CN120092301A - Radiology Workflow Coordination - Google Patents

Abstract

The radiological workflow assistance method includes retrieving information about an upcoming radiological examination of a patient, including information identifying an imaging modality of the upcoming radiological examination, information about the patient, and information obtained from a radiological examination order. Based on the retrieved information, a role-specific exam complexity metric is determined for the respective personnel role of the workflow for performing the upcoming radiological exam. Based on the determined role-specific check complexity metrics, recommendations and/or assistance are provided to personnel assigned to the personnel role in the workflow. Assisting may also include generating a draft communication request by filling out a communication request form based on the query and radiological examination context, enabling the requestor to edit and approve the draft communication request, and transmitting the approved communication request to the recipient identified therein.

Description

Radiology workflow coordination

Technical Field

The following generally relates to the radiology arts, medical imaging arts, radiology Information Technology (IT) support arts, and related arts.

Background

Radiology (also known as medical imaging) is used in a wide range of medical fields for diagnosing and monitoring diseases and other medical conditions. Examples of radiation imaging modalities include Magnetic Resonance Imaging (MRI), computed Tomography (CT) and other X-ray imaging modalities, emission imaging modalities such as Positron Emission Tomography (PET) and Single Photon Emission Computed Tomography (SPECT), and the like. Radiological imaging may also be classified in the medical field, such as oncology imaging, sports medical imaging, cardiac imaging, image Guided Therapy (iGT), etc. Radiological workflow is typically divided into several phases including image acquisition, image interpretation, and clinical application phases. Image acquisition is typically performed by an imaging technician or technician expert or operator, etc. Image interpretation is typically performed by a radiologist, who is typically a doctor (e.g., m.d.) dedicated to interpreting radiological image studies. Clinical applications are typically performed by a patient's physician, e.g., a general practitioner or specialist, such as an oncologist, cardiologist, orthopedic surgeon, etc. Radiology workflows typically involve additional personnel that participate in various additional roles, such as nurses, patient transport personnel, cleaning personnel that clean and disinfect medical imaging equipment and ancillary equipment between imaging examinations, document personnel that maintain radiology examination schedules, information Technology (IT) personnel that maintain image archiving and communication systems (PACS), radiology Information Systems (RIS) and/or other IT infrastructure, biomedical engineers (biomedical) or other field engineers that qualify to perform some type of medical imaging equipment maintenance, multilingual translators that provide translations for patients that do not speak local language, and the like.

Some radiology workflows also include additional personnel that participate in remote roles. For example, a Radiological Operations Command Center (ROCC) may provide assistance to imaging technicians and/or other personnel involved in radiological examinations. ROCC provides a staff of remote specialists that performs the role of providing remote assistance to imaging technologists performing radiological examinations via telephone, video call, text messaging, etc. ROCC staff often include advanced imaging technologists and/or radiologists that can provide additional expertise to assist inexperienced local imaging technologists. Such assistance may be beneficial because it may be expected that a local imaging technician performs radiological examinations using a range of imaging modalities (MRI, CT, PET, etc.) that may be manufactured by different vendors to support a range of medical fields (oncology, cardiology, sports medicine, etc.), working with patients who may have a range of acute and chronic medical conditions. As another example, some medical institutions may outsource the radiological exam interpretation phase to a remote radiology department that hires staff of radiologists on hold to perform remote radiological exam readings. As yet another example, a medical imaging device manufacturer or a third party service provider may be invoked to deal with more complex medical imaging device maintenance issues that cannot be handled internally by an on-hand biomedical engineer. The use of such a class of remote specialists advantageously extends the capabilities of medical institutions without the attendant human resource costs of hiring specialists dedicated to these different fields.

Thus, the performance of radiological examinations involves collaboration between personnel served in various roles. In one non-limiting illustrative example, a patient's physician composes a radiological examination order specifying the examination reason and other relevant information. The order is received by a radiological staff member scheduling an examination of the patient. At a specified time, the patient is transported to the radiology department (either by itself, or by transportation staff and/or nurses, depending on the mobility of the patient), and the nurses, transportation staff and/or imaging technique specialists load the patient into the medical imaging apparatus. The imaging technologist then sets up and performs an imaging scan to acquire the medical image requested by the examination order. The images are reviewed by imaging technologists (and possibly also by ready-to-use radiologists) to ensure that they are of clinical quality, rescanning can be performed appropriately, and the final clinical images and associated metadata are stored in DICOM format in PACS. The patient is discharged as needed with the aid of nurses and/or transportation staff based on the mobility of the patient. At a specific time thereafter, the radiologist logs onto the PACS, downloads images and associated metadata of the radiological exam, and performs radiological reading of the images based on the patient's electronic medical records and/or other available information, and records the conclusion of the interpretation in a radiological report that is stored in the PACS and forwarded to the referring physician for clinical use. This is merely an example workflow.

A problem that may arise is that it may be difficult to effectively coordinate the workload of personnel in different roles to effectively perform radiological examinations and maintain high throughput for the radiology department. Inefficiency or lack of communication may introduce delays in the workflow or may even require costly rescheduling of radiological examinations to the radiology department, inconvenience the patient, and potentially compromise patient care quality. As one illustrative example, if the imaging technician determines at some point in the radiological exam that he or she needs assistance from the ROCC, the imaging technician then places a call to the ROCC. Since this is an unscheduled assistance request, there may be some delay before a remote expert at the ROCC is available to process the assistance request. During this delay, the patient may become trapped in the imaging scanner, and the delay may result in an unexpected backlog of the radiological examination schedule. Similar delays may be caused by other unexpected events such as special transportation difficulties for the patient, infectious diseases for the patient (such as COVID-19), requiring additional hygiene after the examination, etc.

Additional difficulties may be caused by poorly prepared communication requests. For example, if the request for assistance from the ROCC does not include some important information, this may delay assistance or may cause the request to be handled by a ROCC staff member who is not sufficiently aware of the problem at hand to provide effective assistance. Conversely, if the requestor prepares a detailed request with a large amount of information, this may itself introduce delay because the requestor must locate information that may be stored in various databases. Even with such efforts, the requestor may not be able to provide important information because the requestor is unfamiliar (due to making the request) with how to solve the problem.

Some improvements are disclosed below.

Disclosure of Invention

In one disclosed aspect, a radiological workflow assistance apparatus includes an electronic processor and a non-transitory storage medium storing instructions readable and executable by the electronic processor to perform a radiological workflow assistance method. The method comprises retrieving information related to an upcoming radiological examination of a patient, the information comprising at least information identifying an imaging modality to be used in the upcoming radiological examination, information about the patient, and information obtained from a radiological examination order for the upcoming radiological examination, determining a role-specific examination complexity measure for a respective personnel role of a workflow for performing the upcoming radiological examination based on the retrieved information, and providing a recommendation and/or assistance to personnel assigned to act as a personnel role of the workflow based on the determined role-specific examination complexity measure.

In another disclosed aspect, a radiological workflow assistance apparatus includes an electronic processor and a non-transitory storage medium storing instructions readable and executable by the electronic processor to perform a radiological workflow assistance method. The method includes receiving, via an electronic device of a requestor operated by a requestor, a query regarding a radiological exam, generating a draft communication request by filling in fields of a communication request form based on the query and a context of the radiological exam, providing a user interface on the electronic device of the requestor, the user interface displaying the draft communication request such that the requestor can edit the draft communication request and approve the draft communication request, whereby the draft communication request becomes an approved communication request, and transmitting the approved communication request to a recipient identified in the approved communication request.

One advantage resides in providing advance notification to personnel participating in a radiological workflow of a radiological examination that certain difficulties may exist.

Another advantage resides in such advance notification tailored to a particular role expected to be affected by a particular difficulty.

Another advantage resides in providing automatic subscription to auxiliary requests to address particular difficulties.

Another advantage resides in providing role-specific predictions of upcoming radiological exam complexity, enabling staff participating in radiological exams in various roles to prepare ahead of time for upcoming radiological exam complexity.

Another advantage resides in providing automatic or semi-automatic construction of auxiliary requests with sufficient information to facilitate resolution of the requests.

Another advantage resides in providing such automatic or semi-automatic construction of an assistance request based in part on the context of the radiological examination to which the assistance request pertains.

A given embodiment may not provide any of the foregoing advantages, provide one, two, more or all of the foregoing advantages, and/or may provide other advantages that will become apparent to one of ordinary skill in the art upon reading and understanding the present disclosure.

Drawings

The invention may take form in various components and arrangements of components, and in various steps and arrangements of steps. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.

FIG. 1 diagrammatically illustrates a radiological workflow assistance apparatus in the context of a diagrammatically represented radiological examination environment.

FIG. 2 diagrammatically illustrates an embodiment of role-specific checking complexity metric prediction of FIG. 1.

FIG. 3 diagrammatically illustrates a radiological-timetable-based User Interface (UI) for a remote imaging technician.

FIG. 4 graphically illustrates a radiological-timetable-based UI for an in-situ imaging technician.

Fig. 5 diagrammatically shows an example of a role-specific complexity metric in the form of a multidimensional vector.

Fig. 6 diagrammatically shows an illustrative embodiment of the process awareness assistance request process of fig. 1.

FIG. 7 diagrammatically illustrates a Graphical User Interface (GUI) representation of a radiology examination workflow timeline.

Detailed Description

Fig. 1 diagrammatically illustrates a radiological workflow assistance apparatus 8 in the context of a diagrammatically represented radiological examination environment. Radiological examination of a patient 10 is performed using a medical imaging device 12. As used herein, the term "patient" merely indicates that the individual undergoing radiological examination-patient 10 may be a hospital patient, an outpatient, or a person undergoing a conventional screening radiological procedure. In a typical arrangement, imaging device 12 is located in scan room 14, and imaging device controller 16, which is operatively connected to control imaging device 12, is located in an adjacent control room 18, controlling medical imaging device 12, typically separated by a wall having a large window, so that imaging technologist 20 can view scan room 14 in which the patient is located while imaging technologist 20 is located in control room 18. The use of the illustrative individual control room 18 is common in the case of imaging modalities (such as MRI or CT) that can generate strong magnetic/electromagnetic fields, ionizing radiation, etc., but may be omitted in the case of some imaging modalities or some specific radiology layouts, in which case the imaging device 12 and imaging device controller 16 are suitably located in a single room. Medical imaging device 12 may generally have any type or imaging modality for imaging a human body for medical diagnostic, monitoring, screening, or other similar purposes. By way of non-limiting illustrative example, the medical imaging device 12 may include an MRI scanner, a CT scanner or other X-ray imaging modality, a PET scanner, a SPECT scanner, a multi-modality imaging device such as a CT/PET scanner, or the like. Although an imaging technologist 20 is shown in fig. 1 located in the control room 18, the imaging technologist 20 will typically move back and forth between the scan room 14 and the control room 18, e.g., into the scan room 14 to prepare the patient 10 and load the patient 10 into the medical imaging device 12, return into the control room 18 to set up and initiate a scan using the imaging device controller 16, and return to the scan room 14 as appropriate to perform actions such as positioning local MRI coils, and eventually unload and prepare the patient for discharge. The person roles played by the imaging technologist 20 may be otherwise named, for example, imaging technologist, radiological technologist, imaging apparatus operator, etc.

With continued reference to FIG. 1, the diagrammatically represented radiological examination environment is shown as an extended environment, which includes the locations of additional personnel participating in the radiological examination. As a non-limiting illustrative example, a patient room 22 having a plurality of patient rooms 24 is shown. Where the illustrative patient 10 is a hospital patient (i.e., a hospitalized patient), the patient may typically reside (i.e., at the time of admission) in one of the patient rooms 24 assigned to the illustrative patient 10 and may be nursed for a nurse represented by illustrative nurse 26. The radiological examination workflow then begins with a member of the nurse 26 and/or hospital transport staff 28 preparing the patient 10 and transporting it from the patient room 22 to the scan room 14, and may also perform or assist in preparing the patient 10 and loading the patient 10 into the imaging device 12. (on the other hand, if the patient 10 is an outpatient or screening patient, the patient 10 may be moved sufficiently to transport himself or herself to the radiology department without such assistance, but the imaging technician 20, nurse 26, and/or transport staff 28 may still assist in preparing the patient 10 and loading it into the imaging device 12. Other staff roles may be involved in coordination of patient arrival and discharge, not shown, such as a receptionist or may handle other staff files, translators (if needed), etc. that add radiological exams to the radiological exam schedule.

With continued reference to FIG. 1, other personnel roles may be involved in the radiological workflow. As a non-limiting illustrative example, fig. 1 also depicts a radiology department 30 and a Remote Operations Control Center (ROCC) 36, the radiology department 30 containing a radiology workstation 32, wherein a radiologist 34 is in operation during a radiology examination, the Remote Operations Control Center (ROCC) 36 containing a remote imaging technologist workstation 38, wherein a remote (and typically advanced) imaging technologist 40 stands by at any time to provide remote assistance to the local imaging technologist 20. The person roles played by the tele-imaging technologist 40 may be otherwise named, for example, tele-imaging technologist, tele-radiology technologist, tele-expert, etc.

In a typical radiological examination workflow, the workflow is initiated by a radiological examination order placed by a consultant (not shown), such as a General Practitioner (GP) of the patient 10, or a specialist, such as an oncologist, cardiologist, etc. The amount of detail in the radiological examination order may depend on how well the referring physician knows about the radiology, but in general, the radiological examination order will typically contain at least the examination reason, the imaging modality to be used, and the identity of the patient 10 (e.g., by patient name, social security number, patient identification number used in the hospital, various combinations thereof, etc.). The ready-to-arm radiologist 34 (or possibly some other radiologist) may prepare more detailed imaging protocols or instructions based on the radiological examination order. During radiological examinations, a ready-to-arm radiologist 34 may provide consultation assistance to the local imaging technologist 20 in deciding on details about imaging scan or protocol configuration, advice about handling unexpected challenges (e.g., obese patients, pediatric patients who cannot stay stationary during imaging data acquisition, etc.). In some radiological examination workflows, it is also contemplated that ready-to-use radiologists 34 provide initial review of acquired images to ensure that they are of sufficient quality, type, and field of view to provide the information needed to satisfy a radiological examination order. (such a "quality control" review by the ready-to-arm radiologist 34 would precede the actual clinical reading of the radiological exam, during which the radiologist 34, or some other radiologist, reviews the image in detail and writes out a radiological report presenting the radiologist's findings). To provide such review, the on-demand radiologist 34 may physically walk into the control room 18 to review images on the display of the imaging device controller 16, or those images may be transmitted via an electronic network to the radiological workstation 32 for review by the on-demand radiologist 34 residing there.

ROCC36 is also an optional component of a radiological examination workflow. Remote imaging technologists 40, if provided, at the ROCC36 are ready to assist the local imaging technologists during radiological examinations, including being ready to assist the illustrative local imaging technologists 20 in performing radiological examinations on the illustrative patient 10. The remote imaging technologist 40 is typically an experienced and/or advanced imaging technologist that can provide assistance to the (possibly less experienced and/or more primary) local imaging technologist 20 that is actually performing radiological examinations. Such assistance may be provided by telephone, video call, text messaging, etc. To provide situational awareness to the remote imaging technologist 40 so that he or she can provide useful assistance, one or more cameras, microphones, and/or other sensors (not shown) may be located in the scanning room 14 and/or the control room 18, with feeds from these cameras, microphones, or other sensors being delivered to the remote imaging technologist workstation 38 and presented by the remote imaging technologist workstation 38. Additionally or alternatively, a video segmenter, screen sharing software, or the like may be provided to capture the display of the imaging device controller 16 in real-time and present it on the remote imaging technologist workstation 38 for viewing by the remote imaging technologist 40.

As also shown in fig. 1, each of the illustrative personnel who take the role of and participate in the radiology workflow typically has electronic equipment. As a non-limiting illustrative example, the local imaging technologist 20 has an imaging device controller 16, and may also have one or more other electronic devices, such as a tablet computer, for referencing radiology schedules, providing video calls to the ready-to-use radiologist 34 and/or remote imaging technologist 40, etc. His or her electronics including the illustrative radiological workstation 32 are shown to the radiologist 34. The remote imaging technologist 38 is shown with his or her electronics including an illustrative remote imaging technologist workstation 38. Where the nurse 26 and transportation staff 28 are typically more mobile, the corresponding electronic devices may be, for example, an illustrative nurse's cellular telephone (cell phone) 42 and an illustrative transportation staff's cell phone 44, respectively. More generally, a particular person's electronic device is an electronic device that is at least accessible by the particular person. As some non-limiting illustrative examples, the electronic device of a particular person may be a cell phone, tablet computer, workstation, etc. that the particular person is logged on to, or an imaging device controller, radiology department computer, etc., that is typically accessible by a person including the particular person, or by a person in the role of the person that the particular person plays. In some such cases, a particular person may correspond to a group of persons interchangeably taking the role of a person in a radiology examination workflow, for example, in the case of a nurse 26, his or her electronic device may additionally or alternatively be an electronic whiteboard of a nurses' station of the patient room 22. These are merely non-limiting illustrative examples. In any of these cases, the content may be presented on the electronic device of the particular person. Rendering content accessible by a person on a person's electronic device refers to causing the person's electronic device to render the content. Typically, the presentation will be by displaying the content on an LCD display, an LED display, an OLED display, or other display of the person's electronic device. However, the content may be presented on the person's electronic device in other human perceptible ways, such as through computer-generated speech output by speakers of the electronic device, or as Virtual Reality (VR) or Augmented Reality (AR) content in the case where the person's electronic device is a VR or AR headset. It may be noted that in some cases, there may be a time lag in presentation. For example, if the person's electronic device is a cell phone, the content may be displayed only when the person logs in or unlocks the cell phone. In such a case, in some embodiments, an audible notification tone may be issued to notify the person that the content is available.

To further illustrate a typical extended radiological examination environment, table 1 provides some examples of the processes in a radiological examination workflow, as well as the personnel roles involved, the corresponding tasks, and the information sources to obtain information about these tasks.

TABLE 1

Fig. 1 and table 1 provide non-limiting illustrative examples of an extended radiological examination environment to illustrate participation, collaboration, and communication between a clinician and other persons acting in a wide variety of personnel roles, such as an illustrative (local) imaging technologist 20, a remote imaging technologist 40, a ready-to-arm radiologist 34, a nurse(s) 26, a transportation staff 28, and/or potential other personnel roles not shown, such as a staff for a document. The electronic devices 16, 32, 38, 42, 44 of the various participants are typically connected to an electronic network (e.g., including a hospital IT network, the internet, etc.) so that these devices can be used to communicate, wired and/or wireless, via email, text message, audio or video call, between the various persons participating in the radiological examination. However, scheduling and/or initiating such communications between people participating in a radiological examination workflow can be challenging. The auxiliary request from the requester may correspond to an undesired interruption by the requester. Communication requests due to unexpected problems may be particularly difficult to accommodate. In addition, if the request sent by the requester is incomplete, time may be wasted by the requester collecting the missing information. In some cases, the requestor may also be unsure to whom the request should be directed.

The radiological workflow assistance apparatus 8 operating in the context of a radiological examination environment advantageously facilitates more efficient communication between persons participating in a radiological examination workflow. As diagrammatically shown in fig. 1, the illustrative radiological workflow assistance apparatus 8 implements various radiological examination workflow methods or subsystems 50, such as a role-specific examination complexity metric prediction 52 and a process awareness assistance request system 54. The radiological workflow assistance apparatus 8 may be suitably embodied by an electronic processor 56 (e.g., an illustrative server computer 56 or other computer with suitable IT network connection and processing capabilities) and a non-transitory storage medium 58, the non-transitory storage medium 58 storing instructions readable and executable by the electronic processor to implement the radiological examination workflow assistance 50. The non-transitory storage medium 58 may include, for example, a hard disk, a Solid State Disk (SSD), flash memory, an optical disk, various combinations thereof, and the like. It should be appreciated that the electronic processor 56 may be implemented as a plurality of electronic processors in communication with each other, and as such, the non-transitory storage medium 58 may be implemented as a plurality of non-transitory storage media.

The role-specific exam complexity metric prediction 52 provides a pre-estimate to the person participating in the radiological exam workflow as to how complex the radiological exam will be. This may reduce the problem of unexpected assistance requests by providing advance notice that may involve radiological examination of such requests. Role-specific exam complexity metric prediction 52 advantageously provides different complexity metric predictions for different personnel roles, as a given radiological exam may be more or less complex for a person who plays a different personnel role. As just two examples, if the patient 10 is weakened, this may greatly increase the complexity of the nurse 26 and transportation staff 28, as they may require a gurney, wheelchair, or other transportation means, and/or may require additional people to assist the patient. On the other hand, the fragility of the patient 10 may present fewer challenges to the local imaging technologist 20 and may present little additional complexity to the ready-to-arm radiologist 34. On the other hand, if the patient 10 is undergoing a CT examination and has a metal implant in or near the anatomy to be imaged, this can greatly increase the complexity of radiological examination of the local imaging technologist 20, the remote imaging technologist 40 (which may be called to provide advice or verbal assistance), and the ready radiologist 34 that would need to carefully review the images to ensure that the metal implant has not obscured or obscured the relevant anatomy. The metal implant may have little or no effect on the complexity of the examination of nurse 26 and transport 28.

In one approach, role-specific exam complexity metric prediction 52 includes retrieving information related to an upcoming radiological exam of patient 10 including at least information identifying an imaging modality to be used in the upcoming radiological exam, information about patient 10, and information obtained from a radiological exam order of the upcoming radiological exam, determining a role-specific exam complexity metric for a corresponding personnel role of a workflow for performing the upcoming radiological exam based on the retrieved information, and providing recommendations and/or assistance to personnel assigned to take the personnel role of the workflow based on the determined role-specific exam complexity metric. In some embodiments, the role-specific exam complexity metric comprises a multi-dimensional vector, wherein each dimension of the multi-dimensional vector includes a value indicative of a role-specific complexity of the upcoming radiological exam with respect to a corresponding aspect of the upcoming radiological exam. This may enable further narrowing of the timing and scope of possible assistance requests.

The process-aware assistance request system 54 provides context-aware assistance in preparing assistance requests. In one illustrative embodiment, in response to receiving a query regarding a radiological exam via a requestor's electronic device (e.g., one of the participant's electronic devices 16, 32, 38, 42, 44) operated by the requestor, the process-awareness assistance request system 54 generates a draft communication request by filling in fields of a communication request form based on the query and the context of the radiological exam, and provides a User Interface (UI) on the requestor's electronic device that displays the draft communication request such that the requestor can edit the draft communication request and approve the draft communication request, whereby the draft communication request becomes an approved communication request. The auxiliary request system 54 then sends the approved communication request to the recipient identified in the approved communication request (e.g., by sending it to another one of the participant's electronic devices 16, 32, 38, 42, 44 that is associated with the recipient).

Referring to FIG. 2, an illustrative embodiment of role-specific check complexity metric prediction 52 is described. In a first step, information about an upcoming radiological examination of the patient 10 is obtained. Typically, the information includes at least information identifying an imaging modality to be used in the upcoming radiological examination, information about the patient, and information obtained from a radiological examination order for the upcoming radiological examination. This information may be obtained from various information sources 60, such as a Radiology Information System (RIS) that may, for example, store radiology examination orders (typically containing at least patient identification and imaging modalities and examination reasons) and radiology schedules that include information about patient and personnel assignments for the arrangement of various personnel roles in the radiology examination workflow (or for the radiology work shift arrangement for the upcoming radiology examination), medical imaging device log files, PACS tags, HL7 messages, cameras and sensors used by ROCC36 (if available), and the like. The information sources 60 listed in fig. 2 should be understood as non-limiting illustrative examples. Retrieving information from these information sources 60 may be by means of a set of scripts that retrieve allowed and anonymous data from the available data sources, parse, clean up and store the data in a local or remote protected database in a predefined pattern.

The automation process 62 filters the retrieved data and an additional automated feature selection process 64 selects a role related feature 66 for each person role based on the tasks of the target person role (e.g., such as the roles listed in table 1 and/or shown in fig. 1). In one embodiment, a process model (such as a business process model) is used to define all activities (tasks) in the process and the corresponding human resources connected to each activity. In this way, the roles of the staff members participating in a particular activity may be identified. For example, for imaging technologists, their task is mainly to perform scanning examinations. The complexity of their tasks depends on the patient's condition, the nature of the examination, and their own level of expertise. Thus, these features would be useful inputs to a role-specific predictive model implemented as, for example, an Artificial Intelligence (AI) model. On the other hand, for transportation staff, their task mainly involves transporting hospitalized patients from hospital wards to the scanning cabin. Patient condition is the most relevant factor for its task and will therefore be a valuable feature for a transportation staff role-specific predictive model, while the examination characteristics do not have much impact on transportation needs, but may be agents in the absence of unknown patient characteristics.

The output of the automated processes 62 and 64 is a set of role-related features 66 for each of the personnel roles that participate in the radiological examination workflow. For each person role, a corresponding role-specific predictive model 68 is applied to the role-related features 66 to generate a role-specific inspection complexity metric 70 for that person role. In fig. 2, the boxes representing output role-specific exam complexity metrics 70 are labeled by the corresponding roles, such as "nurse," "imaging technician," "cleaning staff," "transportation staff," "radiologist," and "other support" (e.g., remote imaging technician 40 of fig. 1). In one non-limiting illustrative embodiment, the role-specific predictive model 68 is a trained AI model, such as an Artificial Neural Network (ANN) model. In embodiments where the role-specific exam complexity metric 70 of a role comprises a multi-dimensional vector, where each dimension of the multi-dimensional vector contains a value indicative of the role-specific complexity of an upcoming radiological exam with respect to a corresponding aspect of the upcoming radiological exam, a supervised model supporting multiple classes of output may be used. The model may vary depending on the set of role related features 66. For example, a random forest classifier may be a suitable choice if the feature set selected for the imaging technologist is mixed with classification and numerical data. A Support Vector Machine (SVM) classifier may be a suitable choice if the feature set selected for another role consists of numerical data only. These are merely non-limiting illustrative examples. To provide role-specific inspection complexity predictions, the applied prediction model 68 may be varied for each target role determined by the characteristics of the selected feature set. In another embodiment, several statistical and neural network algorithms may be tested to determine the algorithm with the best performance on the test data and the algorithm that is well summarized on the unseen data.

Referring to fig. 3 and 4, the output persona-specific exam complexity metrics 70 from fig. 2 may be used to provide advice and/or assistance to personnel assigned to take on the role of a workflow, e.g., via a radiology-schedule-based User Interface (UI) as shown in fig. 3 and 4. The radiology schedule-based user interface may be implemented, for example, through a web or app-based Application Program Interface (API). Fig. 3 illustrates such a radiological time-schedule based UI72 for the advanced (i.e., remote) imaging technologist 40, while fig. 4 illustrates such a radiological time-schedule based UI74 for the live (i.e., local) imaging technologist 20. Each scheduled upcoming radiological examination is listed on the schedule as a row with a left scheduled time block. The upcoming radiological exam of each arrangement is color coded according to the advanced technical expert specific complexity metric 70 calculated by the process of fig. 2, e.g., red may be used for high complexity prediction, yellow for medium complexity prediction, and green (or white, i.e., uncolored) for low complexity prediction. (in fig. 3 and 4, the color coding is shown graphically by different types of shading or hatching-optionally, such shading or hatching and/or other types of highlighting may actually replace the color coding). Notably, the role-specific complexity metrics 70 may be different because the UI72 of fig. 3 is for an advanced ROCC imaging technologist, while the UI72 of fig. 4 is for a local (in-situ) imaging technologist. This is illustrated in fig. 3 and 4, because the 9:00 upcoming radiological exam (standard liver exam of patient Vera Cruz) has different shadows in fig. 3 and 4 reflecting different complexity metrics determined for advanced ROCC imaging technologists as compared to local (on-site) imaging technologists. Another difference is that radiological examinations from 12:30 and beyond are listed on the advanced technical specialist's UI72, but omitted from the local technical specialist's UI74, reflecting (in this example) the fact that the local technical specialist is working at 12:30. Although fig. 3 and 4 provide two illustrative UIs for two different personas, more generally, each persona may be provided with a different persona-specific schedule-based UI and the appropriate UIs presented on the respective participant's electronic device 16, 32, 38, 42, 44 according to their persona.

The UI may also include other features implemented using suitable Graphical User Interface (GUI) technology and user interfaces (e.g., via a mouse pointer or touch screen). In some embodiments, by hovering over the name of each technical expert, the title and basic expertise of that technical expert may be viewed. Further, by hovering over the check, the reasons for the assigned role-specific complexity metrics (as indicated by color coding) can be viewed, e.g., why the check is marked as "unlikely to need support", "likely to need support", or "very likely to need support", etc. An example of this is shown in fig. 4 as a pop-up bubble for examination at 10:00 (for foot examination of patient Don Quixote). This is a generalized text that may be automatically composed of the most contributing features of the character-related features 66, which may be suitably output by the AI predictive model 68. Further, it is optionally possible to see which technical expert has subscribed to/requested support for which scheduled inspection. When hovering over the yellow button, the message/opinion left by the field technician can be seen highlighting the intended support, as shown by the 13:00 radiological examination in FIG. 3. The UI72 of the advanced technical specialist (which may be arranged to support two or more concurrent radiological examinations) may optionally highlight any scheduling conflicts that need to be supported simultaneously. The example UI74 of the local technical specialist provides a button indicating that "remote support is subscribed to" (from ROCC), if this is the case, or "click to subscribe to support, if support has not yet been subscribed to. These selection buttons suitably invoke a ROCC support scheduling UI (not shown) that enables the local technical specialist to subscribe to support, including adding comments about what assistance is being requested, which comments are available to the advanced technical specialist, for example, through a pop-up window as shown in fig. 3. Wherein more generally UIs for different personnel roles may provide various information and/or control options appropriate for a particular role.

Although different UIs are provided for different roles, optionally the UI may switch between roles, for example using the roles shown in the upper right of the UI74 of fig. 4, a drop down list user dialog.

Referring back to fig. 2, in embodiments in which the role-specific predictive model 68 is an AI model, various methods may be used for training with various training data sources. To train an AI prediction model, a set of features and known complexity values ("reality") are typically provided. Once trained, the AI predictive model can predict the complexity value when provided with the feature. The reality may be collected in different ways, such as by means of a questionnaire or electronic feedback via a graphical user interface, by staff members being required to rate the complexity of the task or activity just performed, indirectly by measuring deviations of certain workflow parameters from an expected average (e.g. checks that are longer than typical checks of the same kind may be rated more complex), by measuring whether a support request related to a certain activity has occurred, e.g. by monitoring support requests or support calls in a ROCC setting (activities associated with support requests are then rated more complex than other activities), etc. As non-limiting illustrative examples, features provided to the AI prediction algorithm may include examination details (agreement requested, clinical questions, referral information.+ -.), patient details (hospitalization/clinic, age, weight, gender, medical history, medication, special requirements, mobility, communication capabilities.+ -.), operational context (time of day, day of week, day of year, room, modality identifier.+ -.), profile/capabilities (experience, expertise, language capabilities.+ -.), assigned to active staff members/roles, and so forth.

In some embodiments, the role-specific predictive model 68 outputs a single complexity metric, which may optionally have a low granularity (e.g., low, medium, or high complexity). In other embodiments, instead of a single-valued complexity score (such as a low, medium, high complexity scale), the complexity score may be represented as a multi-dimensional vector, where each element (i.e., dimension) of the complexity vector represents an aspect of complexity.

Referring to fig. 5, an example of such a role-specific complexity metric in the form of a multi-dimensional vector 76 is shown diagrammatically. In this non-limiting illustrative example, by way of non-limiting illustrative example, the input features for computing multidimensional vector 76 may include, mobility challenge. The multidimensional vector 76 includes several aspects of predictive complexity scores. The scoring value may be, for example, between 0 and 1, so as to map to a likelihood. For example, a score of 0.1 means "less likely to require support", while a score of 0.9 means "more likely to require support". Examples of outputs may be:

"physical assistance required" =0.9;

"required language support" =0.9;

"support geometry planning" =0.1;

...。

the input feature fed into the predictive model 68 may be that the patient is challenged with mobility or that the patient is obese. Thus, predictive model 68 assigns a high score of 0.9 to the aspect "body assistance is needed". The multi-dimensional complexity score (i.e., vector 76) expresses all aspects of complexity simultaneously. All aspects of complexity may optionally be visualized individually to workflow participants, as individual actions may be required to alleviate the expected difficulties. For example, when a mouse pointer is hovered over an examination in the schedule UI72 or 74, the elements of the vector may be shown in a pop-up box (not shown). Training AI models for multidimensional complexity scores exploits the reality of all complexity aspects. In this case, different ways of obtaining the required feedback as described previously can be used simultaneously to ensure that all aspects of complexity are covered.

In general, the role-specific exam complexity prediction 52 may provide various types of recommendations and/or assistance to personnel assigned to the personnel role in the radiological exam workflow based on the determined role-specific exam complexity metrics. Fig. 3 and 4 present some examples, such as color coding a schedule based on a complexity metric or, more generally, presenting information indicative of a role-specific exam complexity metric 70 on an electronic device 16, 32, 38, 42, 44 that is accessible by a person 20, 26, 28, 34, 40 assigned to a person role in a radiology exam workflow. Since the complexity metrics are role-specific, this entails presenting information indicative of each role-specific check complexity metric 70 on one or more electronic devices 16, 32, 38, 42, 44 that are accessible by one or more persons 20, 26, 28, 34, 40 assigned to the person role taking the workflow corresponding to the role-specific check complexity metric. As previously described, such presentation may be delayed, for example, until the user unlocks his or her cell phone, and possibly until the user opens an appropriate application (app). Optionally, the app may push a notification, such as an audible beep and/or text message shown on the lock screen of the handset, so that the user immediately realizes that the presentation is available. Such notifications may be configurable, for example, the user may use a "setup" of the handset to turn off or modify the notification.

In another example of a recommendation and/or assistance, the role-specific check complexity prediction 52 may predict that assistance to a first person role of the workflow will be provided by a second person role of the workflow and automatically arrange for electronic calls (e.g., phone or video calls) between one or more persons acting as the first person role of the workflow and one or more persons acting as the second person role of the workflow. This may include, for example, predicting a time at which assistance to a first person role of the workflow is predicted to be provided by a second person role of the workflow, and automatically scheduling includes scheduling the electronic call within the predicted time. In some embodiments, the expected duration of assistance may also be predicted. In some such embodiments, where electronic calls are automatically placed, the time blocks of the placed call may be set using the predicted time at which assistance is to be provided and the predicted assistance duration. As one non-limiting specific example, the first person role of the workflow may be a local imaging technologist 20 operating the medical imaging device 12 in the workflow, and the second person role of the workflow may be a remote imaging technologist 40 not operating the medical imaging device in the workflow. As another non-limiting specific example, the first person role of the workflow may be a local imaging technologist 20 operating the medical imaging device 12 in the workflow, and the second person role of the workflow may be a radiologist 34 arranged to approve images acquired by the local imaging technologist 20 in the workflow.

It should be appreciated that the role-based complexity scores provided by embodiments such as the illustrative embodiments of fig. 2-5 advantageously provide role-based information to personnel for anticipating whether they may need to make a communication request. The system also provides advance notice of possible communication requests to recipients of such requests.

Referring back to FIG. 1, some illustrative embodiments of the process awareness assistance request system 54 are described below. The system may suitably include a workflow management system providing real-time process context, a user interface for requesting initiation and pre-selection of a subset of request items based on selection of UI elements selected for triggering the request, adapting the proposed items and providing additional context if needed, and approval, a machine learning model for predicting the probability of any remaining request items, and a user interface for selecting the proposed remaining request items. In some embodiments, a model of a radio process is provided in which the state of an instance of the running process is known at any time. The auxiliary request system 54 also takes appropriate paths to process and transmit communication requests, such as through telephone, video call, or text message paths. Auxiliary request system 54 may interoperate with commercially available videoconferencing systems using APIs that ensure compliance with data privacy, data security, and medical device specifications as may be appropriate for a given implementation.

The communication request may be, for example, a message sent to another participant in the radio workflow including specific questions and information about the background, or a ticket submitted to a ticketing system to be picked up and processed by another participant in the radio workflow. In one suitable embodiment, a request is defined as a set of request items entered, for example, by filling out fields of a communication request form. By way of non-limiting illustrative example, the fields may include an identification of the intended recipient of the request, an identification of the patient to whom the request pertains, information regarding the type of activity in the radiological procedure to which the request is connected (e.g., patient preparation, imaging exam, etc.), a reference to a point in time at which the content of the request is relevant or will become relevant (e.g., when the activity is scheduled or predicted to occur), the type of request (type of question or action requested, e.g., an "image quality exam" or "protocol modification approval"), a description of details of the request other than the type of request, an indication of urgency, information regarding the status of the current procedure within the department, etc. A given request may include only a subset of these fields, and/or may include additional fields.

Referring to FIG. 6, an illustrative embodiment of a process awareness assistance request process performed by system 54 is shown. In a first step, a user initiates a communication request by submitting a query about a radiological examination via a requester's electronic device operated by the requester. The query provides a subset 80 of the fields (also referred to herein as request terms) of the communication request table. In one suitable approach, the query is initiated by a user selecting a corresponding element in the graphical representation of the radiological examination workflow (see, e.g., fig. 7). In this way, the requestor implicitly selects some of the requested information simply by clicking on the relevant item on the screen to initiate the request. More generally, the system 54 may automatically extract the background 82 of the radiological examination. These request items 80, 82 provided with the initiation are considered fixed items 80 because they have been implicitly selected by the requester and are therefore not inferred by the AI algorithm of the system 54. The remaining request items 84 that are not provided with the request initiation 80 (i.e., the remaining fields of the request table 88) are proposed by the AI algorithm 90 based on the selected fixed item 80 and the process context 82. The process context 82 includes all real-time status information and resource allocation for all running process instances in the radiology department related to the radiological examination workflow as provided by the workflow management system. For example, process contexts include, but are not limited to, predicted, scheduled, or historical start and end times for all activities, assigning human resources to each activity, such as who is currently engaged in which activity, assigning rooms, devices, and other resources to each activity, and the like.

The AI algorithm 90 proposes missing request items based on historical requests and/or other information. The AI algorithm 90 may be implemented using a decision tree model, an Artificial Neural Network (ANN), a Support Vector Machine (SVM), or the like. The AI algorithm 90 determines the probability of each possible value of the proposed request term. The requestor is then presented with a draft request table 88 that includes the fixed item(s) 80 and the proposed request item(s) 84. Because the AI algorithm 90 may not be able to correctly predict the values of some of the requested items, the user may select among multiple options for the proposed item, for example, using a drop down list Graphical User Interface (GUI) dialog box, as indicated by the right hand "down" arrow in the proposed item 84 of FIG. 6. In some embodiments, the items in the drop down list are ordered according to probability as determined by the AI algorithm 90. In some embodiments, the user dialog of the proposed item 84 additionally or alternatively enables the requester to select to input a value that is not proposed by the AI algorithm 90.

Whenever the requester selects a value for any proposed request item 84, that item may then be considered a fixed item, and the AI algorithm 90 may optionally be rerun, as indicated by the reflow arrow 92 in FIG. 6, treating the most recently selected item as an additional fixed item to reevaluate the probability of the remaining request items. Once the requestor has selected or entered all of the required request items (i.e., all of the fields of the request form have been filled out), the draft request 88 for assistance is completed and the draft request form 88 becomes an approved request form 94. The approved assistance request 94 will then trigger a communication event or create a ticket. For example, the approved assistance request 94 may be presented on an electronic device of a second person (e.g., recipient) accessible to the second person (e.g., recipient). In some embodiments, the recipient may be a group of people, for example, if the request is for transportation assistance, an approved assistance request 94 may be broadcast by the hospital interphone. In some embodiments, the approved assistance request 94 may also be transmitted to a supervisor, such as an operations manager.

Optionally, each approved request form 94 and its corresponding (initial) draft request form 88 are used as training data for further training of the AI algorithm 90. In this training data, each proposed request item 84 generated by the AI algorithm 90 in the draft request from 88 that is unmodified included in the approved request table 94 constitutes a positive reinforcement, wherein the output of the AI algorithm 90 is validated, while each proposed request item 84 generated by the AI algorithm 90 in the draft request from 88 that is changed by the requester such that it differs in the approved request table 94 from the value included in the initial draft table 88 constitutes a negative reinforcement, wherein the output of the AI algorithm 90 is rejected (or at least modified). Using this training data, the AI algorithm 90 may be retrained or updated with training to improve the accuracy of the AI algorithm 90 at the time of use.

With continued reference to FIG. 6 and with further reference to FIG. 7, as previously described, some embodiments of the process awareness assistance request process performed by the system 54 utilize maintenance information and optionally a predictive model of a radiological exam workflow. Fig. 7 illustrates a GUI representation of a radiology examination workflow timeline 100, which may be presented, for example, on a display of electronic devices 16, 32, 38, 42, 44 (see fig. 1) of those participating in the workflow. Fig. 7 shows an example of a radiological examination workflow timeline 100 of a radiological examination workflow presented to an MRI technician giving an overview of the running and upcoming MRI procedure as provided by the workflow management system. In this example, the MRI technologist wishes to initiate a request for assistance during the "perform cardiac MRI" phase of the MRI exam, for example to ask the ready-to-arm radiologist 34 advice regarding the expected changes in the imaging protocol. (thus, in this example, the "requestor" is an MRI technologist, corresponding to imaging technologist 20 of FIG. 1, and the intended requestor is a ready-to-arm radiologist 34 of FIG. 1). To do so, the MRI technician clicks on a point in the "perform heart MRI" phase of the MRI exam workflow timeline 100 (as shown diagrammatically in fig. 7 by the mouse cursor 102 at that point). When clicking on the corresponding activity, the system of FIG. 6 pre-populates the request items "patient", "activity type" and "time" because the elements in the radiology examination workflow timeline 100 have been linked to all of these. Thus, these become fixed items 80 for the draft request of the assist 88. The AI algorithm 90 will then propose the most likely entry for the remaining items 84. For example, based on historical communication events, the AI model 90 may have learned that the most common recipient of a request for the activity type is a radiologist standing by at any time. Furthermore, the AI model 90 may have learned that given the context 82 of the request, the most common request type is "protocol modification approval". Furthermore, the AI model 90 may have learned that, given the context of the request, the most likely level of urgency for the request is "very urgent". Thus, the predicted recipients, request types, and emergency levels are pre-populated as proposed items 84 in a draft request table 88.

More generally, the request initiation depicted in fig. 7 requires receipt of a selection 102 of a time on the timeline 100 via the electronic device of the requestor, and in this case the context 82 of the radiological exam used in the generation of the draft communication request 88 is the context of the radiological exam at the selected time. Even more generally, in some embodiments, the radiological exam is an ongoing radiological exam at the time the query is received, and the background 82 of the radiological exam used in the generation of the draft communication request 88 is the current background of the ongoing radiological exam.

It should be noted that in most cases, the query will at least indicate the requestor's personal role in the radiological exam (because the electronic device from which the query originated is associated with the requestor), and thus the generation of the draft communication request 88 will typically include filling out at least one field of the communication request form (e.g., the identity of the requestor) based on the indicated requestor's personal role. More generally, the draft request 88 may include various metadata, such as a check name, nature of the required assistance, and so forth.

FIG. 7 presents one illustrative example, but it should be appreciated that a representation of an ongoing radiological examination workflow may similarly be used to facilitate initiating requests for assistance between other participants in the radiological examination workflow. As another example, the participant may have a problem with the nurse 26 of the patient room 22 (see fig. 1). The user clicks on the patient's name, allowing auxiliary request system 54 to pre-populate the patient as a fixed request item 80. Other request items have not been uniquely defined, and therefore, the AI model 90 fills these as proposed items 84. For example, the AI model 90 may have learned that the most likely recipient of the request to pre-populate only the patient's name at this time of day is a radiology receptionist (not shown in FIG. 1), and the second most likely nurse 26 on the patient room 22. Thus, the proposed item is "receptionist", but the user may alternatively select "nurse" from the drop-down list GUI dialog 84. When this is done, the AI model 90 is re-evaluated with the new fixed receiver items, as indicated by the reflow arrow 92 of FIG. 6, thereby adjusting the order of the proposed items in the request type.

As another example, the user notices that there is a gap in the schedule and wants to know whether the patient's appointment can be transferred. The user clicks on the corresponding time in the timeline of the UI. The communication request is pre-filled with time as a single fixed item 80. The AI algorithm 90 may have learned from the process context 82 of the earlier event that the request for time for which there is a gap in the schedule is most commonly directed to the receptionist. Thus, the receptionist will be prioritized in the proposed recipient selection.

As yet another example, a user may want to contact a particular person, such as a particular technical expert or radiologist. By clicking on a UI element representing or uniquely associated with the person, a request proposal is generated in which the recipient is pre-populated with fixed items 80. Considering the complexity of the currently running MRI exam, the AI algorithm 90 may propose that if the recipient is a radiologist, the request type is a question of the currently running complex exam, and even propose the corresponding patient and activity type to be selected in the request.

These are merely non-limiting illustrative examples.

In some embodiments, the auxiliary request may be initiated without any initial fixed request items. (i.e., the number of fixed items 80 may be zero). In this case, the user may activate the generic request function via the GUI, or the AI algorithm 90 may operate based solely on the context 82 to decide when to propose the initiation of a request based on, for example, the historically observed time stamp of the request initiation and the process context.

In the above example, the process-aware assistance request system 54 is initiated by receiving a request for assistance from a requestor. However, in other embodiments, role-specific check complexity prediction 52 may be used to initiate auxiliary requests. In such an embodiment, the suggestion and/or assistance provided to the person assigned to the person role in the workflow based on the determined role-specific check complexity metric may include predicting an assistance request by the first person assigned to the first person role in the workflow for the second person assigned to the second person role in the workflow and thereby invoking the process of FIG. 6 to automatically generate an assistance-directed draft request 88 implementing the predicted assistance request and presenting the assistance-directed draft request 88 on the electronic device of the first person. As previously described with reference to fig. 6, upon receiving approval of the auxiliary draft request 88 via the electronic device of the first person, the auxiliary draft request becomes an auxiliary approval request 94, which is then presented on the electronic device of the second person, which is accessible by the second person.

The invention has been described with reference to the preferred embodiments. Modifications and alterations will occur to others upon reading and understanding the preceding detailed description. It is intended that the exemplary embodiment be construed as including all such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (20)

1. A radiological workflow assistance apparatus comprising:

an electronic processor (56)

A non-transitory storage medium (58) storing instructions readable and executable by the electronic processor to perform a radiological workflow assistance method (52) comprising:

Retrieving information (62) related to an upcoming radiological examination of a patient, the information comprising at least information identifying an imaging modality to be used in the upcoming radiological examination, information about the patient, and information obtained from a radiological examination order for the upcoming radiological examination;

determining (64, 68) a role-specific examination complexity measure (70) of the respective person role of the workflow for performing the upcoming radiological examination based on the retrieved information, and

Providing recommendations and/or assistance to persons assigned to the person roles in the workflow based on the determined role-specific check complexity metrics.

2. The radiological communication device of claim 1, wherein determining the role-specific examination complexity metric includes:

Each role-specific check complexity metric is determined by applying a role-specific predictive model (68) to the retrieved information.

3. The radiological communication device of claim 2, wherein the role-specific predictive model is an Artificial Intelligence (AI) model.

4. The radiological communication device of any of claims 2-3, wherein determining the role-specific examination complexity metric further includes:

Deriving (64) character-related features (66) from the retrieved information for each respective person character of the workflow;

Wherein each role-specific check complexity metric (70) is determined by applying a corresponding role-specific predictive model (68) to the role-related features (66) for that person role of the workflow.

5. The radiological communication device of any of claims 1-4, wherein, for at least one human role of the workflow:

The role-specific exam complexity metric includes a multi-dimensional vector (76), wherein each dimension of the multi-dimensional vector includes a value indicative of a role-specific complexity of the upcoming radiological exam with respect to a corresponding aspect of the upcoming radiological exam.

6. The radiological communication device of any of claims 1-5 wherein providing advice and/or assistance includes presenting information indicative of the role-specific examination complexity metric (70) on an electronic device (16, 32, 38, 42, 44) accessible by a person (20, 26, 28, 34, 40) assigned to take the person role of the radiological examination workflow.

7. The radiological communication device of any of claims 1-5 wherein providing advice and/or assistance includes presenting information indicative of each role-specific exam complexity metric (70) on one or more electronic devices (16, 32, 38, 42, 44) accessible by one or more persons (20, 26, 28, 34, 40) assigned to take the person role in the workflow corresponding to the role-specific exam complexity metric.

8. The radiological communication device of claim 7, wherein presenting each role-specific exam complexity metric includes:

Displaying a radiological examination schedule (72, 74) including the upcoming radiological examination on the one or more electronic devices, the one or more electronic devices being accessible by the one or more persons assigned to take the person role in the workflow corresponding to the role-specific examination complexity metric;

wherein the upcoming radiological exam is color coded in the displayed radiological exam schedule based on the role-specific exam complexity metric determined for the upcoming radiological exam.

9. The radiological communication device of any of claims 1-8, wherein providing advice and/or assistance includes:

predicting an assistance request directed by a first person assigned to take on a first person role of the workflow to a second person assigned to take on a second person role of the workflow;

automatically generating a draft assistance request (88) implementing the predicted assistance request, and

The draft assistance request is presented on an electronic device of a first person accessible by the first person.

10. The radiological communication device of claim 9, wherein providing advice and/or assistance further includes:

receiving approval of the draft assistance request (88) via the electronic device of the first person, whereby the draft assistance request becomes an approved assistance request (94), and

The approved assistance request is presented on an electronic device of a second person accessible by the second person.

11. The radiological communication device of any of claims 1-10, wherein providing advice and/or assistance includes:

predicting assistance to a first person role of the workflow to be provided by a second person role of the workflow, and

An electronic call is automatically placed between one or more persons in the first person role of the workflow and one or more persons in the second person role of the workflow.

12. The radiological communication device of claim 11 wherein predicting assistance includes predicting a time at which the assistance to the first person role of the workflow is predicted to be provided by the second person role of the workflow, and the automatically scheduling includes scheduling the electronic call for the predicted time.

13. The radiological communication device of any of claims 11-12, wherein the first personnel role of the workflow is a local imaging technologist (20) operating a medical imaging apparatus (12) in the workflow, and the second personnel role of the workflow is another imaging technologist (40).

14. The radiological communication device of any of claims 11-12, wherein the first personnel role of the workflow is a local imaging technologist (20) operating a medical imaging apparatus (12) in the workflow, and the second personnel role of the workflow is a radiologist (34) arranged to approve images acquired by the local imaging technologist in the workflow.

15. A radiological workflow assistance apparatus comprising:

an electronic processor (56)

A non-transitory storage medium (58) storing instructions readable and executable by the electronic processor to perform a radiological workflow assistance method comprising:

Receiving a query regarding a radiological examination via an electronic device (16, 32, 38, 42, 44) of a requester operated by the requester (20, 26, 28, 34, 40);

generating a draft communication request (88) by filling out fields of a communication request form based on the query and a context (82) of the radiological examination, and

Providing a user interface on an electronic device of the requestor, the user interface displaying the draft communication request such that the requestor is able to edit the draft communication request and approve the draft communication request, whereby the draft communication request becomes an approved communication request (94), and

The approved communication request is sent to a recipient (20, 26, 28, 34, 40) identified in the approved communication request.

16. The radiological workflow assistance apparatus of claim 15, wherein generating the draft communication request includes:

Filling out a first subset of the fields of the communication request form with fixed items (80) determined based on the query and a current context (82) of the radiological examination;

a second subset of the fields of the communication request form is filled in with proposed terms (84) based on the query and a current context (82) of the radiological examination.

17. The radiological workflow assistance apparatus of claim 16 wherein filling out the second subset of the fields of the communication request form with the proposed items (84) includes applying an Artificial Intelligence (AI) model (90) to a current context (82) of the query and the radiological examination.

18. The radiological workflow assistance apparatus of any one of claims 15-17, wherein the radiological workflow assistance method further comprises:

presenting a timeline (100) of a workflow of the radiological examination on an electronic device of the requestor;

receiving a selection of a time on the timeline via an electronic device of the requestor (102);

Wherein the background (82) of the radiological exam used in generating the draft communication request (88) is a background of the radiological exam at a selected time.

19. The radiological workflow assistance apparatus of any one of claims 15-17, wherein the radiological exam is an ongoing radiological exam at a time of receiving the query, and the context (82) of the radiological exam used in generating the draft communication request (88) is a current context of the ongoing radiological exam.

20. The radiological workflow assistance apparatus of any one of claims 15-19, wherein the query indicates a person role of the requestor in the radiological examination, and generating the draft communication request includes filling in at least one field of the communication request form based on the indicated person role of the requestor.