Intelligent system for simplifying communication and reducing interruption of radiology department

Abstract

A non-transitory computer readable medium (16) stores instructions readable and executed by an electronic processor (14) to execute a method (100) requesting radiation assistance. The method includes providing a requester graphical user interface (GUI) (28) on a display device (24) of a requester electronic processing device (18) operable by a requester; receiving one or more inputs from the requester to fill in fields in the requester GUI to generate an assistance request for radiation assistance (40); sending the assistance request for radiation assistance to a recipient electronic processing device (30) operable by a radiologist; providing, on a display device (36) of the recipient electronic processing device, a recipient GUI (38) showing a list (44) of assistance requests for radiation assistance; and tracking and marking the status of each assistance request in the list for radiation assistance.

Description

Technical Field

[0001] The following generally relates to the fields of radiology, radiology assistance, graphical user interface (GUI) generation, picture archiving and communication systems (PACS), and related fields. Background Art

[0002] Radiologists are often interrupted by radiology assistance requests during their working day. Radiologists are interrupted every 4 to 12.1 minutes during normal working hours and receive an average of 72 calls during a typical 12-hour night shift (see, for example, “The Impact of Interruptions on Chest Radiograph Interpretation Effects on Reading Time and Accuracy” by Rachel M. Wynn, PhD, et al., Academic Radiology, Vol. 25, No. 12, pp. 1515-1520, December 1, 2018; “Quantifying the cost of interruption during diagnostic radiologic interpretation using mobile eye-tracking glasses” by Drew T, Williams LH, Aldred B, Heilbrun ME, Minoshima S, J Med Imaging (Bellingham). July 2018; 5(3):031406.doi:10.1117 / 1.JMI.5.3.031406.Epub March 2, 2018 PMID:29531970; PMCID: PMC5833804). These interruptions mainly manifest as answering phone calls, responding to pages, and providing in-person case consultations. Interruptions can lead to increased reading time, patient safety issues when reading abnormal cases, increased stress, or frustration for radiologists. In addition, many of the problems are not actually that urgent and can wait a few minutes, which is usually the time required for radiologists to complete their current tasks.

[0003] Problems requesting radiology assistance are mainly raised by referring physicians and technicians. Interruptions from referring physicians mainly involve study review, order issues, and inquiries about study results, while imaging technicians usually request radiology assistance in aspects such as protocol assignment, image examination, and problem discovery.

[0004] Technical staff or referring physicians may also be interrupted when sending or receiving responses by phone, so in most cases, asynchronous communication via text-based messaging is preferred. The time required for a response depends on the urgency of the task the recipient is performing and the urgency of the issue. The absence of an answer may affect the patient (clinical urgency) or may disrupt the workflow. Complaints about response delays or difficulty reaching an available radiologist(s) at certain critical times are common. Currently, interruptions (whether by phone or pager / text message) cannot distinguish between urgent and non-urgent matters.

[0005] Depending on the setup of each clinical institution, one or more radiologists may be assigned to respond to questions or requests for radiology assistance raised within a given time. The most common assignment of radiologists during the day shift is rotation based on the modality of the study or the specialty department. In this case, the radiologist is only responsible for questions raised in the designated department or modality. On weekends or during the night shift, there may be only one on-call radiologist available. Therefore, the radiologist will be responsible for answering all questions raised in any department or modality. In addition, large medical institutions or hospitals may have multiple radiologists, so they will be responsible for most of the work in the hospital or hospital group.

[0006] In addition, requests for assistance to on-call radiologists vary in urgency, depending on, for example, whether the patient is still in the scanner or in the dressing room, the type and severity of the case (clinical urgency), and the patient's medical history. Sometimes, over time, the urgency of the request changes and may even become moot because an answer has been found in another way or because the patient has to leave due to another appointment. Sometimes, the radiologist cannot answer the phone when the requesting technician or doctor wants to contact them, and vice versa. When responding to an assistance request, the radiologist is completely taken away from the image review or examination reading that the radiologist is conducting. In some cases, the radiologist even manages several phone calls while assisting with an urgent request. This can lead to a very stressful workday and inefficient communication and collaboration.

[0007] The radiologist is able to directly record the results with the appropriate stakeholder(s) assigned to a specific case ticket via a chat function. However, in practice, due to the benefits of verbal communication, requests for assistance still cause the radiologist and the technician to sometimes interrupt each other and make phone calls. However, the interruptions may occur at inopportune times and usually result in disruptions to the workflow, increased cognitive load, frustration, stress, and generally a lot of chaos during the workday.

[0008] Certain improvements that overcome these and other problems are disclosed below. Summary of the Invention

[0009] In some embodiments disclosed herein, a non - transitory computer - readable medium stores instructions that can be read and executed by an electronic processor to perform a method for requesting radiology assistance. The method includes: providing a requester graphical user interface (GUI) on a display device of a requester electronic processing device operable by a requester; receiving one or more inputs from the requester to fill in fields in the requester GUI, thereby generating an assistance request for radiology assistance; sending the assistance request for radiology assistance to a recipient electronic processing device operable by a radiologist; providing a recipient GUI on a display device of the recipient electronic processing device that shows a list of assistance requests for radiology assistance; and tracking and marking the status of each assistance request for radiology assistance in the list.

[0010] In some embodiments disclosed herein, an assistance request method includes: receiving one or more inputs from a requester to fill in fields in a requester GUI displayed on a display device of a requester electronic processing device, the requester electronic processing device being operable by the requester to generate an assistance request for radiology assistance; sending the assistance request for radiology assistance to a recipient electronic processing device operable by a radiologist; and tracking and marking the status of the assistance request for radiology assistance on a recipient GUI provided on a display device of the recipient electronic processing device.

[0011] In some embodiments disclosed herein, an assistance request method includes: determining the urgency of a medical imaging examination performed by a requester; determining the interruption score of a radiologist to whom the requester is requesting assistance; and determining at least one subsequent action for the radiologist to provide to the requester based on the determined urgency and the determined interruption score.

[0012] One advantage is that it reduces the interruption of radiologists during the imaging workflow.

[0013] Another advantage is that it reduces the task switching among radiologists during the imaging examination workflow.

[0014] Another advantage is that it improves the quality of the radiologist workflow by reducing interruptions during the workflow.

[0015] Another advantage is that it reduces the complaints about the delayed response to radiologists during the imaging workflow.

[0016] Another advantage is that it is easier to identify the radiologists who request assistance during the imaging workflow.

[0017] Another advantage is the automatic creation, prioritization, and tracking of assistance requests.

[0018] Another advantage is that it enables radiologists to stay focused and minimizes the impact of distractions from others.

[0019] A given embodiment may not provide any of the foregoing advantages, provide one of the foregoing advantages, two or more of the foregoing advantages, or provide all of the foregoing advantages, and / or may provide other advantages that will be apparent to those of ordinary skill in the art upon reading and understanding this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] This disclosure may take the form of various components and component arrangements and various steps and step arrangements. The drawings are only for illustrative purposes of the preferred embodiments and should not be construed as limiting this disclosure.

[0021] Figure 1 An assistance request device according to the present disclosure is schematically shown.

[0022] Figure 2 An assistance request method using the Figure 1 device is schematically shown.

[0023] Figure 3 An electronic processing device of the Figure 1 device that can be operated by different users is schematically shown.

[0024] Figure 4 Another embodiment of the assistance request device according to the present disclosure is schematically shown. DETAILED DESCRIPTION

[0025] Currently, imaging technicians and doctors who request assistance from radiologists mainly use synchronous communication paths such as telephones or video calls (e.g., some institutions use Zoom, Skype, or Microsoft Teams) or pagers. Such requests usually also have no priority, so radiologists are often interrupted to handle radiology assistance requests that may have low priority or can wait.

[0026] The following provides a system for providing asynchronous radiology assistance requests to be processed with an assigned request priority. A requester graphical user interface (GUI) is provided through which a requester can submit a request for radiology assistance. A request for radiology assistance can be, for example, an imaging technician requesting assistance in setting up an imaging scan, or a doctor or other medical professional requesting assistance in understanding the content of a radiology image or radiology report. The requester GUI includes fields for assigning a priority on a predefined priority schedule, such as a number of discrete priorities ranging from "not urgent" to "immediate action". The user can also specify a time range for a response and details that impact the workflow and / or patient (e.g., "the patient is on the table"), providing information to the radiologist to conclude that not answering the question will disrupt the workflow. However, the radiologist may have a clinical emergency, in which case they will always prioritize the request over allowing the workflow to be interrupted. The requester GUI also allows the requester to attach documents or document links, such as an object review link in a Picture Archiving and Communication System (PACS). The requester GUI can also allow flexible addressing options, such as specifying a particular radiologist as the addressed recipient, or specifying a role (e.g., the recipient can be any radiologist with expertise in a particular imaging modality), or not specifying a particular recipient. A module then processes sending the request to an appropriate radiologist. When resolving issues other than a particular radiologist, the system then assigns a receiving radiologist based on who is on call, their expertise, and workload.

[0027] On the receiving radiologist side, a recipient GUI provides a work list of requests addressed to that receiving radiologist organized by priority, specified response time, or other criteria. The recipient GUI also provides communication paths, such as a video conferencing path, a text messaging path, a VOIP phone path, etc., through which the receiving radiologist can provide an appropriate response. At the requester GUI, the recipient GUI, or both, each request can also be marked or updated with a status, such as "not sent", "new", "in progress", "reopened", "closed", etc. In some examples, the work list can include questions for a department / role, in which case they can process cases based on availability and their own processes. In such a case, the requester also needs to know which ones are already occupied, by whom, etc.

[0028] In some embodiments disclosed herein, the requester may attach one or more clinical images or image series annotated by the requester to indicate image features or other image content that are the subject of the request (e.g., an arrow pointing to an image feature for which a more specific explanation is being requested). Since it is not desirable to annotate images in the PACS in this manner, a copy of the annotated image with a potentially reduced resolution and / or that is compressed may be attached to the request. If the attached image has a reduced resolution or is compressed, a link to the original image in the PACS is preferably provided. For example, clicking on the attached image using a mouse or other user input device may retrieve and display the original image.

[0029] In some variant embodiments disclosed herein, in addition to providing asynchronous radiology assistance request processing for requests originating from imaging technicians or other non-radiologist medical staff, the system may also provide asynchronous radiology assistance request processing for radiologist-to-radiologist messaging.

[0030] In some embodiments disclosed herein, an artificial intelligence (AI) component may be integrated into the system. For example, if the imaging system is equipped with a computer-aided diagnosis (CADx) module, then if the CADx module detects that a suspicious feature may be an incidental finding, it may automatically generate a request. The radiologist is required to confirm or reject the CADx conclusion, or take other actions, such as obtaining additional images of the suspicious feature. Similarly, the automatic detection of image quality issues by the AI module may trigger an automatic request. For example, the urgency of the request may also be set automatically rather than manually based on a machine learning (ML) analysis of the request content.

[0031] In other embodiments disclosed herein, the system may monitor upcoming radiological examinations to ensure that the radiologist completes all required inputs before the examination begins. For example, if the radiologist is required to specify an imaging sequence for an examination card, then if this is not done within a certain set time before the examination (e.g., at least 24 hours in advance), a request to do so is automatically generated.

[0032] In other embodiments disclosed herein, based on real-time feedback such as monitoring the radiologist's eye movements to evaluate the radiologist's engagement in his or her current work (e.g., reading a radiological examination), the complexity of the radiological examination the radiologist is currently reading, the patient's location (which may change over time), etc., the work order priority and / or the recommended communication mode (e.g., phone, chat, video with screen sharing, etc.) are monitored and adjusted in real time. The urgency of the technician's request and the cost of interrupting the radiologist are evaluated in real time and balanced to update the request priority and / or the recommended communication mode in real time.

[0033] Reference Figure 1, illustrates an illustrative apparatus 10 for providing assistance during an imaging examination. As Figure 1 shown, the monitoring apparatus 10 includes a server computer 14 or is accessible by the server computer 14. The server computer 14 includes a computer or other programmable electronic device that includes or is operatively accessible to a non-transitory computer-readable medium. The server computer 14 is connected to other devices via a communication network 12 (such as the Internet), optionally connected to one or more local area networks (LANs) or wide area networks (WANs) (such as the LAN or WAN of the hospital where the PACS 12 is located and / or the LAN or WAN of the vendor or the LAN or WAN of the cloud computing service provider that provides the server computer 14 to the vendor). It should be understood that the server computer 14 can be implemented as multiple server computers, for example, interconnected to form a server cluster, cloud computing resources, etc., to perform more complex computing tasks.

[0034] A requesting party electronic processing device 18 (such as a workstation computer, or more generally a computer, a mobile device (e.g., a tablet computer)), operable by a requesting party (RQ) (such as a technician performing an imaging examination, etc.), to provide a user interface for an imaging assistance method or process 100 running on the server computer 14. The requesting party electronic processing device 18 includes typical components for a user interface computer, such as an electronic processor 20 (e.g., a microprocessor), at least one user input device (e.g., a mouse, a keyboard, a trackball, etc.) 22, and a display device 24 (e.g., an LCD monitor, a plasma monitor, etc.). In some embodiments, the display device 24 can be a component separate from the requesting party electronic processing device 18, or can include two or more display devices.

[0035] A receiving party electronic processing device 30 (such as a workstation computer, or more generally a computer, a mobile device (e.g., a tablet computer)), operable by a receiving party (RC) (such as a technician monitoring one or more imaging examinations, etc.), to provide a user interface for an imaging assistance method or process 100 running on the server computer 14. The receiving party electronic processing device 30 includes typical components for a user interface computer, such as an electronic processor 32 (e.g., a microprocessor), at least one user input device (e.g., a mouse, a keyboard, a trackball, a dictation device, etc.) 34, and a display device 36 (e.g., an LCD monitor, a plasma monitor, etc.). In some embodiments, the display device 36 can be a component separate from the receiving party electronic processing device 30, or can include two or more display devices.

[0036] The server computer 14 includes a database that includes a non-transitory storage medium 16. As a non-limiting illustrative example, the non-transitory storage medium 16 may include one or more of a magnetic disk, a RAID, or other magnetic storage media; a solid state drive, a flash drive, an electronically erasable read only memory (EEROM), or other electronic memory; an optical disc or other optical storage device; various combinations thereof; and may be, for example, a network storage device, an internal hard drive of the electronic processing device 18, various combinations thereof, etc. It should be understood that any reference herein to one or more non-transitory media 16 should be construed broadly to cover a single medium or multiple media of the same or different types. Similarly, the electronic processor 20 may be embodied as a single electronic processor or two or more electronic processors. The non-transitory storage medium 16 stores instructions executable by at least one electronic processor 20. The instructions include instructions for generating a visualization of a requester graphical user interface (GUI) 28 to be displayed on a display device 24 of the requester electronic processing device 18 and a visualization of a recipient GUI 38 to be displayed on a display device 36 of the recipient electronic processing device 30.

[0037] As described above, the apparatus 10 is configured to perform an imaging assistance method or process 100. The database 16 stores instructions executable by the server computer 14 (and / or by the requester electronic processing device 18 and / or the recipient electronic processing device 36) to perform the imaging assistance method or process 100. In some examples, the method 100 may be performed at least in part by cloud processing (i.e., the server computer 16 may be implemented as cloud computing resources including an ad hoc network of server computers).

[0038] Referring Figure 2 and continuing to refer Figure 1 to, illustrative embodiments of an example of the imaging assistance method 100 are schematically shown in the form of a flowchart.

[0039] In operation 102, a requester GUI 28 is provided on a display device 24 of the requester electronic processing device 18. The requester GUI 28 may include one or more fields through which the requester RQ may provide input via at least one user input device 22. Optionally, at this time, a recipient GUI 38 may be provided on a display device 36 of the recipient electronic processing device 30.

[0040] At operation 104, one or more inputs can be received from a requester RQ to fill in fields in the requester GUI 28, thereby generating an assistance request 40. In one example, the fields of the requester GUI 28 include a recipient field that is configured to receive a recipient as any one of the following: (i) a specific radiologist; (ii) a radiologist role; or (iii) an unspecified recipient. In another example, the fields of the requester GUI 28 include a field for assigning a priority on a predefined priority schedule. In another example, the fields of the requester GUI 28 include a field for attaching a document or a document link. In another example, the fields of the requester GUI 28 include a field for requesting an assistance request 40 from a specific radiologist. In another example, the fields of the requester GUI 28 include a field for attaching a clinical image that is the subject of the assistance request (40). In this example, the requester GUI 28 also provides a field through which the requester RQ can annotate the clinical image, and the annotated clinical image is input into the field for attaching the clinical image. In yet another example, the requester GUI 28 includes a field for updating the status of the assistance request 40. In yet another example, the requester GUI 28 includes a field for displaying the status of an imaging acquisition or workflow. These are merely examples and should not be construed as limiting.

[0041] In some embodiments, an artificial intelligence (AI) component 42 (stored in the database 16) can be used to perform the assistance request generation operation 40. For example, the AI component 42 can include a multi-class machine learning model. In one example, the AI component 42 is configured to analyze computer-aided diagnosis (CADx) features of an imaging device used in an imaging examination performed by the requester RQ. The assistance request 40 is generated based on the analysis of the CADx features. In another example, the AI component 42 is configured to analyze clinical images generated by an imaging device used in an imaging examination performed by the requester RQ. The assistance request 40 is generated based on the analysis of the clinical images. These are merely examples and should not be construed as limiting.

[0042] Once generated, assistance request 40 is sent to server computer 14. At operation 106, assistance request 40 is sent to recipient electronic processing device 30. At operation 108, a list 44 of assistance requests 40 is provided on recipient GUI 38. The list 44 of assistance requests 40 displayed on recipient GUI 38 includes a work list of requests addressed to recipient RC based on one or more criteria (e.g., priority, reply-by time, etc.). Additionally, recipient GUI 38 includes one or more fields through which recipient RC can provide input via at least one user input device 34. The (one or more) fields of recipient GUI 38 can include, for example, one or more of the following fields: a field for the communication path 19 between the recipient and each requester who submitted assistance request 40 (which communication path can then be established), a field for updating the status of assistance request 40, and so on.

[0043] At operation 110, each assistance request 40 on list 44 can be tracked and labeled ("not sent", "new", "in progress", "reopened", "closed", etc.).

[0044] In some embodiments, method 100 can include monitoring the scheduling of upcoming radiology exams, including detecting upcoming radiology exams with incomplete exam cards that require information from a radiologist (i.e., requester RQ) to complete the exam card. A request can be generated for requester RQ to provide the information needed to complete the exam card before the imaging exam begins.

[0045] Example

[0046] Apparatus 10 and method 100 are described in more detail below. Figure 3 Aspects of the example are schematically depicted, including modules implemented by requester device 18, recipient device 30, and server 14. Server computer 14 can include one or more modules to perform method 100 in conjunction with the various modules of requester device 18 and recipient device 30. For example, as Figure 3As shown, one of the modules may include a module for initiating a communication request (e.g., implemented at the requester device 18). This module is used for the user to send a communication request. The primary users of the requester device 18 may include technicians or referring physicians, and the less frequent users may include hospital residents and radiologists. The users of the recipient device 30 are typically radiologists. Both asynchronous and synchronous channels can be used to create communication requests for radiology assistance. In this illustrative example, various features are also supported to simplify communication requests, including indication of urgency, linking the request to a study, screen sharing, attaching studies or patient background, and enabling, for example, full-channel (i.e., automatic) generation of requests initiated by an AI module, managing request status, and sending reminders.

[0047] The main part of the communication request is the content. The content typically contains questions or requests regarding a scan or study. The content of the communication request is conveyed in the form of a message in asynchronous communication and can be sent via a work order or chat function. In synchronous communication, the content can be sent via a phone call, web call, or video call. Additionally, screen sharing and remote control are enabled to enhance the content. Enabling screen sharing and remote control allows the recipient to access and control the scanner from a remote setting.

[0048] The question can be described in free text or using predefined questions that can be selected by clicking on graphical UI elements (e.g., tiles). It is also desirable to indicate the urgency of the request and an identifier that links the request to a study along with the content. The urgency of the request defines the time span within which the request needs to be answered. The input of the urgency of the request can be generated in various ways, including but not limited to user input or AI-based prediction. The urgency can be indicated in different ways, such as using an item scale (e.g., not urgent - urgent - very urgent - execute immediately). Alternatively, a target response time in minutes (e.g., within 30 minutes) is used to reflect the urgency. In this way, the urgency can be set manually or selected from a list of predefined target response times (e.g., within 0 minutes, within 5 minutes). Additionally, workflow information (e.g., whether there is a patient on the examination table, when the missing protocol for the (scheduled patient) is required, etc.) can be included in the determined urgency.

[0049] In some embodiments, the urgency is determined by the AI component 42. For example, a multi-class machine learning model can be trained to predict the urgency level of the request. The inputs to the model will be the content of the question, the characteristics of the patient, and the study, such as modality, department, scan type, etc. The training labels or outputs will be time spans in a classification format within which a response should be provided, e.g., 'within 5 minutes', 'within 30 minutes', 'within 1 hour', etc. The machine learning model can also use the actual response time (e.g., the duration of the time interval from submitting the request to opening the request) as an alternative ground truth.

[0050] Sometimes it is also beneficial to associate a communication request with a study to provide a research background, for example, the identifier of the study should be provided. This can be achieved in multiple ways. The sender can manually enter the study identifier. Alternatively, a list of studies can be provided to the sender to select a request and associate the request with it. The list of studies is based on the patients being scanned or to be scanned today. The list can be compiled based on the information contained in the scanner (and using console extraction techniques to extract it), HL7 messages sent to the Radiology Information System (RIS), and the Electronic Medical Record (EMR) database. For example, the requesting device 18 and the receiving device 30 can be linked to such a database, which is an option to select a patient and / or add further details to the request.

[0051] Another feature of some embodiments allows the sender to attach more patients and research background to the message, such as DICOM images, patient history, referral records, etc. This helps to provide supplementary information to clarify or enhance the background of the communication request, thus improving the efficiency of communication. Although providing this information as an attachment is useful for assisting the recipient in understanding the clinical background of the patient and the study, the recipient can still access the research background through other channels already enabled in the system. One alternative way is through the screen sharing function. In the case of providing an identifier, the recipient can also access the study / patient information in other clinical informatics systems.

[0052] The communication request can be initiated through multiple channels. Another optional feature is to adopt a full-channel (or multi-channel) approach to allow communication requests to be generated from multiple sources, such as AI-generated requests. The request should be automatically linked to the patient, thus providing all the required patient details (e.g., RIS or PAC or EMR). There should also be a link to retrieve the correct patient history at the recipient's location.

[0053] Through the requesting device 18, the requester can send a communication request with patient information, a question, and an indication of urgency. Once sent, the message will be generated in the chat window opened on the receiving device 30. The radiologist can follow up on the request through synchronous and asynchronous communication.

[0054] To facilitate the automatic routing of radiology assistance requests, role-based logins can be used to identify users on both the sender side and the recipient side.

[0055] Another module may include an AI module to generate communication requests for radiology assistance. The module may contain multiple AI engines to predict different communication requests and / or detect image features that require radiologist consultation. In one embodiment, the module receives DICOM images and applies one or more AI engines implementing CADx analysis to detect findings that require urgent attention from a radiologist, such as pneumothorax, potential COVID-19, or aneurysm. In another embodiment, the AI module detects potential image quality issues (e.g., motion artifacts) in images (x-ray, CT, MR) or missing sequences (CT, MR). The output of the module provides the content of the communication request and will be used as an input for generating a communication request that includes all or some of the above elements (e.g., problem, urgency). Each automatically generated request can be sent to the relevant requester (e.g., technician) to complete / edit the request if necessary, and / or can be directly sent to the corresponding recipient(s).

[0056] Another module may include a module for routing communication requests to the corresponding recipient(s). The module routes the communication request to the recipient without the sender absolutely indicating the individual who needs to receive the request. The requester initiates the communication request, and the recipient is responsible for replying to the request.

[0057] A user of the system sends a request to an individual (e.g., Dr. Doe) or a role (e.g., any radiologist who can assist with an MR brain scan). The system can be configured to support only direct communication with an individual or role-based communication, or both.

[0058] Before routing the communication request, the scope of the request is identified. The scope refers to the selected department or modality for which the recipient is responsible for answering the request posed. The sender may indicate the scope of the request. If the study background with modality or scanner information is provided, the scope can also be identified. Alternatively, an AI model can be trained to automatically classify the scope of the request and assign it to the most appropriate recipient. For example, a natural language processing (NLP) model can be trained to extract information from the content of the request and predict the scope.

[0059] Using the identified scope, the communication request can be routed in various ways. For example, the sender can specify the individual radiologist recipient and then send the request for radiology assistance to that particular radiologist.

[0060] In some embodiments, the system can automatically identify the appropriate receiving radiologist and direct requests for radiology assistance to that radiologist without the sender having to specify the recipient. This can be achieved through role-based routing, in which case each radiologist will use their login information to indicate the scope of requests for which they are responsible. For example, the receiving radiologist can indicate that he / she is available to receive requests related to brain MR (or other clinically relevant scan types), in which case the system will then direct all questions regarding brain scans to that account. When multiple radiologists can answer requests from the same scope, the system can allow multiple radiologists to log in under the same role-based account. For example, under the account 'rads for brain scans', multiple radiologists can log in to the same system and evaluate the same list of directed requests.

[0061] Communication requests for radiology assistance can also be directed based on availability or workload.

[0062] When multiple recipients are available to answer requests from the same scope, the system can also intelligently direct communication requests based on the workload of each user within that same scope. If the system detects that a radiologist is unavailable or under a heavy image interpretation workload, the request will be directed to another radiologist responsible for that scope. For example, a Bayesian probability model can be trained to balance the workload and urgency of requests in order to maximize efficiency and minimize disruptions. The output of the Bayesian probability model will be the probability of answering a request within a given time span given the current workload.

[0063] The radiologist can configure the scope of requests to receive. This is very useful in situations such as night / weekend shifts or when only one radiologist is available to answer all requests. For example, during the night shift, there is usually one dedicated staff member who can be called in case of too much workload / emergency situations, etc. System 10 can perform this automatically or predict when this is also needed.

[0064] The radiologist login can be adjusted according to the above-selected routing mechanism. The radiologist can choose to log in either through a user-specific identity or through role-based login, in which case the radiologist will log in with the department or scanner that he / she supports.

[0065] The recipient device 30 provides a mechanism for the radiologist to provide a response. The primary user of the recipient device 30 is the radiologist, but other users responsible for responding to communication requests for radiology assistance are also considered.

[0066] At the receiving device 30, a comprehensive work list presents an overview of communication requests that a radiologist can open when he / she is idle, thus allowing the radiologist to plan tasks and time allocation, thereby reducing interruptions (e.g., by giving the radiologist an opportunity to complete the task he / she has started, which reduces task switching). For each request in the work list, basic information, status, requester, and urgency are presented. The basic information helps link the study to the request. In some embodiments, the minimum information to be provided may be the study / patient identifier. Additional information may also be provided to give a short clinical background, such as modality, room, scanner technician, scan type, patient information, etc. A request can have multiple statuses, including but not limited to "unsent", "new", "in progress", "closed", "reopened", etc. Filtering and reordering functions also enable the radiologist to control and reorganize the work list content. In addition, the receiving device 30 can forward or automatically forward the request to the requester device 18. A challenge for radiologists is that they often encounter problems that are not suitable for themselves (i.e., unnecessary problems). Additionally, if they are called away, the system should automatically reroute (especially more urgent) problems.

[0067] For each upcoming request for radiology assistance, there is an associated urgency. In one embodiment, the urgency is indicated by the expected response time in minutes. In this embodiment, the expected response time and / or the current waiting time and / or the expected response time minus the current waiting time can be displayed. In this embodiment, complex filters based on urgency can be applied, which facilitate requests that may not be urgent but are pushed to the top of the list due to the waiting time exceeding the expected response time. In some examples, the AI component 42 can combine the waiting time with the workflow to see which request is at the top of the list or should be at the top of the list.

[0068] In a suitable default method, only requests for which the radiologist is responsible for responding are sent. However, in some embodiments, the radiologist may be allowed to configure the scope of requests to receive. Channels for asynchronous and synchronous communication, screen sharing, and remote control are supported. The receiving device 30 not only supports one-to-one communication but also, in some embodiments, supports interdisciplinary group communication, which meets the needs of university hospitals for group consultations, multidisciplinary meetings, and learning.

[0069] The system can also manage the status of communications and provide reminders when needed. This enables both the requester and the recipient to automatically update the status of the communication and provide reminders when needed. Requests for radiology assistance can have multiple statuses, including but not limited to "not sent", "new", "in progress", "closed", "reopened", etc. "New" indicates that it has been sent to the recipient, but no action has been taken on the communication request yet. Once the status of a new work order has been changed, it can never be set back to "new". "In progress" indicates that the recipient is reviewing the communication request (i.e., for role-based requests, the request can include who the requested party is). "Closed" indicates that the communication request has been answered, or the recipient is not responsible for answering. "Reopened" indicates that the communication request was previously closed, but a follow-up question / request has been raised.

[0070] "Not sent", "new", and "in progress" are statuses automatically generated by the system. The user needs to decide on work orders to close or reopen. A notification of the status change will be sent to the user to follow the progress of the communication request. Additionally, reminders will be sent to ensure timely receipt of a response. Reminders can be triggered manually by the user or automatically based on defined rules. For example, a rule can be defined such as "send a reminder to the recipient when only 5 minutes remain before the request expires". The system can have a rule configuration module for setting reminders, or include personalized alerts and reminders for radiologists.

[0071] Figure 3 The system shown also includes a data source layer, such as the illustrative PACS 12 and / or radiology information system (RIS), patient electronic records, etc., to enable access to data in these databases. To support the above functions, the necessary data can be provided, which can include, for example, basic information about patients and studies, such as patient MRN, study ID, modality, scanner, room, technician, referring physician, etc.; employee information, such as the roles and professional information of technicians and radiologists; DICOM images; patient clinical background, such as the patient's historical laboratory results; and so on. The basic study information is used to link communication messages to the study. This information will also be presented in the work list to provide an overview of the open communications to the recipient. Employee information is needed to identify the message and allow the message to be sent to the appropriate message recipient. Providing radiologists with patient and imaging data in this solution also has the following advantages: they do not have to switch systems and can easily return to the reading tasks they may be performing during this period without having to switch patients or confuse the images / data they are viewing. DICOM images and patient clinical background are used to clarify the background of the problem and also allow radiologists to view the background in the sample application.

[0072] Figure 3The system shown in can be a "two-way device". That is, radiologists can also ask questions of technicians and referring physicians. Another advantage of the system is that each party doesn't have to remember as much information. Each party will also have more of an overview because they don't have to remember questions (e.g., when someone doesn't answer the phone), the status of their questions, and / or patient data (e.g., patient number). Two-way communication can also assist radiologists (and technicians / attending physicians who know what they still need to do). Additionally, radiologists can interrupt technicians / referring physicians.

[0073] In some embodiments, device 10 can be configured to sense specific background information regarding a radiology review request to update the urgency of the case ticket and the availability of the radiologist in real time. For example, device 10 can be configured to optimize case scheduling and interruption impact. The "interruption cost" is based on the complexity of the case the radiologist is working on and the level of engagement the radiologist experiences while performing the review. In this way, the technician can consider his / her reason for interruption based on the interruption cost and be more empathetic towards the radiologist. This allows for reducing, and in some cases eliminating, the impact of interruptions. In one approach, the background adaptation weighs both sides (urgency of the technician's request versus the radiologist's interruption cost) and presents a recommended follow-up action for the technician and / or radiologist. In some embodiments, a list of available radiologists who can also assist in resolving their problems / cases is provided to the technician.

[0074] The situation where a radiologist is interrupted by a technician (or another radiologist) often occurs in the context of an urgent case ticket or inquiry. In some embodiments, the case urgency is determined by automatically evaluating and / or by the technician manually evaluating his or her urgency score for the radiology assistance request. The real-time "interruption cost" is automatically evaluated based on the radiologist's current engagement score, combined with the urgency and complexity of the task he / she is currently performing (e.g., current radiology exam interpretation). These two main indicators (request urgency and interruption cost) are combined based on the determined importance of all the parameters mentioned, for example, as a weighted average. By considering both indicators, subsequent actions are performed and / or recommended.

[0075] As described above, device 10 is configured to perform imaging assistance method or process 200. Database 16 stores instructions that can be run by server computer 14 (and / or by requesting party electronic processing device 18 and / or receiving party electronic processing device 36) to perform imaging assistance method or process 200. In some examples, method 200 can be at least partially performed by cloud processing (i.e., server computer 16 can be implemented as cloud computing resources including a server computer in a self-organizing network).

[0076] ReferenceFigure 4 , and continuing to refer to Figure 1 , an illustrative embodiment of an example of the imaging assistance method 200 is schematically shown.

[0077] At operation 202, the requester RQ determines, quantifies, and reports the urgency of the imaging examination. The urgency of the imaging examination depends on several different factors. Figure 4 Four non-limiting illustrative factors are listed: patient history (e.g., critically ill patients may tend to have a higher request urgency); patient location (e.g., a patient loaded in the imaging system tends to have a higher request urgency, while a patient not scheduled for imaging today tends to have a lower request urgency); clinical urgency (e.g., an imaging session performed to evaluate whether a patient should immediately undergo emergency surgery tends to have a higher request urgency); and patient status (this factor can cover various situations, such as whether the patient is an inpatient or an outpatient). For example, if the patient is still on the patient table or in the dressing room, the work order has a higher priority. Additionally, the type of case, clinical urgency, and remaining wait list affect the priority of the work order. In some examples, the urgency changes when an answer has been found in another way or if the patient has to leave for another appointment. The device 10 can automatically quantify the urgency based on inputs from the imaging device, computer vision system (i.e., sensing whether the patient is still present), electronic medical record (EMR) (i.e., imaging request), and natural language processing (NLP) interpretation of questions from technicians related to the imaging knowledge database.

[0078] To perform operation 202 of estimating the urgency of the radiology assistance request, the device 10 is configured to determine individual scores for specific parameters sensed automatically or indicated manually by the technician. The patient history affecting the urgency score is filled in manually by the technician, as well as the clinical urgency score (based on the type and severity of the case) and the status and / or schedule of the patient. If the case work order or inquiry is more urgent based on whether the patient is still on the examination table or in the dressing room, it is automatically analyzed via a camera in the image acquisition room. All parameters have a specific importance level that is typically predetermined. However, this can be adjusted individually for each case. As mentioned before, a quantified urgency score is established from 1 - 10 due to the significance and severity of each parameter. These scores are classified as "low (1 - 4)", "medium (4 - 7)", and "high (7 - 10)" levels of urgency.

[0079] At operation 204, the recipient RC is determined (e.g., illustrative Figure 4The "interruption cost" score of the radiologist (in the radiology department). The interruption cost is determined by the radiologist operating the recipient electronic processing device 30. The interruption cost score is based on the commitment and engagement of the recipient RC in reading his / her current imaging examination or other current task (e.g., measured via a gaze tracking mode, pulse rate, and / or other suitable biometric sensor(s)), as well as the complexity and urgency of the current task. For example, if the radiologist is currently reading a complex magnetic resonance imaging examination, this will result in a higher interruption cost; however, if the radiologist is currently reading a simple chest X-ray, this will result in a lower interruption cost. Thus, the weighting of these parameters is directly related to the "distraction cost" of the recipient RC. The more focused the recipient RC is on a complex image examination, the higher the cost of distracting him / her (and vice versa).

[0080] The parameters considered to determine the "interruption cost" score are the radiologist's engagement, as well as the complexity and urgency of the current case he / she is reviewing. In a non-limiting illustrative embodiment that employs eye tracking as a biometric sensor, engagement and commitment are quantified by measurements of pupil dilation, head position, and / or body posture by an eye tracking device. The complexity and urgency scores are indicated by the technician when he / she creates the case work order. As previously mentioned, as a result of these elements, a quantified interruptibility score is established, for example, in the range of 1 - 10. These scores are classified as "low (1 - 4)", "medium (4 - 7)", and "high (7 - 10)" levels of interruption cost.

[0081] At operation 206, the recipient RC generates a recommended follow-up action for the requester RQ. To do this, the urgency and interruption cost are scored to determine the allowed / recommended communication mode from the requester RQ to the recipient RC. Depending on the balance of the two scores, the recommended follow-up action can include, for example, allowing an immediate interruption, submitting a request work order, or referring to another radiologist in cases where the case is urgent but the preferred radiologist cannot be disturbed. The assessment of urgency and interruption cost is continuous and real-time, so the device 10 can change its recommendations / rules when the situation of one party and / or the other changes. Additionally, when, for example, a radiologist is non-interruptible, the device 10 provides alternative solutions of other available radiologists. Table 1 shows a list of possible recommended follow-up actions based on the urgency and interruption cost scores.

[0082]

[0083]

[0084] Table 1

[0085] In some embodiments, facial recognition or other types of user identification (e.g., logins) can be implemented to identify and authenticate radiologists and technicians. The identification can be linked to a profile to understand their preferences and schedules. In this way, their personal data and attributes can also play a role in the equation, allowing for a more personalized and adaptive system. As a non-limiting illustrative example of this, each radiologist can a priori rate his or her proficiency in reading radiological examinations of different modalities (e.g., MRI, CT, PET, etc.). This information can be used to assess the current case complexity in a personalized manner. For example, if the current case is an MRI reading and the radiologist (identified by facial recognition) has self-rated his or her proficiency in MRI reading as low, then this will result in the weight of the current case complexity being rated as "complex" or "highly complex"; however, for another radiologist, if he or she has self-rated his or her proficiency in MRI reading as high, then this will result in the weight of the current case complexity being rated as "low" or "medium".

[0086] In some embodiments, emotion state sensing based on biometric measurements of radiologists (e.g., facial expressions, galvanic skin response, HRV, etc.) can be implemented. This also plays an important role in the interruptibility of radiologists. When a radiologist is feeling very stressed and frustrated, the "interruption cost" is considered to be higher than when he / she is feeling calm and neutral. This leads to an empathy system with more personalized and collaborative capabilities.

[0087] The present disclosure has been described with reference to the preferred embodiments. After reading and understanding the foregoing detailed description, others may make modifications and changes. The illustrative embodiments are intended to be construed as including all such modifications and variations as long as they fall within the scope of the claims or their equivalents.

Claims

1. A non - transitory computer - readable medium (16) that stores instructions executable by an electronic processor (14) to perform a method (100) for requesting radiology assistance, the method comprises: providing, on a display device (24) of a requester electronic processing device (18) operable by a requester, a requester graphical user interface (GUI) (28); receiving one or more inputs from the requester to fill fields in the requester GUI, thereby generating an assistance request (40) for radiology assistance; sending the assistance request for radiology assistance to a recipient electronic processing device (30) operable by a radiologist; providing, on a display device (36) of the recipient electronic processing device, a recipient GUI (38) showing a list (44) of assistance requests for radiology assistance; and tracking and marking the status of each assistance request for radiology assistance in the list.

2. The non - transitory computer - readable medium (16) according to claim 1, wherein, the fields in the requester GUI (28) at least include: a recipient field configured to receive a recipient as a specific radiologist or a radiologist role; a field for assigning a priority on a predefined priority schedule; and a field for attaching a document or a document link.

3. The non - transitory computer - readable medium (16) according to any one of claims 1 and 2, wherein, the list (44) of assistance requests displayed on the recipient GUI (38) includes a work list of the requests addressed to the recipient based on one or more criteria, the one or more criteria including at least priority or response time.

4. The non - transitory computer - readable medium (16) according to any one of claims 1 - 3, wherein, the recipient GUI (38) includes a field for a communication path between the recipient and each requester who has submitted an assistance request (40).

5. The non - transitory computer - readable medium (16) according to any one of claims 1 - 4, wherein, the recipient GUI (38) and / or the requester GUI (28) includes a field for updating the status of the assistance request (40).

6. The non - transitory computer - readable medium (16) according to any one of claims 1 - 5, wherein, the fields of the requester GUI (28) include a field for attaching clinical images that are the subject of the assistance request (40), and the requester can annotate the clinical images via the field, and the annotated clinical images are input into the field for attaching the clinical images.

7. The non - transitory computer - readable medium (16) according to any one of claims 1 - 6, wherein, the method (100) further comprises: establishing a natural communication path (19) between the requester and the recipient.

8. The non - transitory computer - readable medium (16) according to any one of claims 1 - 7, wherein, the method (100) further comprises: Generate the assistance request (40) using an artificial intelligence (AI) component (42).

9. The non-transitory computer-readable medium (16) according to claim 8, wherein, the AI component (42) is configured to: analyze computer-aided diagnosis (CADx) features of an imaging device; and generate the assistance request (40) based on the analysis of the CADx features.

10. The non-transitory computer-readable medium (16) according to claim 8, wherein, the AI component (42) is configured to: analyze clinical images generated by an imaging device; and generate the assistance request (40) based on the analysis of the clinical images.

11. The non-transitory computer-readable medium (16) according to any one of claims 1-10, wherein, the method (100) further includes: monitoring the scheduling of an upcoming radiological examination, including detecting an upcoming radiological examination with an incomplete examination card that requires information from a radiologist to complete the examination card; and generating a request for the requester to provide the information required to complete the examination card before the imaging examination begins.

12. The non-transitory computer-readable medium (16) according to any one of claims 1-11, wherein, tracking and marking the status of each assistance request for radiological assistance in the list includes: estimating the urgency (202) of each assistance request for radiological assistance in the list; estimating the interruption cost (204) of interrupting a radiologist operating the recipient electronic processing device (30); and updating the status of the assistance request based on the estimated urgency score and the estimated interruption cost of each assistance request for radiological assistance in the list.

13. The non-transitory computer-readable medium (16) according to claim 12, wherein, the interruption cost (204) is estimated at least in part based on biometric sensor data collected by the radiologist operating the recipient electronic processing device (30).

14. The non-transitory computer-readable medium (16) according to any one of claims 12 and 13, wherein, the interruption cost (204) is estimated at least in part based on the complexity of the current task performed by the radiologist operating the recipient electronic processing device (30).

15. An assistance request method (100), the method comprises: receiving one or more inputs from a requester to fill in fields in a requester graphical user interface (GUI) (28) displayed on a display device (24) of a requester electronic processing device (18), the requester electronic processing device (18) being operable by the requester to generate an assistance request (40) for radiological assistance; sending the assistance request for radiological assistance to a recipient electronic processing device (30) operable by a radiologist; and tracking and marking the status of the assistance request for radiological assistance on a recipient GUI (38) provided on a display device (36) of the recipient electronic processing device.

16. The assistance request method (100) according to claim 15, wherein, tracking and marking the status of each assistance request for radiology assistance in the list includes iteratively: estimating the urgency (202) of the assistance request for radiology assistance; estimating the interruption cost (204) of interrupting the radiologist from operating the receiving party's electronic processing device (30); and updating the status of the assistance request for radiology assistance based on the urgency score and the estimated interruption cost.

17. An assistance request method (200), the method comprises: determining the urgency of a medical imaging examination performed by a requester; determining an interruption score of a radiologist to whom the requester is requesting assistance; and determining at least one subsequent action provided by the radiologist to the requester based on the determined urgency and the determined interruption score.

18. The method (200) according to claim 17, wherein, determining the interruption score includes: sensing one or more biometric parameters of the radiologist; and determining the interruption score based on the sensed biometric parameters.

19. The method (200) according to any one of claims 17-18, wherein, determining the urgency includes: determining the complexity of the medical imaging examination; and determining the urgency based on the determined complexity.

20. The method (200) according to any one of claims 17-19, wherein, determining the at least one subsequent action includes: weighting the urgency and the interruption score to determine one or more permitted or recommended communication paths.

21. The method (200) according to any one of claims 17-20, wherein, the method (200) further comprises: using facial recognition to identify at least one of the radiologist and the requester, and the at least one subsequent action is also determined based on the identification.

22. The method (200) according to any one of claims 17-21, wherein, the at least one subsequent action includes: allowing an immediate interruption, submitting a request work order, or referring to another radiologist in case of an urgent case but the preferred radiologist cannot be disturbed.

Images