Researchers Submit Patent Application, “Express Tracking For Patient Flow Management In A Distributed Environment”, for Approval (USPTO 20200134571)

2020 MAY 20 (NewsRx) -- By a News Reporter-Staff News Editor at Hospital & Nursing Home Daily -- From Washington, D.C., NewsRx journalists report that a patent application by the inventors Demick, Michael (Wake Forest, NC); Wright, Mark (Tobaccoville, NC), filed on October 30, 2019, was made available online on April 30, 2020.

The patent’s assignee is Laboratory Corporation of America Holdings (Burlington, North Carolina, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Patient flow is the movement of patients through a healthcare facility. It involves the medical care, physical resources, and internal systems needed to get patients from the point of admission to the point of discharge while maintaining quality and patient/provider satisfaction. Improving patient flow is a critical component of process management in hospitals and other healthcare facilities. Patient flow is primarily associated with hospitals and doctor’s offices, especially with back-ups, overcrowding, and inefficient scheduling. However, patient flow problems are not isolated to hospitals and doctor’s offices, patient flow problems also exist in ancillary healthcare services such as radiology centers, medical laboratories, respiratory therapy offices, dialysis centers, chemotherapy centers, urgent care clinics, etc.

“Conventional patient flow management systems resemble any complex queueing network in that delays are reduced through: (1) synchronization of work among service stages (e.g., coordination of patient intake, diagnosis processes, medical testing, treatments, and discharge processes), (2) automation of information gathering and data processing, (3) scheduling of resources (e.g., doctors, nurses, technicians, service providers, etc.) to match patterns of arrival, and (4) constant system monitoring (e.g., tracking number of patients waiting by location, diagnostic grouping and acuity) linked to immediate actions. In order to improve upon conventional techniques for managing patient flow, a primary goal for patient flow management systems has been to optimize resource management such as scheduling beds and services for patients, optimize monitoring of the patient flow in real-time, and provide intuitive analysis of incoming data to provide solutions for problems that arise in the patient flow. Although conventional patient flow management systems achieve some success in reducing patient wait times, decreasing costs associated with poor patient flow (e.g., wasted resources), and reducing lost opportunities (e.g., walk-outs), these systems do not typically focus on improving the intake and discharge processes of the patient flow management. Instead, these systems typically focus improvements on activities and processes that occur between the point of admission and the point of discharge and simply rely on a number of software products running on multiple platforms to implement the intake and discharge processes. This ad hoc manner for implementing the intake and discharge processes can lead to bottlenecks in the patient flow, increased costs to maintain the various products and platforms, and increased complexity requiring specialized training on each piece of software. Accordingly, the need exists for improved techniques for patient flow management.”

As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors’ summary information for this patent application: “Techniques are provided (e.g., a method, a system, non-transitory computer-readable medium storing code or instructions executable by one or more processors) for express tracking of patient flow management in a distributed environment.

“In various embodiments, systems and methods of express tracking are provided for patient flow management in a distributed environment. Particularly, aspects are directed to a computer implemented method that includes initiating a check-in process that includes prompting a user to scan an identifier; determining whether the user is known user based on the identifier; when the user is a known user, verifying user data saved in the computing system associated with the identifier; once the user data is verified, determining whether the user has an outstanding balance for prior services; when the user does not have the outstanding balance, determining whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

“In some embodiments, the method further comprises when the user is not the known user, initiating a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system.

“In some embodiments, the method further comprises when the user does not have a scheduled appointment or after accepting the terms and conditions for scheduling the services via the computing system, displaying a list of services currently available for appointment, and prompting the user to select one or more services for scheduling; upon receiving the selection of the one or more services, displaying a list of times currently available for having the one or more services performed, and prompting the user to select a time for scheduling; and upon receiving the selection of the time, generating an appointment for the services at the selected time.

“In some embodiments, the method further comprises when the user does have the outstanding balance, prompting the user to pay the outstanding balance or a portion of the outstanding balance.

“In various embodiments, a method is provided comprising: initiating, by a computing system in a distributed environment, a check-in process that includes prompting a user to scan an identifier; receiving, by the computing system, image data from the scan of the identifier; extracting, by a first convolutional layer of a multi-task convolutional neural network model, a first set of features from the image data for a first piece of information on the identifier, wherein the first set of features are specific to a first task of classifying the identifier; extracting, by a second convolutional layer of the multi-task convolutional neural network model, a second set of features from the image data, wherein the second set of features are specific to a task of predicting a location of a second piece of information on the identifier; classifying, by a first fully connected layer of the multi-task convolutional neural network model, the identifier based on the first set of features and the second set of features; predicting, by a second fully connected layer of the multi-task convolutional neural network model, the location of the second piece of information on the identifier based on the first set of features and the second set of features; extracting, by the computing system, image data pertaining to the second piece of information based on the predicted location of the second piece of information on the identifier; generating, by a recurrent neural network model, a sequence of alphanumeric characters from the image data pertaining to the second piece of information; outputting, by the multi-task convolutional neural network, the classification of the identifier based on the first piece of information; and outputting, by the recurrent neural network model, the second piece of information as the sequence of generated alphanumeric characters.

“In some embodiments, the identifier is an insurance card, the first piece of information is an insurance provider, and the second piece of information is a member identifier.

“In some embodiments, the method further comprises: determining, by the computing system, whether the user is known user based on the second piece of information; when the user is a known user, verifying, by the computing system, user data saved in the computing system associated with the identifier; once the user data is verified, determining, by the computing device, whether the user has an outstanding balance for prior services; when the user does not have the outstanding balance, determining, by the computing device, whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

“In some embodiments, the method further comprises when the user is not the known user, initiating, by the computing system, a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system.

“In some embodiments, the method further comprises: when the user does not have a scheduled appointment or after accepting the terms and conditions for scheduling the services via the computing system, displaying, by the computing system, a list of services currently available for appointment, and prompting the user to select one or more services for scheduling; upon receiving the selection of the one or more services, displaying, by the computing system, a list of times currently available for having the one or more services performed, and prompting the user to select a time for scheduling; and upon receiving the selection of the time, generating, by the computing system, an appointment for the services at the selected time.

“In some embodiments, the method further comprises when the user does have the outstanding balance, prompting, by the computing device, the user to pay the outstanding balance or a portion of the outstanding balance.

“In some embodiments, a method is provided that comprises initiating, by a computing system in a distributed environment, a check-in process that includes prompting a user to scan an identifier; determining, by the computing system, whether the user is known user based on the identifier; when the user is not the known user, initiating, by the computing system, a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system. The requesting includes prompting the user to scan in their insurance card. The method further comprises receiving, by the computing system, image data from the scan of the insurance card; extracting, by a first convolutional layer of a multi-task convolutional neural network model, a first set of features from the image data for a first piece of information on the insurance card, wherein the first set of features are specific to a first task of classifying the insurance card; extracting, by a second convolutional layer of the multi-task convolutional neural network model, a second set of features from the image data, wherein the second set of features are specific to a task of predicting a location of a second piece of information on the insurance card; classifying, by a first fully connected layer of the multi-task convolutional neural network model, the insurance card based on the first set of features and the second set of features; predicting, by a second fully connected layer of the multi-task convolutional neural network model, the location of the second piece of information on the insurance card based on the first set of features and the second set of features; extracting, by the computing system, image data pertaining to the second piece of information based on the predicted location of the second piece of information on the insurance card; generating, by a recurrent neural network model, a sequence of alphanumeric characters from the image data pertaining to the second piece of information; outputting, by the multi-task convolutional neural network, the classification of the identifier based on the first piece of information; and outputting, by the recurrent neural network model, the second piece of information as the sequence of generated alphanumeric characters.

“In some embodiments, a system is provided that includes one or more data processors and a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform part or all of one or more methods disclosed herein.

“In some embodiments, a computer-program product is provided that is tangibly embodied in a non-transitory machine-readable storage medium and that includes instructions configured to cause one or more data processors to perform part or all of one or more methods disclosed herein.

“Some embodiments of the present disclosure include a system including one or more data processors. In some embodiments, the system includes a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform part or all of one or more methods and/or part or all of one or more processes disclosed herein. Some embodiments of the present disclosure include a computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform part or all of one or more methods and/or part or all of one or more processes disclosed herein.

“The terms and expressions which have been employed are used as terms of description and not of limitation, and there is no intention in the use of such terms and expressions of excluding any equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the invention claimed. Thus, it should be understood that although the present invention as claimed has been specifically disclosed by embodiments and optional features, modification and variation of the concepts herein disclosed may be resorted to by those skilled in the art, and that such modifications and variations are considered to be within the scope of this invention as defined by the appended claims”

The claims supplied by the inventors are:

“1. A method comprising: initiating, by a computing system in a distributed environment, a check-in process that includes prompting a user to scan an identifier; receiving, by the computing system, image data from the scan of the identifier; extracting, by a first convolutional layer of a multi-task convolutional neural network model, a first set of features from the image data for a first piece of information on the identifier, wherein the first set of features are specific to a first task of classifying the identifier; extracting, by a second convolutional layer of the multi-task convolutional neural network model, a second set of features from the image data, wherein the second set of features are specific to a task of predicting a location of a second piece of information on the identifier; classifying, by a first fully connected layer of the multi-task convolutional neural network model, the identifier based on the first set of features and the second set of features; predicting, by a second fully connected layer of the multi-task convolutional neural network model, the location of the second piece of information on the identifier based on the first set of features and the second set of features; extracting, by the computing system, image data pertaining to the second piece of information based on the predicted location of the second piece of information on the identifier; generating, by a recurrent neural network model, a sequence of alphanumeric characters from the image data pertaining to the second piece of information; outputting, by the multi-task convolutional neural network, the classification of the identifier based on the first piece of information; and outputting, by the recurrent neural network model, the second piece of information as the sequence of generated alphanumeric characters.

“2. The method of claim 1, wherein the identifier is an insurance card, the first piece of information is an insurance provider, and the second piece of information is a member identifier.

“3. The method of claim 1, further comprising: determining, by the computing system, whether the user is known user based on the second piece of information; when the user is a known user, verifying, by the computing system, user data saved in the computing system associated with the identifier; once the user data is verified, determining, by the computing device, whether the user has an outstanding balance for prior services; when the user does not have the outstanding balance, determining, by the computing device, whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

“4. The method of claim 1, further comprising when the user is not the known user, initiating, by the computing system, a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system.

“5. The method of claim 1, further comprising: when the user does not have a scheduled appointment or after accepting the terms and conditions for scheduling the services via the computing system, displaying, by the computing system, a list of services currently available for appointment, and prompting the user to select one or more services for scheduling; upon receiving the selection of the one or more services, displaying, by the computing system, a list of times currently available for having the one or more services performed, and prompting the user to select a time for scheduling; and upon receiving the selection of the time, generating, by the computing system, an appointment for the services at the selected time.

“6. The method of claim 1, further comprising when the user does have the outstanding balance, prompting, by the computing device, the user to pay the outstanding balance or a portion of the outstanding balance.

“7. A non-transitory machine readable storage medium having instructions stored thereon that when executed by one or more processors cause the one or more processors to perform operations comprising: initiating a check-in process that includes prompting a user to scan an identifier; receiving image data from the scan of the identifier; extracting, by a first convolutional layer of a multi-task convolutional neural network model, a first set of features from the image data for a first piece of information on the identifier, wherein the first set of features are specific to a first task of classifying the identifier; extracting, by a second convolutional layer of the multi-task convolutional neural network model, a second set of features from the image data, wherein the second set of features are specific to a task of predicting a location of a second piece of information on the identifier; classifying, by a first fully connected layer of the multi-task convolutional neural network model, the identifier based on the first set of features and the second set of features; predicting, by a second fully connected layer of the multi-task convolutional neural network model, the location of the second piece of information on the identifier based on the first set of features and the second set of features; extracting image data pertaining to the second piece of information based on the predicted location of the second piece of information on the identifier; generating, by a recurrent neural network model, a sequence of alphanumeric characters from the image data pertaining to the second piece of information; outputting, by the multi-task convolutional neural network, the classification of the identifier based on the first piece of information; and outputting, by the recurrent neural network model, the second piece of information as the sequence of generated alphanumeric characters.

“8. The non-transitory machine readable storage medium of claim 7, wherein the identifier is an insurance card, the first piece of information is an insurance provider, and the second piece of information is a member identifier.

“9. The non-transitory machine readable storage medium of claim 7, wherein the operations further comprise: determining whether the user is known user based on the second piece of information; when the user is a known user, verifying user data saved in the computing system associated with the identifier; once the user data is verified, determining whether the user has an outstanding balance for prior services; when the user does not have the outstanding balance, determining whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

“10. The non-transitory machine readable storage medium of claim 7, wherein the operations further comprise when the user is not the known user, initiating, by the computing system, a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system.

“11. The non-transitory machine readable storage medium of claim 7, wherein the operations further comprise: when the user does not have a scheduled appointment or after accepting the terms and conditions for scheduling the services via the computing system, displaying, by the computing system, a list of services currently available for appointment, and prompting the user to select one or more services for scheduling; upon receiving the selection of the one or more services, displaying, by the computing system, a list of times currently available for having the one or more services performed, and prompting the user to select a time for scheduling; and upon receiving the selection of the time, generating, by the computing system, an appointment for the services at the selected time.

“12. The non-transitory machine readable storage medium of claim 7, wherein the operations further comprise when the user does have the outstanding balance, prompting, by the computing device, the user to pay the outstanding balance or a portion of the outstanding balance.

“13. A system comprising: a memory configured to store computer-executable instructions; and a processor configured to access the memory and execute the computer-executable instructions to perform operations comprising: initiating a check-in process that includes prompting a user to scan an identifier; receiving image data from the scan of the identifier; extracting, by a first convolutional layer of a multi-task convolutional neural network model, a first set of features from the image data for a first piece of information on the identifier, wherein the first set of features are specific to a first task of classifying the identifier; extracting, by a second convolutional layer of the multi-task convolutional neural network model, a second set of features from the image data, wherein the second set of features are specific to a task of predicting a location of a second piece of information on the identifier; classifying, by a first fully connected layer of the multi-task convolutional neural network model, the identifier based on the first set of features and the second set of features; predicting, by a second fully connected layer of the multi-task convolutional neural network model, the location of the second piece of information on the identifier based on the first set of features and the second set of features; extracting image data pertaining to the second piece of information based on the predicted location of the second piece of information on the identifier; generating, by a recurrent neural network model, a sequence of alphanumeric characters from the image data pertaining to the second piece of information; outputting, by the multi-task convolutional neural network, the classification of the identifier based on the first piece of information; and outputting, by the recurrent neural network model, the second piece of information as the sequence of generated alphanumeric characters.

“14. The system of claim 13, wherein the identifier is an insurance card, the first piece of information is an insurance provider, and the second piece of information is a member identifier.

“15. The system of claim 13, wherein the operations further comprise: determining whether the user is known user based on the second piece of information; when the user is a known user, verifying user data saved in the computing system associated with the identifier; once the user data is verified, determining whether the user has an outstanding balance for prior services; when the user does not have the outstanding balance, determining whether the user has a scheduled appointment; and when the user has a scheduled appointment, checking the user in for the scheduled appointment.

“16. The system of claim 13, wherein the operations further comprise when the user is not the known user, initiating, by the computing system, a registration process that includes requesting demographic information from the user and prompts the user to accept terms and conditions for scheduling services via the computing system.

“17. The system of claim 13, wherein the operations further comprise: when the user does not have a scheduled appointment or after accepting the terms and conditions for scheduling the services via the computing system, displaying, by the computing system, a list of services currently available for appointment, and prompting the user to select one or more services for scheduling; upon receiving the selection of the one or more services, displaying, by the computing system, a list of times currently available for having the one or more services performed, and prompting the user to select a time for scheduling; and upon receiving the selection of the time, generating, by the computing system, an appointment for the services at the selected time.

“18. The system of claim 13, wherein the operations further comprise when the user does have the outstanding balance, prompting, by the computing device, the user to pay the outstanding balance or a portion of the outstanding balance.”

For additional information on this patent application, see: Demick, Michael; Wright, Mark. Express Tracking For Patient Flow Management In A Distributed Environment. Filed October 30, 2019 and posted April 30, 2020. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220200134571%22.PGNR.&OS=DN/20200134571&RS=DN/20200134571

(Our reports deliver fact-based news of research and discoveries from around the world.)