System and method for adjusting communication output with hospital customers based on predicted bottlenecks and customer preferences during case processing

Abstract

A non-transitory computer readable medium (26) stores: a database (30) storing a plurality of maintenance solution workflows (32); and instructions that enable at least one electronic processor (20) to execute a method (100) that recommends one or more solution workflows. The method comprises: receiving a current service case (34) for the medical device (12); identifying, in the database, one or more maintenance solution workflows for resolving the current service case; populating the identified one or more maintenance solution workflows with case information of the current service case to produce corresponding one or more current service case solution workflows (36); identifying at least one possible bottleneck for the current service case based on the one or more current service case solution workflows; analyzing the influence of the identified at least one possible bottleneck; and outputting a recommendation or interpretation (38) based on the analyzed impact.

Description

Technical Field

[0001] The following generally relates to the fields of medical imaging, medical imaging equipment maintenance, medical imaging equipment diagnostic procedures, and related fields. Background Art

[0002] Medical imaging systems or other medical devices may occasionally malfunction and, as a result, not function properly. Failures are identified by the medical device operator based on observed symptoms, such as the medical device failing to operate, unsatisfactory output from the medical device (e.g., a patient monitor failing to read a vital sign sensor, a medical imaging device producing low-quality images, etc.), and / or error codes generated by the medical device, or based on other symptoms. Depending on the fault scenario, the problem can sometimes be resolved remotely by a remote service engineer (RSE). During diagnosis, the RSE may interact with a variety of tools that assist in troubleshooting the system and identify the best course of action to resolve the problem. For example, the RSE may decide to perform several actions, such as searching historical service records for similar service cases and identifying how they were resolved, searching technical documentation for possible root causes and potential solutions, examining the medical imaging system's log files to identify relevant diagnostic information (such as error messages), contacting the customer to obtain a description of the problem, and so on.

[0003] If the fault cannot be handled remotely, the remote service engineer can issue a request for a field service engineer (FSE) to repair the medical device on-site.

[0004] When maintenance issues arise that require downtime of some imaging equipment, this can be inconvenient and costly for customers, as imaging exams may be abruptly canceled or rescheduled. In these situations, customers want to minimize downtime and also want quick and accurate information about the estimated downtime and any possible actions to mitigate the impact of the downtime on radiology laboratory operations.

[0005] Some improvements are disclosed below to overcome these and other problems. Summary of the Invention

[0006] In some embodiments disclosed herein, a non-transitory computer-readable medium stores: a database storing a plurality of maintenance solution workflows; and instructions executable by at least one electronic processor to perform a method for recommending one or more solution workflows. The method includes: receiving a current service case for a medical device; identifying one or more maintenance solution workflows for resolving the current service case in the database; populating the identified one or more maintenance solution workflows with case information of the current service case to generate one or more corresponding current service case solution workflows; identifying at least one possible bottleneck for the current service case based on the one or more current service case solution workflows; analyzing the impact of the identified at least one possible bottleneck; and outputting a recommendation or explanation based on the analyzed impact.

[0007] In some embodiments disclosed herein, a non-transitory computer-readable medium stores: a database storing a plurality of maintenance solution workflows; and instructions executable by at least one electronic processor to perform a method for recommending one or more solution workflows. The method includes: receiving a current service case for a medical device; identifying, in the database, a plurality of maintenance solution workflows for resolving the current service case; populating the identified maintenance solution workflows with case information of the current service case to generate a corresponding current service case solution workflow; identifying, based on the current service case solution workflow, at least one possible bottleneck for the current service case; analyzing the impact of the identified at least one possible bottleneck; and outputting a recommendation or explanation based on the analyzed impact.

[0008] In some embodiments disclosed herein, a method for recommending one or more solution workflows includes: receiving a current service case of a medical device; identifying a maintenance solution workflow for resolving the current service case stored in a database; populating the identified maintenance solution workflow with case information of the current service case to generate a corresponding current service case solution workflow; identifying at least one possible bottleneck for the current service case based on the current service case solution workflow; analyzing the impact of the identified at least one possible bottleneck, including estimating a resolution time for the current service case based at least on the at least one possible bottleneck; and outputting a suggestion or explanation for the resolution time, including identifying the at least one possible bottleneck.

[0009] One advantage is communicating potential service activities, delays, and problems to customers who own medical devices.

[0010] Another advantage resides in managing expectations of customers who own medical devices regarding maintenance issues with the medical devices.

[0011] Another advantage is reduced downtime during maintenance procedures.

[0012] Another advantage resides in reducing delays in the delivery of parts needed to complete a medical device maintenance procedure.

[0013] Another advantage is the ability to accurately predict when medical equipment needs repair.

[0014] A given embodiment may provide none of the aforementioned advantages, provide one, two, more, or all of the aforementioned advantages, and / or may provide other advantages, as will become apparent to one of ordinary skill in the art upon reading and understanding this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The disclosure 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 disclosure.

[0016] Figure 1 The figure schematically illustrates a medical equipment service workflow recommendation apparatus according to the present disclosure.

[0017] Figure 2 Schematically shows the use of Figure 1 Embodiments of a medical device service workflow recommender method for an apparatus.

[0018] Figure 3 Schematically shows the use of Figure 1 Embodiments of a medical device service workflow recommender method for an apparatus.

[0019] Figure 4 An exemplary output of a workflow recommender device is illustrated. DETAILED DESCRIPTION

[0020] The following relates to a system for improving the planning of maintenance solutions and their communication with customers. The disclosed system includes a database of solution workflows for various types of maintenance problems. A given solution workflow may include various tasks with various interdependencies. For example, a workflow may include ordering / delivering a replacement part and installing the replacement part in an imaging system. The installation is dependent on the ordering / delivery because the installation can only occur after the part has been delivered. Certain portions of the solution workflow may also be probabilistic. For example, if a workflow includes dispatching a field service engineer (FSE), the portion of the workflow performed by the FSE may depend on the FSE's inspection of the imaging device. In some embodiments, these probabilistic aspects can be represented as a decision tree, with probabilities labeled as tree branches, for example based on statistics extracted from historical data. The completion times for various tasks in the workflow may also be situational and can be estimated in real time based on information such as the number of remote service engineers (RSEs) or FSEs currently on duty (or when a task is expected to occur in the future). For example, the completion times that depend on the RSE or FSE can be estimated in real time based on duty personnel data and historical information on the number of tasks that a given RSE or FSE can handle per hour. Similarly, parts delivery may be situation-specific, and the delivery completion time for a given part may be based on actual delivery time estimates provided by the delivering company, or based on historical data for delivery times for that type of part given the time of day, day of the week, month, year, or the like. (For example, historical data may indicate that a certain part is typically delivered within 8 hours, but if the part is ordered on a major holiday, the delivery time may be 16 hours).

[0021] Based on a workflow (retrieved from a database for current maintenance problem cases) populated with situation-specific information such as task completion times and probabilities (for uncertain branching events of the workflow) and task interdependencies specified in the workflow, specific bottlenecks can often be identified that cause significant expected delays in resolving the current case. A given bottleneck may also have an associated probability of occurrence. For example, an FSE check may be required to determine whether the current maintenance problem can be resolved by a quick action (such as a software update or calibration of an installed component) or whether the current problem can only be resolved by replacing the part (thus creating a bottleneck in ordering / delivering the part). A probability is assigned to the bottleneck based on the probability that the check indicates that the current case requires a replacement part (e.g., marked as a corresponding branch of the solution workflow tree, derived from historical data).

[0022] Although described below for one resolution workflow, there may be two, three, or more (candidate) resolution workflows to resolve the current case. For example, one candidate workflow might dispatch an FSE as quickly as possible to resolve the current case, another candidate workflow might use an in-house biotech to attempt to resolve the current case, another candidate workflow might utilize a contracted third-party service provider to resolve the current case, and yet another candidate workflow might dispatch an FSE after a predetermined delay while continuing to use the imaging equipment on a limited basis to perform specific types of imaging exams that can be performed despite the maintenance issue.

[0023] The next step is an impact analysis, which analyzes the impact on the customer of each such candidate solution workflow in resolving the current case, including any identified bottlenecks. This may require comparing the imaging exam schedule for the imaging device with the delays introduced by each candidate workflow to determine the candidate workflow's impact on the customer, taking into account the situation-specific completion times for the various workflows' tasks. For candidate workflows that would continue to use the imaging device on a reduced basis, the impact analysis might consider what portion of the upcoming imaging exam could actually be performed on a reduced basis. For each candidate solution workflow, these analyses output a timeline of the solution workflow, annotated with times when the imaging device was unavailable or available on a reduced basis, as well as an estimated time until the current case is fully resolved. The timeline may also indicate the actors who perform each task.

[0024] By analyzing the impact of these candidate solutions on the workflow, recommendations or explanations are provided during the communication phase. The recommendations or explanations output depend on the bottlenecks identified. For bottlenecks with high probabilities (or confidence values), and if alternative actions can have a significant impact on the impact, the exposed system will decide to focus on recommending alternative actions.

[0025] The communication phase is typically customer-facing. However, in some embodiments, there may also be a service provider-facing communication aspect. Typically, the RSE or other service provider employee assigned to the case should be aware of the recommendations or explanations provided to the customer and, if a recommendation was provided, should also communicate the customer's decision to the RSE. (For example, the system might recommend delaying the FSE dispatch while the imaging device continues to be used at reduced capacity, but the customer could still select a different candidate resolution workflow to dispatch the FSE as soon as possible.)

[0026] refer to Figure 1, an exemplary apparatus 10 for servicing a medical device 12 is shown. The medical device 12 may include, for example, a medical imaging device 12 (also referred to as a medical device, an imaging device, an imaging scanner, and variations thereof), which may be a magnetic resonance imaging (MRI) scanner, a computed tomography (CT) scanner, a positron emission tomography (PET) scanner, a gamma camera for performing single photon emission computed tomography (SPECT), an interventional radiology (IR) device, an X-ray device, an image-guided therapy (IGT) device, an ultrasound (US) device, and the like. Although the medical device 12 is described herein as an imaging device, it may be any other suitable medical device, such as a patient monitor, a radiation therapy device, a mechanical ventilator, and the like.

[0027] An electronic processing device 18, such as a workstation computer, or more generally a computer, smart device (e.g., a cellular phone ("mobile phone"), smart tablet, etc.), can be operated by a service engineer (SE). The electronic processing device 18 may also include a server computer or multiple server computers, for example, interconnected to form a server cluster, cloud computing resources, etc., to perform more complex computing tasks. The electronic processing device 18 includes typical components such as an electronic processor 20 (e.g., a microprocessor), at least one user input device (e.g., a mouse, keyboard, trackball, etc.) 22, and a display device 24 (e.g., an LCD display, a plasma display, a cathode ray tube display, etc.). In some embodiments, the display device 24 may be a separate component from the electronic processing device 18, or may include two or more display devices.

[0028] The electronic processor 20 is operably connected to one or more non-transitory storage media 26. The non-transitory storage media 26 may include, by way of non-limiting illustrative examples, one or more of the following: a magnetic disk, RAID, or other magnetic storage media; a solid-state drive, a flash drive, an electrically erasable read-only memory (EEROM), or other electronic memory; an optical disk or other optical storage media; various combinations thereof; and the like; and may be, for example, a network storage, an internal hard drive of the workstation 18, various combinations thereof, and the like. It should be understood that any reference herein to one or more non-transitory media 26 should be broadly interpreted to encompass a single medium or multiple media of the same or different types. Similarly, the electronic processor 20 may be implemented as a single electronic processor or as two or more electronic processors. The non-transitory storage media 26 stores instructions that are executable by at least one electronic processor 20. The instructions include instructions for generating visualizations of a graphical user interface (GUI) 28 for display on the display device 24.

[0029] The electronic processing device 18 also communicates with a database 30 (in Figure 1The database 30 communicates with a server computer (shown as a server computer in FIG), storing a plurality of maintenance solution workflows 32. For example, in the case of a database 30 of medical imaging system service cases, the plurality of maintenance solution workflows 32 may include maintenance solution workflows including diagnostic sequences, repair operations, logistics data, maintenance reports, and the like. It should be appreciated that the number of maintenance solution workflows 32 in the database 30 may be substantial, such as tens of thousands of cases, hundreds of thousands of cases, or more, and that, in many cases, a search may return tens of thousands of maintenance solution workflows 32 (or more).

[0030] The apparatus 10 is configured as described above to perform a method or process 100 for recommending one or more solution workflows 32. The non-transitory storage medium 26 stores instructions that can be read and executed by at least one electronic processor 20 to perform the disclosed operations, including executing the service method or process 100. In some examples, the method 100 can be performed at least in part through cloud processing.

[0031] refer to Figure 2 , and continue to refer to Figure 1 , an illustrative embodiment of an example of method 100 is schematically shown in the form of a flowchart.

[0032] In operation 102, a current service case for a medical device 12 is received at the electronic processing device 18. In some examples, the received current service case 34 includes an error code generated by the medical device 12, a user-provided problem description, historical search results, or a summary from a service provider (SE). Operation 102 may include, for example, an RSE or other customer call receiving personnel answering the call from the customer and entering such information into a form field; or the customer may directly fill out a form via a customer-facing web-based service request form filled out using a web browser. These are all examples. A case ticket or the like may be created to track the currently open current service case.

[0033] In operation 104, one or more maintenance solution workflows 32 for resolving the current service case 34 are identified. The identifying operation 104 may include extracting features from the received current service case 34 and matching the extracted features with features of the maintenance solution workflows 32 stored in the database 30. In some examples, only one maintenance solution workflow 32 may be identified, while in other examples, multiple maintenance solution workflows 32 may be identified.

[0034] In operation 106, the identified one or more maintenance solution workflows 32 are populated with the case information of the current service case 34 to generate corresponding one or more current service case solution workflows 36. (If there are two or more populated current service case solution workflows 36, they can be considered candidate workflows.) This operation 106 can include identifying future bottleneck(s) in the workflow.

[0035] At operation 108 , at least one potential bottleneck for the current service case 34 is identified based on one or more current service case solution workflows 36 . As used herein, the term "bottleneck" (and its variations) refers to a timeframe issue, i.e., a point in the workflow that causes a delay in resolving the service case 34 . Typically, though not necessarily, bottlenecks are at least partially caused by dependencies, where a subsequent step depends on a previous step and can only be executed after the previous step has completed. For example, a part installation step can only be executed after the previous parts ordering and parts delivery steps have completed. While parts ordering is typically fast, the bottleneck may be the parts delivery step. A bottleneck may also be probabilistic, i.e., have an assigned probability. For example, if a faulty system requires an on-site inspection by an on-site FSE, a bottleneck may arise based on the inspection results. For example, if the inspection reveals a software issue, remediation may be fast, whereas if the inspection reveals a hardware issue, remediation may be slow due to the need for parts ordering / delivery / installation. Here, the bottleneck is again delivery time, but now with a probability of occurrence determined based on statistical results for similar historical FSE inspection cases. Each maintenance solution workflow 32 includes tasks and interdependencies based on the bottleneck, and may also include a probability of the bottleneck occurring.

[0036] In operation 110, the impact of the at least one identified possible bottleneck is analyzed. In operation 112, a recommendation or explanation 38 is output based on the analyzed impact. These operations can be performed in a variety of ways. In some examples, when the identification operation 104 identifies a plurality of maintenance solution workflows 32 (which are populated to generate a corresponding plurality of current service case solution workflows 36), the analysis operation 110 includes generating an alternative solution workflow timeline from the plurality of current service case solution workflows 36. The alternative candidate solution workflow timeline includes the at least one identified possible bottleneck. The output operation 112 then includes presenting the alternative candidate solution workflow timeline on the display device 24.

[0037] In other examples, when the identifying operation 104 identifies a single maintenance solution workflow 32 (which populates to generate a single current service case solution workflow 36), the analyzing operation 110 includes estimating a resolution time for the current service case 34 based at least on the at least one possible bottleneck. The outputting operation 112 then includes presenting an explanation 38 of the resolution time, including the identification of the at least one possible bottleneck.

[0038] In some embodiments, the analysis operation 110 includes analyzing the impact of at least one possible bottleneck on an examination plan performed using at least the medical device 12. To this end, while the current service case 34 issue remains unresolved, a reduced functionality of the medical device 12 is determined, and a modified examination plan that can be performed by the medical device 12 with the determined reduced functionality is determined. In this example, the analysis operation 110 includes generating a timeline (including suggestions or explanations 38) of the current service case solution workflow 36, annotated with failure times when the medical device 12 is unavailable or available under the determined reduced functionality. In some examples, the timeline also includes an estimated time for the current case to be fully resolved. In other examples, the timeline also includes annotations indicating the medical professional who performed each task of the solution workflow.

[0039] In some embodiments, the analyzing operation includes (i) estimating a task completion time for resolving a potential bottleneck, (ii) calculating a probability of resolving a potential bottleneck, or both. Operations 102 - 110 may be repeated for multiple interrelated current service cases 34 .

[0040] Example

[0041] The apparatus 10 and method 100 are described in more detail below. The method 100 generally relates to a method for communicating the most relevant information to a hospital client during case processing (or monitoring). The relevant information that needs to be communicated should focus on alternative actions or explanations (when there are no better alternative actions). The method 100 proactively predicts and detects potential bottlenecks and determines the most appropriate communication message based on the confidence level of the prediction and the client's preferences. The method 100 is intended to be used for each state change during case processing, as well as for situations where unexpected waits are known.

[0042] refer to Figure 3 , which diagrammatically illustrates a more detailed embodiment of the medical equipment repair workflow recommender used in this example, and which can be used, for example, Figure 1The electronic processing device 18 may include one or more modules implemented in at least one electronic processor 20 to execute method 100. The bottleneck module 120 is programmed to predict or detect bottlenecks or steps that may impact customers, identify the causes, and prioritize them based on their impact. Examples of these factors include logistics chain shortages, unavailability of RSE, etc. The bottleneck module 120 contains information about the entire maintenance process. To model the process, various algorithms can be used, ranging from process mining (i.e., comparing event logs with constructed process models and analyzing differences) to Business Process Management Notation (BPMN) and Petri Nets (PN). To quantify the probability of a specific bottleneck step, Petri Net (PN) modeling and risk assessment or similar techniques can be used to generate a risk score. This module is continuously updated as the case progresses (e.g., utilizing data from a service record management system). For example, when an RSE inserts a service record indicating that they have completed a diagnosis, the device automatically updates the service case status to "Remote Diagnosis Completed."

[0043] The impact analysis module 122 is used to quantify the impact of each bottleneck step and retrieve alternative actions and their impact when used (e.g., "How long does it take to deliver the part using an alternative company instead of the regular supplier?" "How many patients will be affected during the (extended) downtime?", etc.). The module quantifies the impact of each bottleneck step. In the following example, duration is used as an example of impact (i.e., a 24-hour delivery delay has a greater impact than obtaining an available FSE. The impact analysis module 122 may consider interdependencies between causes. For example, the unavailability of an RSE may only cause a 1-hour delay, but without the RSE, the potential part may not be identified. In this case, the availability of the RSE has a higher priority than a logistics chain shortage that cannot identify the potential part. The duration estimate takes into account the hospital's address). Table 1 lists an example of the output of the impact analysis module 122.

[0044]

[0045] Table 1. Examples of outputs for predicting or detecting bottlenecks. The last row shows an example of predictive maintenance (rather than reactive maintenance).

[0046] For high priority reasons, the module searches external data sources such as third-party suppliers to see if an alternative option can be found and estimates the duration. It also determines whether the alternative solution meets all of the customer's criteria, including regulatory requirements. If the alternative solution takes less time than waiting for the bottleneck to be resolved, it is considered a valid alternative. For example, an RSE requests a replacement table for an MR device. Currently, such a shipment might take 24 hours instead of 4 hours (the average duration). The unit can find a "new" company that has received approval from the U.S. Food and Drug Administration (FDA) to produce the MR device table, and the shipment would take 4 hours. This alternative option becomes valid.

[0047] The partial functionality module 124 is configured to determine the functionality of the medical device 12 that is affected and match it with the scheduled appointments for the expected downtime period. The result is the number of appointments that can be kept or should be postponed within the time frame. Alternatively, the result can be a list of examinations that can still be performed using the partially functional system. Once the diagnosis is complete and the impact of the problem is known (for example by specifying the fault area of ​​the medical device 12), the partial functionality of the device 12 can be determined. When there is a known fault area for the device 12, this module generates a list of possible operations / examinations for that device. It then matches these with the scheduled examinations and determines a list of appointments that are not affected and a list of appointments that need to be moved to after the expected fault time. When the fault is unknown, the operating user (for example, a biomedical engineer at the hospital) can provide input on the types of operations that can still be performed. Various checks and balances can be performed to ensure patient safety. For example, Figure 3 The recommendation for continued use generated by the partially functional module 124 in the output to the customer can be sent to the radiology department manager or other appropriately qualified personnel for review and approval before the listed examinations can be performed using the partially functional system. Figure 3 The output of block 126 is sent to a Figure 1ed electronic processing device 18 to perform such a review. If the reviewer approves the recommendation to continue operating with partial functionality, additional measures can be selectively taken based on the functional limitations of the imaging equipment, such as having the on-call radiologist review and approve images acquired for these examinations prior to discharge of the patient, and / or assigning a more experienced imaging technician to perform these examinations using a reduced-functionality imaging device. On the other hand, if the reviewer rejects the recommendation to perform the listed examinations using a reduced-functionality imaging device, that decision can be fed back to the impact analysis 122, which then updates the alternative actions accordingly. For example, if an initial run of the impact analysis 122 outputs a list of examinations recommended for performance using a partially functional system, but that recommendation is rejected by the human reviewer, a subsequent run of the impact analysis 122 will exclude this option and thereby output one or more additional alternative actions, such as a recommendation to quickly call an RSE.

[0048] In a variant approach, the output to the client may be a list of recommended examinations to be performed using a partially functional system, and the user (e.g., a radiology department manager) may personally accept or deny proceeding with each imaging examination on the list. Thus, only a subset of the listed imaging examinations may be permitted to be performed using the reduced-functionality imaging device. This updated information may be fed back to the impact analysis 122, which may update its recommended alternative action(s) based on this additional information. In some examples, selected portions of the output recommendations or explanations 40 may be automatically implemented in the medical device 12 in response to the received input.

[0049] The communication focus module 126 is configured to determine the focus of the communication output based on the predicted / detected bottleneck(s), i.e., whether to focus on alternative actions or on explanations of management expectations. If a bottleneck is predicted with a high probability (or confidence) and alternative actions are possible, the communication output will focus on such actions. If a bottleneck is predicted with a low probability (or confidence) and / or alternative actions are not possible, the communication output will focus on providing explanations that provide transparency to the user about what is happening in the process. The explanation topic can be selected based on customer preferences.

[0050] This module combines the probability of each predicted bottleneck, the available alternative actions, and the impact of each action. For bottlenecks with high probability (or confidence), and if the alternative actions can have a significant impact on the impact, the unit will decide to focus on recommending alternative actions.

[0051] refer to Figure 4 , shows a non-limiting illustrative example of a suitable output of the communication focus module 126 for a situation where multiple (illustratively three) different candidate solution workflows have been identified. The output of the communication focus module 126 may be in Figure 1The GUI 28 of the electronic processing device 18 is presented. Figure 4 As shown in FIG, the first candidate solution workflow is illustrated in the first row of the GUI 28 and is labeled "has bottlenecks". The highlighted background or other graphical representation can indicate the expected downtime and the identified bottlenecks. For example, the bottleneck is highlighted with a red icon. Figure 4 ), there is a problem with the first workflow. Figure 4 28 ) describe two additional candidate solution workflows, labeled "Suggestion 1" and "Suggestion 2," one of which is to obtain third-party access and the other of which is to reschedule some appointments. Both are considered to represent a significant change in impact compared to the "with bottleneck" candidate solution flow and are therefore recommended. The customer can choose which option to adopt (i.e., to choose between the "with bottleneck," "Suggestion 1," or "Suggestion 2" candidate workflows), or can request more information. In addition, the user can provide one or more inputs via the user input device 22 to select an icon, solution workflow, or any other item displayed on the GUI 28 to view additional information about the selected item. If the recommendation includes a list of examinations recommended to be performed using a limited-capacity imaging device, the user interface can list these examinations and allow the user to approve or reject the entire list, and / or individually approve or reject each imaging examination on the list.

[0052] If the probability (or confidence) of the bottleneck is low, or no better alternative action can be identified, the unit will decide to focus on explaining to the hospital customer. An example of a communication output could be "Based on the estimated timeline for the first available RSE, there is a low probability of finding an RSE in time to diagnose the problem." The explanation is also adapted to the customer's preferences. It can include multiple aspects such as contact person, source of estimate, findings of alternative actions, etc. The decision on which aspects to focus on can be based on customer input (see optional unit Customer Input) or analysis of NPS or customer complaint records. Based on NLP analysis, one can cluster factors that determine customer satisfaction or dissatisfaction with communication. For example, Hospital ABC has complained in the past about the vendor not telling which data source the estimate was based on. Therefore, based on this analysis, the navigation to the explanation should reveal the source of the data used in the estimate.

[0053] In some examples, the customer input module can allow users to specify which aspects and at what level of granularity they want explanations for, and to respond if they have further questions about the explanations and recommendations. Some customers want to know why a particular change occurred; others may want to know how the decision was made (an intermediate step in applying artificial intelligence). Table 2 shows examples of various communication outputs based on predicted bottlenecks and the availability of alternative actions.

[0054]

[0055] Table 2 shows an example of determining communication outputs based on predicted bottlenecks and the availability of alternative actions.

[0056] The disclosed system 10 and method 100 can be implemented for a group of medical devices 12. For example, the system 10 can analyze the current service cases 34 for a plurality of devices 12 in the group of devices and analyze the nature of scheduled examinations to help determine which examinations can be performed, thereby providing a number of different alternatives to address identified bottlenecks.

[0057] The present disclosure has been described with reference to preferred embodiments. Those skilled in the art, by reading and understanding the foregoing detailed description, may make various modifications and variations. It is intended that the present disclosure be constructed to include all such modifications and variations, as long as they fall within the scope of the appended claims or their equivalents.

Claims

1. A non-transitory computer-readable medium (26) storing: a database (30) storing a plurality of maintenance solution workflows (32); and Instructions executable by at least one electronic processor (20) to perform a method (100) of recommending one or more solution workflows, the method comprising: receiving a current service case (34) for a medical device (12); identifying in the database one or more maintenance solution workflows for resolving the current service case; populating the identified one or more maintenance solution workflows with the case information of the current service case to generate corresponding one or more current service case solution workflows (36); identifying at least one possible bottleneck for the current service case based on the one or more current service case solution workflows; analyzing the impact of the identified at least one possible bottleneck; as well as Recommendations or explanations are output based on the analyzed impacts (38).

2. The non-transitory computer readable medium (26) of claim 1, wherein: When a plurality of maintenance solution workflows (32) are identified and populated to generate a corresponding plurality of current service case solution workflows (36): The analyzing includes generating an alternative candidate solution workflow timeline based on the plurality of current service case solution workflows, wherein the alternative candidate solution workflow timeline includes the identified at least one possible bottleneck; and The outputting includes presenting the alternative candidate solution workflow timeline on a display device (24).

3. The non-transitory computer readable medium (26) of claim 1, wherein: When a single maintenance solution workflow (32) is identified: The analyzing includes estimating a resolution time for the current service case (34) based at least on the at least one possible bottleneck; and The outputting includes presenting an explanation (38) of the resolution time, the explanation including identifying the at least one possible bottleneck.

4. The non-transitory computer readable medium (26) according to any one of claims 1 to 3, wherein: The impact of analyzing at least one possible bottleneck identified includes: The impact of the at least one possible bottleneck on an examination schedule to be performed using at least the medical device (12) is analyzed.

5. The non-transitory computer readable medium (26) of claim 4, wherein: The impact of analyzing the inspection schedule includes: determining a reduced functionality of the medical device (12) while the current service case (34) remains unresolved; and A modified examination plan is determined that can be performed by the medical device having the determined reduced functionality.

6. The non-transitory computer readable medium (26) of claim 5, wherein: The impact of at least one possible timeframe issue identified by the analysis includes: A timeline (38) of the current service case solution workflow (36) is generated, the timeline being annotated with failure times when the medical device (12) was unavailable or available but with determined reduced functionality, and the timeline is output on a display device (24).

7. The non-transitory computer readable medium (26) of claim 6, wherein: The timeline (38) also includes an estimated time by which the current case will be fully resolved.

8. The non-transitory computer readable medium (26) according to any one of claims 6 and 7, wherein: The timeline (38) also includes annotations indicating the medical professional who performed each task of the current service case resolution workflow (36).

9. The non-transitory computer readable medium (26) according to any one of claims 1-8, wherein: The analysis includes: Estimate the task completion time for resolving the possible bottleneck.

10. The non-transitory computer readable medium (26) of any one of claims 1-9, wherein: The analysis includes: The probability of resolving the possible bottleneck is calculated.

11. The non-transitory computer readable medium (26) of any one of claims 1-10, wherein: The method (100) further comprises: An input is received indicating approval of the outputted recommendation or interpretation (38).

12. The non-transitory computer readable medium (26) of any one of claims 1-10, wherein: The method (100) further comprises: receiving input indicating a selection of a portion of the outputted recommendation or explanation (38); and At least one of the following: (i) displaying additional information related to a selected portion of the output recommendation or explanation; and (ii) automatically implementing selected portions of the outputted recommendation or explanation in response to the received input.

13. The non-transitory computer readable medium (26) of any one of claims 1-12, wherein: The method (100) further comprises: The receiving, the identifying, the recognizing, the populating, the analyzing, and the outputting are repeated for a plurality of current service cases (34).

14. The non-transitory computer readable medium (26) of any one of claims 1-13, wherein: Each maintenance solution workflow (32) includes tasks and interdependencies based on the at least one bottleneck.

15. The non-transitory computer readable medium (26) of any one of claims 1-14, wherein: The device (12) comprises a group of devices, and the method (100) further comprises: The receiving, identifying, recognizing, populating, analyzing, and outputting are repeated for a plurality of current service cases (34) of the devices in the group of devices.

16. A non-transitory computer-readable medium (26) storing: a database (30) storing a plurality of maintenance solution workflows (32); and Instructions executable by at least one electronic processor (20) to perform a method (100) of recommending one or more solution workflows, the method comprising: receiving a current service case (34) for a medical device (12); identifying in a database a plurality of maintenance solution workflows for resolving the current service case; populating the identified maintenance solution workflow with case information for the current service case to generate a corresponding current service case solution workflow (36); identifying at least one possible bottleneck for the current service case based on the current service case solution workflow; analyzing the impact of the identified at least one possible bottleneck; as well as Recommendations or explanations are output based on the analyzed impacts (38).

17. The non-transitory computer readable medium (26) of claim 16, wherein: The analyzing includes generating an alternative candidate solution workflow timeline based on the plurality of current service case solution workflows, wherein the alternative candidate solution workflow timeline includes the identified at least one possible bottleneck; and The outputting includes presenting the alternative candidate solution workflow timeline on a display device (24).

18. The non-transitory computer readable medium (26) of claim 16, wherein analyzing the impact on the inspection schedule comprises: determining a reduced functionality of the medical device (12) while the current service case (34) remains unresolved; and A modified examination plan is determined that can be performed by the medical device having the determined reduced functionality.

19. The non-transitory computer readable medium (26) of claim 18, wherein: The impact of at least one possible timeframe issue identified by the analysis includes: A timeline (38) of the current service case solution workflow (36) is generated, the timeline being annotated with failure times when the medical device (12) is unavailable or available but with determined reduced functionality.

20. A method (100) for recommending one or more solution workflows, the method comprising: receiving a current service case (34) for a medical device (12); identifying a maintenance solution workflow (32) stored in a database (30) for resolving the current service case; populating the identified maintenance solution workflow with the case information of the current service case to generate a corresponding current service case solution workflow (36); identifying at least one possible bottleneck for the current service case based on the current service case solution workflow; analyzing the impact of the identified at least one possible bottleneck, including estimating a resolution time for the current service case (34) based at least on the at least one possible bottleneck; and A recommendation or explanation for the resolution time is output (38), including identification of at least one possible bottleneck.

Images