20 phoneme, n—smallest unit of sound in a spoken
4.3.2.3 Reduced malpractice risks.
language.
4.3.2.4 Facilitation of appropriate reimbursement.
3.1.21 prompts, n—reminders provided in order to complete
4.3.3 For the medical transcriptionist and/or SRMTE, de-
a task.
creased repetitive stress injuries, such as neck, arm, wrist, and
heel pain.
3.1.22 real-time recognition, n—simultaneous speech-to-
4.3.4 Facilitation of cost controls related to document
text transcription.
completion.
3.1.23 RecO—speech recognition error
4.3.5 Better utilization of medical language skills of MTs as
3.1.24 RIFF file, n—Resource Interchange File Format
productivity is not limited by keyboarding skills.
(RIFF) is self-descriptive; that is, the voice file format is
5. Speech Recognition Technology Systems
defined within the file.
5.1 Speech recognition technology (SRT) is designed to
3.1.25 speech recognition, n—computerized transcription of
capture voice and transcribe that speech into text. This can be
speech to text.
done by a single user working at a standalone computer or by
3.1.26 speech recognition medical transcription editor,
a large group of users working on a network. Another method
n—medical transcriptionist who edits compound files and/or
is processing a pre-recorded digital voice file through an SRT
the SRT language model.
system, with the resulting text and/or SRT engine being edited
by the MTE.
3.1.27 SRT engine, n—speech recognition processor.
5.2 Speech recognition technology system workflow.
3.1.28 standalone system, n—system not connected to a
5.2.1 Front-end speech recognition process involves:
network.
5.2.1.1 Recording the voice.
3.1.29 synchronization, v—having voice and text matched
5.2.1.2 SRT transcription of the voice file to text.
such as in a point-and-play manner.
5.2.1.3 Editing may be done by the originator and/or
3.1.30 text file, n—a file that contains text message. SRMTE.
E2364 − 04 (2010)
5.2.1.4 Compound file may be saved as an option. (1) The networked system may be programmed for a single
5.2.1.5 Text file can be printed, archived, transmitted, or medicalspecialtyorsubspecialty,suchasradiology,pathology,
family practice, physical therapy, or emergency medicine.
integrated into an electronic health record.
(2) A networked system may also be programmed with
5.2.1.6 Update the SRT context for RecOs and new termi-
many contexts or language models so originators from many
nology.
different medical specialties can use it to improve speech
5.2.2 Back-end speech recognition process involves:
recognition accuracy.
5.2.2.1 Recording the voice.
5.2.4.4 Editing may be done in the same facility, or the
5.2.2.2 Transmitting the voice file to the speech recognition
compound files may be sent to a remote SRMTE.
engine.
5.2.4.5 Input devices.
5.2.2.3 SRT transcription of the voice file to text.
(1) Noise-canceling SRT microphones.
5.2.2.4 Saving the voice and text as a compound file.
(2) Handheld digital recorders.
5.2.2.5 Routing the compound file to the SRMTE.
(3) Digital dictation systems.
5.2.2.6 Editing done by the SRMTE.
(4) Telephone.
5.2.2.7 Saving the text file.
5.2.4.6 The following scenarios are offered to give the
5.2.2.8 Returning the edited text file to the originator for
reader examples of how these systems work. They are not
authentication.
intendedtorepresenteverypossiblescenarioforthesesystems.
5.2.2.9 SRMTE updates the SRT context for RecOs and
(1) Six radiologists simultaneously dictate at individual
new terminology.
workstations. Each voice file is routed to a recognition server,
5.2.3 Standalone SRT System:
or the processing may take place on each workstation, with
5.2.3.1 Only one person at a time can use a standalone
information regarding the originator’s specialty and
system.
identification, allowing the recognition server to load the
5.2.3.2 Context is limited by the hard drive space.
corresponding acoustic model and context. The voice file is
5.2.3.3 Editing is done locally, at the point of input, either
processed by the SRT engine and the resulting compound file
by the originator or by the SRMTE.
(voice and text files) is routed to the SRMTE for editing. The
5.2.3.4 Input devices.
SRMTE may also be responsible for editing the SRT context.
(1) Noise-canceling SRT microphones.
(2) A hospital has 300 healthcare providers dictating into
(2) Handheld digital recorders.
portable handheld digital recording devices from the hospital
(3) Digital dictation systems.
and several remote satellite clinics, or dictation may take place
(4) Telephones.
on individual workstations. The voice files are encrypted and
5.2.3.5 The following scenarios are offered to give the
securely transmitted to the digital dictation system of a
reader examples of how these systems work. They are not
contracted transcription company. Each voice file is routed to a
intendedtorepresenteverypossiblescenarioforthesesystems.
recognition server, or the processing may take place on
(1) A radiologist (originator) dictates into a microphone
workstations, with information regarding the originator’s spe-
connected to a personal computer running an SRT program.
cialtyandidentification,allowingtherecognitionservertoload
The voice is translated to text in real time. The originator edits
the corresponding acoustic model and context.The voice file is
the text and/or the SRT context.
processed by the SRT engine and the resulting compound file
(2) A family practitioner dictates into a personal computer
(voice and text files) is routed to the SRMTE for editing.
throughout the day. Each compound file is saved and then,
SRMTEs working both in the office and remotely receive
using the same computer, the SRMTE edits the text, listening
recognized compound files via encrypted Internet transmis-
to the recorded voice as necessary for clarification. The
sions. The editing is performed on standalone computers and
SRMTE may also be responsible for editing the SRT context.
the encrypted text files are returned. The SRMTE may also be
(3) A group of cardiologists dictate into handheld digital
responsible for editing the SRT context.
recording devices throughout the day. The voice files are
transmittedfromtherecorderstoacomputerandrecognizedby
6. Training
the SRT engine, using the cardiology context and each physi-
cian’s acoustic model. Once recognized, each text file is edited
6.1 Originators:
by the SRMTE. The SRMTE may also be responsible for
6.1.1 Voice enrollment and proper position of microphone
editing the SRT context.
and proper placement of microphone element.
5.2.4 Networked SRT System:
6.1.2 Build customized language model.
5.2.4.1 On a networked system, all files containing recorded
6.1.3 Build “normal” dictations per user.
dictation(voicefiles)aretransmittedtoaserver,wherethefiles
6.1.4 Develop skill sets.
are queued up for recognition. The compound files are then
6.1.4.1 Proper correction technique for a RecO.
routed to the SRMTE for editing.
6.1.4.2 Navigation/mobility skills for moving around in the
5.2.4.2 A networked system is designed to allow multiple
document.
originators and SRMTEs to work simultaneously. The voice
6.1.4.3 Editing skills specific to SRT products.
files are recognized on a server or at the workstation(s) and the
6.1.4.4 Editing language model.
resulting compound fi
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.