System and method enabling bi-translation for improved prescription accuracy

• US 9,230,222 B2
• Filed: 07/21/2009
• Issued: 01/05/2016
• Est. Priority Date: 07/23/2008
• Status: Active Grant

• Current Assignee: Noel J. Guillama
• Original Assignee: Noel J. Guillama, Quantum Group Inc.
• Inventors: Heath, Chester, Martinez, Pedro, Guillama, Noel
• Primary Examiner(s): BAKER, MATTHEW H
• Application Number:
  US12/506,570
• Publication Number:
  US 20100023312A1
• Time in Patent Office: 2,359 Days
• Field of Search: 704/257, 704/235, 704/270
• US Class Current: 1/1
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A system for bi-translation of speech and writing is provided. The system can comprise one or more electronic data processors contained within one or more computing devices. The system can also include a module configured to execute on the one or more electronic data processors in order to record a spoken and written segment into the one or more computing devices, where the segments can be corroborated by selecting potential medications and processes. The module can also be configured to convert the spoken segment into a stream of text or tokens and the written segment into a stream of text or tokens. Furthermore, the module can be configured to compare the converted spoken and written streams of text or tokens to determine whether the spoken segment and the written segment match and output the results.

Claims

1. A computer-based method for bi-translation of speech and writing, the method comprising:

recording, at separate times, a spoken segment and a written segment from a prescriber into at least one computing device, wherein the spoken segment and the written segment can be corroborated by selecting potential medications and processes, the written segment comprising handwriting, the recording comprising determining that a beginning and an end of each of the spoken segment and the written segment are undetectable and, in response to determining that the beginning and the end of each of the spoken segment and the written segment are undetectable, prompting the prescriber to re-record the spoken segment and the written segment;

converting the spoken segment into a first stream of text or tokens and the written segment into a second stream of text or tokens;

comparing the first stream and the second stream to determine whether the spoken segment and the written segment match and concurrently displaying the first stream and the second stream;

in response to determining that the spoken segment and the written segment match, configuring the at least one computing device to permit a prescriber to verify, via the at least one computing device, the results of the comparing; and

in response to determining that the spoken segment and the written segment do not match, providing an alert for the prescriber at the at least one computing device and configuring the at least one computing device to permit a prescriber to select, via the at least one computing device, the correct text sequence from alternatives displayed on the at least one computing device and a correct medication for the text sequence from a list of medications displayed on the at least one computing device.

2. The method of claim 1, wherein the recording step is initiated and completed by selecting at least one of icons and characters on the at least one computing device.

3. A computer-based system for bi-translation of speech and writing, the system comprising:

at least one electronic data processor contained within at least one computing device; and

a module configured to execute on the at least one electronic data processor, wherein the module is configured to;

record, at separate times, a spoken segment and written segment from a prescriber into the at least one computing device, wherein the spoken segment and the written segment can be corroborated by selecting potential medications and processes, the written segment comprising handwriting, the recording comprising determining that a beginning and an end of each of the spoken segment and the written segment are undetectable and, in response to determining that the beginning and the end of each of the spoken segment and the written segment are undetectable, prompting the prescriber to re-record the spoken segment and the written segment;

convert the spoken segment into a first stream of text or tokens and the written segment into a second stream of text or tokens;

compare the first stream to the second stream to determine whether the spoken segment and the written segment match and concurrently display the first stream and the second stream;

in response to determining that the spoken segment and the written segment match, configure the at least one computing device to permit a prescriber to verify, via the at least one computing device, the results of the comparing; and

in response to determining that the spoken segment and the written segment do not match, provide an alert for the prescriber at the at least one computing device and configure the at least one computing device to permit a prescriber to select, via the at least one computing device, the correct text sequence from alternatives displayed on the at least one computing device and a correct medication for the text sequence from a list of medications displayed on the at least one computing device.

4. The system of claim 3, wherein the module is configured to initiate and complete a recording by enabling a user to select at least one of icons and characters on the at least one computing device.

5. A non-transitory computer-readable storage medium having stored therein computer-readable instructions, which, when loaded in and executed by a computer causes the computer to perform the steps of:

recording, at separate times, a spoken segment and a written segment from a prescriber into at least one computing device, wherein the spoken segment and the written segment can be corroborated by selecting potential medications and processes, the written segment comprising handwriting, the recording comprising determining that a beginning and an end of each of the spoken segment and the written segment are undetectable and, in response to determining that the beginning and the end of each of the spoken segment and the written segment are undetectable, prompting the prescriber to re-record the spoken segment and the written segment;

converting the spoken segment into a first stream of text or tokens and the written segment into a second stream of text or tokens;

comparing the first stream and the second stream to determine whether the spoken segment and the written segment match and concurrently displaying the first stream and the second stream;

in response to determining that the spoken segment and the written segment match, configuring the at least one computing device to permit a prescriber to verify, via the at least one computing device, the results of the comparing; and

in response to determining that the spoken segment and the written segment do not match, providing an alert for the prescriber at the at least one computing device and configuring the at least one computing device to permit a prescriber to select, via the at least one computing device, the correct text sequence from alternatives displayed on the at least one computing device and a correct medication for the text sequence from a list of medications displayed on the at least one computing device.

6. The non-transitory computer-readable storage medium of claim 5, wherein the recording step is initiated and completed by selecting at least one of icons and characters on the at least one computing device.