Forecasting future laboratory performance

Abstract

To provide a computer-implemented method for forecasting future laboratory performance of a laboratory system and the laboratory system.SOLUTION: A laboratory system comprises laboratory devices, a laboratory middleware, a control unit, and a dashboard display, which are communicatively connected via a network communication connection. A method includes: providing laboratory operator preferences, laboratory constraints, laboratory input data, and order data to an optimization module; optimizing laboratory configuration in the optimization module; simulating future laboratory performance of the laboratory system by a simulation module of the control unit on the basis of the optimized laboratory configuration provided by the optimization module and real-time laboratory inputs and order data; and displaying the simulated future laboratory performance and actual laboratory performance on the dashboard display to the laboratory operator.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Field of the Invention The present disclosure generally relates to methods for predicting or anticipating the performance of a laboratory system in order to optimize the performance of the laboratory system.

Background Art

[0002] Background of the Invention Typical laboratory performance dashboards only show the current and past performance of the laboratory and the potential gaps with the required performance. Further, typical dashboards do not show future performance or realistically optimal performance, nor do they predict future laboratory events.

[0003] Furthermore, current laboratory performance dashboards cannot provide laboratory operators with an accurate prediction of when laboratory test results will be available to them. Generally, only a rough estimate of the availability of laboratory test results is currently provided. These rough estimates typically rely on simple algorithms that use analyzer data provided to laboratory middleware.

[0004] Furthermore, currently, there is no means for quickly and accurately determining the results regarding laboratory performance due to daily variations in laboratory workload or when laboratory operators change workflow variables, maintenance schedules, and / or laboratory configurations. Instead, when the laboratory does not function as expected due to the results of changes from the starting design, laboratory operators typically complain about longer workdays and / or delayed delivery of test results to laboratory customers. Therefore, time, cost, and resources can be saved for the laboratory if the dashboard can quickly and accurately demonstrate to laboratory operators the effect of such changes on laboratory performance before the changes are made.

[0005] European Patent No. 2602625 discloses a method for monitoring a diagnostic test process by simulating the process, receiving data representing the actual progress of the diagnostic test process, and displaying the simulated actual diagnostic test process.

[0006] U.S. Patent No. 7,960,178 discloses a method for processing samples that provide an operator with an alternative scheduling process to accomplish a particular task.

[0007] U.S. Patent No. 9,194,876 discloses a method for creating and displaying estimates of when sample results may become available, based on various laboratory data sources.

[0008] U.S. Patent No. 9,466,040 discloses a method for predicting congestion in automated analysis systems and adjusting sample timing and retrieval to avoid congestion. [Overview of the Initiative]

[0009] Summary of the Invention The purpose of this disclosure is to predict or forecast the performance of a laboratory system in order to optimize its performance.

[0010] One aspect of this disclosure discloses a computer implementation method for predicting the future laboratory performance of a laboratory system. The laboratory system may comprise a plurality of laboratory instruments configured to perform tests on laboratory test samples, pre-analysis instruments, post-analysis instruments, laboratory middleware, a control unit, a laboratory test sample transport system, and a dashboard display that is communicably connected via a network communication connection. The method may include providing the laboratory operator's preferences and laboratory constraints from the laboratory operator to an optimization module of the control unit; providing laboratory input data and order data to the optimization module of the control unit; optimizing the laboratory configuration in the optimization module of the control unit based on the laboratory operator's preferences, laboratory constraints, laboratory input and order data; simulating the future laboratory performance of the laboratory system by a simulation module of the control unit based on the optimized laboratory configuration and real-time laboratory input and order data provided by the optimization module; and displaying the simulated future laboratory performance and actual laboratory performance to the laboratory operator on a dashboard display.

[0011] Laboratory input data and order data can be provided continuously in real time by laboratory middleware. Sample collection data and laboratory test sample transfer data can also be provided continuously in real time by laboratory middleware.

[0012] Real-time laboratory data includes, for example, the status of laboratory equipment, the status of transport systems, the availability of laboratory operators, the availability of reagents, the availability of consumables, the status of laboratory test samples, the timing of masking of laboratory equipment, i.e., the capacity of laboratory equipment to accept laboratory test samples, the allocation and placement of reagent packs, sample loading scheduling, workflow rules, and / or combinations thereof, as well as the status of resources within the laboratory.

[0013] The state of a laboratory test sample may include, for example, the location of the laboratory test sample at any given point in time, i.e., which laboratory equipment is the laboratory test sample, or at what location within the laboratory, how much processing has been performed and how much remains, i.e., which test operations have been performed and which still need to be performed, how much of the test sample remains, and / or a combination thereof.

[0014] Workflow rules may include rules that define, for example, which laboratory equipment should be used to test laboratory test samples, in what order aliquots should be prepared, and / or combinations thereof.

[0015] The simulated future laboratory performance may include predicting the arrival of test results from multiple laboratory instruments.

[0016] The displayed simulated future performance may include simulated throughput, sample turnaround time (TAT), time to results, buffer levels, sample traffic intensity, laboratory operator instrument load and workload, idle time, number of samples, reagents, or tests exceeding performance tolerances, point-to-point travel time, buffer wait time, walkaway time, number of laboratory operator interactions per hour, number of laboratory operators required, power consumption, water consumption, operating costs, or a combination thereof.

[0017] The displayed simulated future performance may include indicators of the advantages of the simulated laboratory configuration compared to the current laboratory configuration.

[0018] The computer implementation method may further include modifying the current laboratory configuration of the laboratory via input from the laboratory operator, based on simulated future laboratory performance.

[0019] The computer implementation method may further include triggering a warning if simulated future laboratory performance and actual laboratory performance deviate from acceptable levels, and / or if the arrival of simulated test samples and actual test samples deviates from acceptable levels, and / or if an anomaly is detected.

[0020] The computer implementation method may further include indicating the potential cause of the deviation or anomaly on the dashboard display.

[0021] The computer implementation method may further include calculating estimated future performance based on an optimized laboratory configuration.

[0022] The computer implementation method may further include calculating the sample loading effect on simulated future laboratory performance.

[0023] The computer implementation method may further include scheduling manual interactions with the laboratory system based on an optimized laboratory configuration.

[0024] In some embodiments, laboratory processes may be unknown to the simulation model. In these embodiments, "unknown" may mean, for example, that there is no currently available model to represent the behavior of the laboratory equipment or manual process, or that the model is not sufficiently good. Unknown elements and inadequate models may result in unknown or poorly predicted times in the simulation model. However, as data from the corresponding laboratory processes is received by the laboratory system, it can be used to improve the simulation model and increase the accuracy of future simulations. As more data is received, the model may become better at predicting future events.

[0025] The computer implementation method may further include displaying predicted future events on a dashboard, indicating when predicted future events are expected to occur. Predicted future events may include, for example, changes in the status of laboratory test samples, laboratory data, or laboratory equipment; publication of test results; a change in status from processing to ready for one or more samples; samples being ready to be taken from laboratory equipment; racks or trays of test samples ready for the laboratory operator to take; changes in the load on laboratory equipment or changes in the number of test samples in the test sample queue of laboratory equipment; time to perform quality control (QC); or time to replenish reagents or consumables in laboratory equipment.

[0026] Additional anticipated future events may include estimates of when refilling will be needed, and / or estimates of the start time of a laboratory maintenance event, and / or estimates of the duration of a laboratory maintenance event, predictions of when future laboratory maintenance events will occur, when a complete batch of laboratory test samples has been analyzed, when laboratory test samples are ready to be removed from laboratory equipment or systems, and when all or specific test results for a particular laboratory test sample are released (e.g., urgent / critical) so that verification needs to be performed or test results can be communicated to healthcare professionals, etc. Forecasts can also help define when urgent laboratory tests will be completed so that laboratory personnel can plan activities that may cause longer turnaround times, such as taking coffee breaks, performing QC tests, or performing activities that may delay the manual loading of samples, reagents, or consumables.

[0027] According to a second aspect of the present disclosure, a computer-implemented method for predicting the future laboratory performance of a laboratory system is disclosed. The laboratory system can include a plurality of laboratory devices configured to perform tests on laboratory test samples, a laboratory middleware, a control unit, and a dashboard display, which are communicably connected via a network communication connection. The method includes providing various configurations of the laboratory system from a laboratory operator to a simulation module of the control unit, continuously providing real-time laboratory input data from the plurality of laboratory devices to the laboratory middleware, continuously providing the real-time laboratory input data and order data from the laboratory middleware to the simulation module, simulating the future laboratory performance of various configurations of the laboratory system by the simulation module of the control unit based on the real-time laboratory input and order data, and displaying the simulated future laboratory performance and the actual laboratory performance of various configurations of the laboratory system on a dashboard display of the laboratory operator.

[0028] The computer-implemented method can further include selecting, by a laboratory operator, one of various configurations of the laboratory system based on the simulated future laboratory performance of the various configurations, and reconfiguring the laboratory system based on the selected configuration.

[0029] The reconfiguration of the laboratory system can be performed manually and / or automatically.

[0030] The computer-implemented method can further include optimizing, in an optimization module, the future laboratory performance of various configurations based on the preferences of the laboratory operator, laboratory constraints, real-time laboratory input, and order data.

[0031] A third aspect of this disclosure discloses a laboratory system for predicting future laboratory performance. The laboratory system may comprise a plurality of laboratory instruments configured to perform tests on laboratory test samples, laboratory middleware communicatively connected to the plurality of laboratory instruments, a dashboard display configured to display performance information of the laboratory system, and a control unit connected to the plurality of laboratory instruments and laboratory middleware via a network communication connection, including an optimization module and a simulation module. The control unit may be configured to provide laboratory operator preferences and laboratory constraints from the laboratory operator to the optimization module and to continuously provide real-time laboratory input data from the plurality of laboratory instruments to the laboratory middleware. The control unit may also continuously provide real-time laboratory input data and order data from the laboratory middleware to the optimization module, and the optimization module may be configured to optimize the laboratory configuration based on the laboratory operator preferences, laboratory constraints, and real-time laboratory input and order data. The control unit can also be configured to use a simulation module to simulate the future laboratory performance of the laboratory system based on the optimized laboratory configuration provided by the optimization module, as well as real-time laboratory input and order data, and to display the simulated future laboratory performance and actual laboratory performance to the laboratory operator on a dashboard display.

[0032] Several advantages emerge from using simulations to predict or forecast future laboratory performance. Firstly, the timing of deviations can be identified more accurately. For example, laboratory operators typically only learn of deviations between the time to real-time results and the time to desired results after, for instance, the sample test results have been published. This is often too late to correct the deviation in that particular sample, thus delaying other samples in the process as well. However, by forecasting future laboratory performance, one or more workflow steps where deviations may occur, such as a sample transfer step or within laboratory equipment, can be identified during the test sample processing time by comparing each reported event with a corresponding simulated event, allowing for correction in the actual laboratory setting as soon as the deviation is detected.

[0033] Furthermore, laboratory system elements involved in the deviation can be identified, or at least potential laboratory elements that may be involved in the deviation can be narrowed down for decision-making during the simulation process. [Brief explanation of the drawing]

[0034] The following detailed description of specific embodiments of this disclosure can be best understood in conjunction with the following drawings, in which similar structures are indicated by similar reference numerals.

[0035] [Figure 1] This document shows a flowchart of the laboratory configuration optimizer and simulation during the laboratory design phase according to an embodiment of this disclosure. [Figure 2] This document shows an exemplary user interface dashboard display during the laboratory design phase according to an embodiment of the present disclosure. [Figure 3] This document shows a flowchart for runtime application of a laboratory configuration with laboratory performance simulation according to an embodiment of the disclosure. [Figure 4]This document shows an exemplary actual laboratory performance dashboard display showing a time-versus-results histogram according to an embodiment of the present disclosure. [Figure 5] This diagram shows a flowchart for runtime application of a laboratory configuration, including laboratory performance simulation based on laboratory user input, according to an embodiment of the disclosure. [Figure 6] This embodiment of the disclosure shows an exemplary user interface dashboard display in which a laboratory operator manually changes the laboratory configuration. [Figure 7] This flowchart illustrates the use of a simulator to check the time required to perform laboratory maintenance services and / or laboratory maintenance according to embodiments of the present disclosure. [Figure 8] This embodiment of the disclosure shows an exemplary user interface dashboard display illustrating the impact of maintenance service equipment on laboratory performance. [Figure 9] This document shows a flowchart of a laboratory performance simulation, which is performed in parallel with actual laboratory performance to predict future laboratory problems, according to embodiments of this disclosure. [Figure 10] This document shows an exemplary user interface dashboard display illustrating how laboratory problems can be identified according to embodiments of this disclosure. [Figure 11] This invention provides a graphical method for identifying laboratory problems according to embodiments of this disclosure. [Figure 12] This document shows a flowchart of a laboratory performance simulation, which is performed in parallel with actual laboratory performance to predict when reagents will run out, according to an embodiment of the present disclosure. [Figure 13] This embodiment of the disclosure shows an exemplary user interface dashboard display illustrating the difference between simulated performance and the current laboratory configuration. [Figure 14]This document shows a flowchart of a laboratory performance simulation, performed in parallel with actual laboratory performance, to predict when test results can be expected or when test samples can be prepared, according to embodiments of the present disclosure. [Figure 15] This embodiment of the disclosure shows an exemplary user interface dashboard display that shows the prediction of important laboratory events through simulation. [Modes for carrying out the invention]

[0036] Detailed description of the invention The following detailed description of embodiments refers to the accompanying drawings, which show specific embodiments that form part of this specification and can be implemented as illustrative rather than restrictive. It should be understood that other embodiments may be available and that logical, mechanical, and electrical modifications may be made without departing from the spirit and scope of this disclosure.

[0037] In the following context, the terms “have,” “comprise,” or “include,” or any grammatical variations thereof, are used in a non-exclusive manner. Therefore, these terms may refer to both situations in which the entity being described in this context has no further features beyond those introduced by these terms, and situations in which one or more additional features exist. For example, the expressions “A has B,” “A has B,” and “A includes B” may both refer to situations in which A has no other elements besides B (i.e., A consists solely of B and exclusively of B), and situations in which entity A has one or more additional elements besides B, such as element C, elements C and D, or even further elements.

[0038] Furthermore, it should be noted that the terms “at least one,” “one or more,” or similar expressions indicating that a feature or element can exist one or more times are usually used only once when introducing each feature or element. In most cases below, when referring to each feature or element, the expressions “at least one” or “one or more” will not be repeated, despite the fact that each feature or element can exist one or more times.

[0039] The use of "a" or "an" may be used to describe elements and components of the embodiments herein. This is done simply for convenience and to give a general meaning to the concepts of the invention. This description should be read as including one or at least one, and singular forms include plural forms unless it is clear that this is not the case.

[0040] As used herein, the terms “laboratory equipment” or “laboratory apparatus” may encompass any device or apparatus component capable of performing and / or causing to perform one or more processing steps / workflow steps on one or more biological samples and / or one or more reagents. Thus, the expression “processing step” may refer to a physically performed processing step such as centrifugation, aliquoting, sample analysis, sample transfer, or storage. The terms “equipment” or “apparatus” may encompass pre-analysis equipment / apparatus, post-analysis equipment / apparatus, analytical equipment / apparatus, and laboratory middleware.

[0041] As used herein, the term “laboratory middleware” can refer to any physical or virtual processing device that can be configured to control laboratory equipment / devices or a system comprising one or more laboratory equipment / devices, so that workflows and workflow steps can be executed by laboratory equipment / systems. For example, laboratory middleware can instruct laboratory equipment / systems to perform pre-analysis, post-analysis, and analysis workflows / workflow steps, as well as sample transfer steps. Laboratory middleware can receive information from a data management unit regarding which steps need to be performed for a particular test sample. In some embodiments, laboratory middleware can be integrated with a data management unit, can be configured by a server computer, and / or be part of a single laboratory piece of equipment / device, or can be distributed across multiple pieces of equipment / devices in a laboratory automation system. Laboratory middleware may be embodied, for example, as a programmable logic controller that runs a computer-readable program containing instructions for performing operations.

[0042] As used herein, the term “workflow control unit” is a broad term and should be given its usual and customary meaning to those skilled in the art, and should not be limited to any special or customized meaning. Specifically, the term can refer to, but not limited to, an electronic device configured by hardware and / or software programming in particular for controlling the functionality of a sample processing system within laboratory middleware. The workflow control unit may be further configured for data exchange with at least one monitoring system and / or at least one cloud server. Specifically, the workflow control unit may be a computing device within the laboratory middleware, such as at least one processor, configured to receive an electronic signal from at least one monitoring system and / or at least one cloud server, such as at least one information item, and to further evaluate the received signal. Furthermore, the workflow control unit may be configured to control a function based on the received and evaluated signal, for example, based on at least one piece of information.

[0043] A "data storage unit" or "database" can be a computing unit for storing and managing data, such as memory, hard disk, or cloud storage. This may include data related to biological / medical test samples processed by an automated system. The data management unit can be connected to a Laboratory Information System (LIS) and / or Hospital Information System (HIS). The data management unit can be a unit within laboratory equipment / devices, or located in the same location as the laboratory equipment / devices. It can be part of laboratory middleware. Alternatively, the database can be a remote unit; for example, it can be implemented in a computer connected via a communication network.

[0044] As used herein, the term “communication network” can encompass any type of wireless network, such as WiFi®, GSM®, UMTS, Bluetooth, ultra-wideband (UWB), infrared, inductive, or other wireless digital networks, or cable-based networks, such as Ethernet®. In particular, a communication network may implement the Internet Protocol (IP). For example, a communication network may include a combination of cable-based and wireless networks.

[0045] As used herein, the terms “remote system” or “server” may include any physical or virtual machine having physical or virtual processors and capable of receiving, processing, and transmitting data. A server may run on any computer, including dedicated computers, which may often also be individually referred to as “servers” or shared resources such as virtual servers. Often, a computer may provide multiple maintenance services and have multiple server runs. Thus, the term server may include any computerized device that shares resources with one or more client processes. Furthermore, the terms “remote system” or “server” may include distributed data transmission and processing systems over a data network (such as a cloud environment).

[0046] As used herein, the term “simulation” can encompass the execution of a computer-implemented model to predict future system behavior (e.g., the state, quantity, and key performance indicators (KPIs) of components) based on available data such as current conditions, historical data, anticipated future data, expected data ranges, and / or probability distributions. A simulation can encompass any use of a model that reflects relevant aspects of laboratory conditions and orders, as well as the use of calculations to predict any data of interest regarding the future condition or performance of a laboratory. A simulation can use a computer implementation of a laboratory model to mimic one or more aspects of the actual behavior of a laboratory.

[0047] The simulation can calculate the changes in the state of entities moving through a process (e.g., sample tubes) and resources required for the process (e.g., equipment, human resources, consumables, reagents, etc.) over time. Changes in the state of entities can be caused by processes or activities performed on them, such as entering or leaving laboratory equipment, waiting before an entity can be processed, processing time, and transport of the entity, but can also be influenced by the state of resources (e.g., laboratory equipment being turned off) and the state of other entities (e.g., occupying the same resources, using the same process, etc.).

[0048] The simulation can be a discrete-event simulation in which state changes are called "events," or any other method from predictive analytics such as machine learning, extrapolation, or statistical simulation. In one embodiment, the simulation results are used to calculate aggregate information about the laboratory, such as expected future workload, buffer occupancy, performance parameters, potential performance, violation issues, resource consumption, costs, or derived events for laboratory equipment, transport systems, and human resources.

[0049] As used herein, the term “optimization” can encompass the activity of identifying the best option from several alternatives (e.g., scheduling of activities, configuration of laboratory equipment, configuration of software, amount of resources, workflow to follow and resources to use, location of resources) while considering constraints (e.g., resource availability, location of entities) such that one or more objective functions are maximized or minimized. The objective function is a mathematical function that numerically expresses how well the option meets quality criteria (e.g., those of the laboratory owner / operator, the healthcare professional who ordered the test, and / or the patient). The objective function is constructed from relevant performance metrics such as turnaround time, time to results, throughput, (in)efficiency, cost, robustness, and workload. The results of optimization may include one or more options that are good, optimal, or better than the current state, as measured by the objective function while considering the achievement of constraints. Optimization also includes actions necessary to implement the identified best option in order to achieve the improved objective. Such actions may include manual adjustments by the laboratory operator, along with suggestions from the laboratory system and / or fully automated computer-based adjustments. All adjustments can share the goal of improving one or more or a weighted combination of key performance indicators (KPIs) of the laboratory.

[0050] The difference between simulation and optimization is that optimization generates proposals for achieving goals, such as high performance, in the best possible way. Therefore, optimization is a prescriptive method, not a predictive (simulation) method. Prescriptive analytical methods can be used to generate suggestions or automatic adjustments for laboratory operators. For example, optimization may propose a new allocation of reagent cassettes to laboratory analytical instruments to achieve better (optimal) performance, after which simulation is used to evaluate the performance that the newly proposed configuration can achieve. An example of a prescriptive analytical method is presented in the paper P.FESTA, "A brief introduction to exact, approximation, and heuristic algorithms for solving hard combinatorial optimization problems," 16th International Conference on Transparent Optical Networks (ICTON), 2014, pages 1 to 20, doi:10.1109 / ICTON.2014.6876285.

[0051] Optimization problems can be solved by exact optimization methods, approximating the original problem with simpler methods, solving the simpler problem, and / or by heuristics and / or metaheuristics. Exact optimization methods can be (i) branch and bound methods, (ii) dynamic programming methods, or (iii) solvers. However, other exact optimization methods may be assumed and used.

[0052] A solver can have multiple algorithms (i.e., not just exact ones). An exact optimization method can also include a combination of the methods described above. Solving an approximated simpler problem can include applying (i) one or more greedy algorithms, (ii) local search, (iii) one or more relaxation-based algorithms, or (iv) one or more random algorithms. Other methods for solving an approximated simpler problem can be assumed and used. Solving an approximated simpler problem can also include a combination of the methods described above. Heuristics and / or metaheuristics can be (i) simulated annealing, (ii) one or more evolutionary algorithms, (iii) tabu search, or (iv) one or more greedy randomized adaptive search procedures (GRASP). Heuristics and / or metaheuristics can also include a combination of the methods described above.

[0053] Typically, a standard laboratory performance dashboard displays current and historical laboratory performance. The laboratory performance dashboards disclosed herein can predict or forecast future laboratory performance. By running a full-laboratory simulation in the background in real time, the following capabilities can be part of a laboratory performance dashboard system: - Laboratory operators can "look to the future" to gain a better prognosis. For example, a laboratory operator can get the time needed to prepare specific test results. This can be important for some types of test samples, such as urgent samples, such as short-time-to-analyze (STAT) samples for emergencies. Furthermore, a laboratory operator can obtain information on when a test sample has completed processing, which can then be made available for other processes, such as analytical instruments or manual analytical processes that require manual processing of the test sample. In addition, a laboratory operator can be notified when human interaction is needed by the laboratory, such as for upcoming laboratory issues, reloading reagents or consumables or removing sample racks, predictive maintenance and service activities, or waste removal. - Laboratory operators can be informed about the results of any intended laboratory operations. For example, laboratory operators can see the impact of changes made to the laboratory configuration, such as changes to test assignments, the number of cassettes, etc. Furthermore, combined with suggestions generated by laboratory predictions, laboratory operators could see the effect of selecting one or more proposed alternative laboratory configurations. In addition, laboratory operators can see the impact on laboratory performance of a particular selection of sampling load relative to the time to obtain test results. Furthermore, laboratory operators can see the impact on laboratory performance of maintaining analytical instruments or transfer lines at a specific time, or turning off or putting a particular laboratory system into standby mode, for example, to save energy. Also, laboratory operators can see the potential improvement in laboratory performance when using aliquots or, for example, centrifugating several test samples in separate, independent centrifuge systems, rather than using only centrifuges connected to a fully automated laboratory system.

[0054] Regarding laboratory simulators, one or more of the following aspects should be considered. Firstly, when analyzing a new configuration, the laboratory simulation model can obtain those configuration inputs from the laboratory optimizer and the order list from the laboratory middleware. The order list is processed, for example, to scale up the order load of the laboratory system. Alternatively, the laboratory configuration can be directly input / modified by the laboratory operator, for example, by manually defining where, which, and how many test cassettes should be installed. However, the changes that can be made manually or suggested by the optimizer automatically depend on the situation and the preferences of the laboratory operator. For example, during design time, the laboratory hardware may vary, for example, by space limitations. During runtime, if the laboratory system is installed, for example, only the reagent cassette placement on the existing laboratory hardware may be optimized. The laboratory configuration designer can add customer preferences, for example, preferred types of laboratory hardware or which analytical instruments should perform the same type of testing.

[0055] Secondly, in order to analyze the impact of changes in laboratory configuration or the availability of laboratory analytical instruments, such as during laboratory maintenance services or repairs, laboratory operators can define laboratory events, such as when to turn off specific laboratory analytical instruments or other hardware.

[0056] Thirdly, the simulation / configuration state can be synchronized with the current state information of the laboratory to improve predicted laboratory performance. For example, if the laboratory model is not 100% accurate, or if other delays occur, test samples may enter the laboratory analyzer earlier or later in real time compared to the laboratory simulation. Synchronizing the laboratory simulation can help compensate for these deviations. The information required for synchronization can be obtained from known laboratory event data from the laboratory middleware, which can also include when and which laboratory analyzers are masked / unmasked.

[0057] Fourth, changes to the laboratory configuration can be synchronized with data from laboratory middleware and / or laboratory analytical instruments, such as which analytical instruments are masked, the placement of reagent packs, and / or the sample scheduling configuration of the laboratory middleware.

[0058] Fifth, the laboratory operator or the laboratory system itself can trigger a process used to supply order data to the optimizer, such as from laboratory middleware over several days. One or more proposed possible laboratory configurations can be obtained and simulated. Optionally, the laboratory operator can select a scenario from the different proposals to be simulated. The dashboard can then show the difference in laboratory performance values ​​between the current laboratory configuration and alternative laboratory configurations. For example, the laboratory operator can observe the impact of changes in laboratory configuration on test assignment to laboratory analytical instruments on turnaround time (TAT) or walkway time, the impact on human resource scheduling including TAT pause time or working time such as when the last test sample was processed, and the impact of turning off or maintaining laboratory equipment at specific times in the TAT.

[0059] Sixth, the dashboard displays one or more laboratory performance metrics for the past, present, or future time period, as well as a comparison with the same laboratory metrics for the current laboratory system, based on actual data such as: - Simulated throughput - For example, simulated TAT of test samples such as TAT ​​of samples entering the laboratory until test results are published, TAT of orders entered by physicians until test results are sent to physicians, TAT of pre-analysis systems, and / or TAT of serum work area analysis. - Simulated time obtained - Simulated buffer level - Traffic intensity of simulated test samples - Simulated laboratory equipment load and human resource workload - Simulated idle time - For example, the number of test samples or simulated tests that exceed laboratory performance tolerances, either absolutely or relatively, such as the percentage of test samples or test results that fall within or outside the specified maximum time to result. - Simulated point-to-point travel time - Simulated latency, e.g., non-productive time such as within a buffer. - Simulated walkaway time or the number of required human interactions per hour - For example, cost or benefit metrics of an alternative laboratory configuration compared to the current laboratory configuration, such as the number of quality control (QC) operations per day, the cost of QC operations per day, the number of wasted tests, and / or costs due to the expiration dates of reagents.

[0060] Seventh, the dashboard provides laboratory operators, laboratory system owners, and / or laboratory maintenance service providers with information on anticipated upcoming laboratory activities and events, showing when these events are expected, for example, in the next 10 minutes, 30 minutes, 1 hour, half day, per week, shift, day, or week, enabling laboratory operators to anticipate these events. Examples of these events and activities are as follows: - Estimating when reagents, consumables, and / or disposable supplies will run low and need to be replenished. For example, reagent levels may be low, but if they are not ordered frequently, they may have longer walkaway times than if they are ordered frequently. - An estimate of the timeframe until small or large laboratory maintenance service / maintenance activities, performed by a system operator or technician, are required may be necessary. This information may be displayed only within the laboratory system, or it may be automatically communicated to laboratory service providers, such as customer service, so that service visits can be scheduled.

[0061] Eighth, laboratory simulations are used to determine operating confidence intervals by running many laboratory simulations using the same partial probability parameters, such as order distribution and processing time variability. These confidence intervals can be used to compare with the actual laboratory system. If the actual laboratory system deviates excessively negative from the interval determined by the simulation, this is an indicator that the actual laboratory system needs improvement. Laboratory simulations can determine potential causes of deviations, as well as the sensitivity to parameters that may cause deviations, such as delayed laboratory operator interactions.

[0062] Furthermore, laboratory simulations can include, for example, optimization-based schedulers to simulate an ideal working laboratory system where manual interactions can be performed at appropriate times. The simulations demonstrate the achievable laboratory performance relative to actual laboratory performance, showing customers that improvements are possible through better scheduling. The scheduler within the simulator can demonstrate how to achieve optimal laboratory performance.

[0063] Furthermore, laboratory simulations can be used to provide missing information from parts of the laboratory system. Examples of missing information are as follows: - Lack of knowledge about the behavior of third-party providers that makes it difficult to include them in a well-scheduled laboratory system. Using machine learning or statistical data, models of third-party providers that can be included in the scheduler can be created. -To obtain information, laboratory equipment that does not communicate necessary information, such as the expected time for test results, their buffer, and resource load levels, can be simulated.

[0064] Furthermore, laboratory simulations can be continuously adjusted by real-time laboratory events. Because laboratory simulation models are typically simplifications of real-world events, predictions become less accurate as they are further examined. By continuously adjusting the state of the model according to recent real-time laboratory data, predictions or forecasts can be optimally predicted or anticipated.

[0065] Finally, the differences between reality and the model can also be analyzed to trigger alarms / warnings or simply notify the laboratory operator that the actual laboratory system is behaving differently than expected. Examples include: - Trend detection where specific elements show increasing deviations from an ideal state, such as the aging of components, and where a time lag exists between actual laboratory events and modeled laboratory events as the frequency increases. These trends can be displayed on a dashboard and, through extrapolation, an estimate of the remaining time before service / part replacement in the laboratory can be given. - For example, anomaly detection via machine learning that can identify unique laboratory events that differ from normal laboratory operations. These can be, for example, short congestion of test samples, congestion of test sample traffic, and delays due to unique laboratory events such as combinations of factors that lead to unacceptable situations, such as incorrect prioritization and logical processing rules combined with a specific order list that result in unacceptable lead times. Laboratory operators can be notified about these situations, including the time when the problem occurred. In this case, recorded and simulated laboratory event data can be replayed for analysis and to help find solutions.

[0066] Referring first to Figure 1, Figure 1 shows a flowchart of a laboratory configuration optimizer and performance configuration simulation during the design phase according to an embodiment of the present disclosure. First, the laboratory configuration module 110 determines an optimized laboratory configuration using the laboratory configuration optimizer. Laboratory operator preferences and constraints 25 and laboratory order data 50 are used as inputs to the laboratory configuration optimizer. The resulting optimized laboratory configuration is supplied to the simulation module 110 to simulate how the resulting optimized laboratory configuration can be performed. The laboratory order data 50 is also supplied to the simulation module 110 to provide input to the simulated laboratory. From the simulation module 110, the output or performance of the simulated laboratory configuration is sent to the performance visualization module 120 or dashboard so that the laboratory operator can see how the resulting optimized laboratory configuration functions.

[0067] Furthermore, the resulting optimized laboratory configuration can be used by the ordering system module 150 to facilitate ordering of laboratory supplies. Additionally, the resulting optimized laboratory configuration can be used by the cost calculation module 140 to facilitate the calculation of costs associated with the laboratory.

[0068] Figure 2 provides an exemplary user interface dashboard display during the laboratory design phase. The optimized laboratory hardware is displayed in the upper half 1210 of the dashboard, and the test assignment configuration is displayed in the lower half 1220 of the dashboard. The optimized laboratory hardware 1210, i.e., analytical instruments, is displayed linearly in the upper left 1250 of the dashboard and as graphic modules in the upper right 1260. The test assignments 1220 may include a list of parameters 1230 assigned to each laboratory module, along with submodules such as a measurement work cell or reagent rotor, in the lower left of the dashboard. Since reagent cassettes can be used for multiple test parameters, a list of cassette material numbers, along with the physical locations of the reagent cassettes, may be enumerated in the lower right 1240 of the dashboard display.

[0069] Optionally, the resulting optimized laboratory configuration can also be supplied to the animation / virtual reality (VR) module 130 to provide a visual representation of the resulting optimized laboratory configuration to the laboratory's customers or other laboratory personnel.

[0070] Referring to Figure 3, Figure 3 shows a flowchart of the runtime application of a laboratory configuration with simulation according to an embodiment of the present disclosure. In Figure 3, the laboratory configuration optimization module 200 proposes a simulated laboratory configuration based on order data 150 from the actual laboratory 240 and the laboratory operator's preferences and constraint inputs 125. The proposed optimized laboratory configuration is then input to the laboratory performance simulation module 210. The order data 150 from the actual laboratory 240 is also input to the laboratory performance simulation module 210. The simulated laboratory performance from the laboratory performance simulation module 210 is compared with the actual laboratory performance from the actual laboratory 240 and displayed on a dashboard 220 for the laboratory operator. The laboratory operator can then reconfigure the actual laboratory 240 by selecting the proposed laboratory configuration 230 displayed on the dashboard 220 along with other laboratory operator inputs 175.

[0071] Figure 4 shows an exemplary actual laboratory performance dashboard display illustrating a histogram of time to results, i.e., the distribution of time to results per test sample. The x-axis 1410 represents the turn-to-attach (TAT) time. The y-axis 1420 represents the number of test samples with that particular TAT. The dashed line 1430 represents the target cutoff or time threshold, i.e., the time by which all test sample results should be available. In this example, the goal is to obtain all test sample results within 90 minutes. For test sample results that exceed this target, a warning box 1440 is displayed on the dashboard. In this example, 11% of the test sample results exceeded the 90-minute target time. However, the simulated laboratory performance was able to demonstrate that achieving the 90-minute target time for test sample results was possible.

[0072] Figure 5 shows a flowchart of the runtime application of a laboratory configuration with operator input simulation according to an embodiment of the present disclosure. Figure 5 is similar to Figure 3, except that in this embodiment, instead of having a laboratory configuration optimization module 200, a laboratory operator proposes changes to a laboratory configuration 225, which are input to the laboratory performance simulation module 310 along with order data 250 from the actual laboratory 240, and the laboratory performance of the input laboratory configuration is simulated. In one embodiment, the order data 250 from the actual laboratory 240 is historical order data and can be aggregated into a typical order list for that day. The simulated laboratory performance from the laboratory performance simulation module 310 is compared with the actual laboratory performance from the actual laboratory 340 and displayed on a dashboard 320 for the laboratory operator. The laboratory operator can then select which laboratory configuration can be implemented next 330. The laboratory operator can select the simulated laboratory configuration if the simulated laboratory performance is better than the actual laboratory performance.

[0073] Figure 6 shows an exemplary user interface dashboard display illustrating how a laboratory operator can manually modify a laboratory configuration. The laboratory operator can select a laboratory analyzer module 1610 from among the laboratory analyzer modules displayed in the upper right corner of the dashboard. After selecting the laboratory analyzer module 1610, a list of the possible test parameters 1620 installed for that laboratory analyzer module 1610 is displayed. These test parameters can be selected by the laboratory operator and assigned to laboratory submodules 1640, such as a reagent rotor. The test assignment can be modified by the laboratory operator by selecting the number of reagent cassettes to add (+1) or the number of reagent cassettes to remove (-1). If the laboratory operator selects the simulate button 1650, the laboratory performance of the new laboratory configuration can be simulated before actually implementing the configuration in the laboratory to verify whether it performs better than the current configuration.

[0074] Figure 7 shows a flowchart illustrating the use of the laboratory performance simulation module 410 to suggest the time for performing laboratory maintenance services that minimize disruption to laboratory performance, according to an embodiment of the present disclosure. In this embodiment, the laboratory performance simulation module 410 can suggest the time for performing laboratory maintenance or servicing on laboratory equipment, for example, for a time that does not excessively negatively impact laboratory performance when one of the laboratory analytical instruments is offline. To see the impact on overall laboratory performance, different cases / times, i.e., different times to initiate laboratory maintenance services / servicing and / or which laboratory equipment to maintain, can be suggested as input to the laboratory performance simulation module 410 by the laboratory operator 405. Known order data 350 from the actual laboratory 440 can also be input to the laboratory performance simulation module 410. Furthermore, in one embodiment, predicted order data 355 based on forecast / expected order data can also be input to the laboratory performance simulation module 410. The simulated laboratory performance from the laboratory performance simulation module 410 can then be displayed on a dashboard 420 for the laboratory operator. The laboratory operator can then select the best time to schedule laboratory maintenance services (430) and, based on the simulated impact of the laboratory maintenance services on the laboratory's performance, select which laboratory equipment to schedule.

[0075] Figure 8 shows an exemplary user interface dashboard display illustrating the impact of maintenance service equipment on laboratory performance. On the left side of the dashboard display 1800, a line of laboratory equipment or individual laboratory modules 1810 are displayed and can be selected for maintenance service. The start time 1815 and duration of the laboratory maintenance service 1820 can also be selected. Several laboratory maintenance service scenarios, or examples, can be selected simultaneously. Different laboratory maintenance service examples can be simulated by the laboratory operator selecting the simulate button 1825. The results of the laboratory simulation can be displayed and compared in the simulation display box 1830. In one embodiment, a scenario without laboratory maintenance service can also be displayed for comparison. Thus, the laboratory operator can determine the impact of laboratory maintenance service on laboratory performance and select the scenario with the least impact on laboratory performance, for example, the scenario with the least impact on the target TAT time. The laboratory operator can then select the optimal time to perform maintenance service on the laboratory equipment, i.e., the time with the least impact on laboratory performance.

[0076] Figure 9 shows a flowchart of simulated laboratory performance, run in parallel with actual laboratory performance to predict future problems, such as shortages of reagents and / or other consumables, according to an embodiment of the present disclosure. The times when these undesirable events may occur can be shown on the dashboard. In this embodiment, known order data from the actual laboratory 540, the current laboratory configuration, and consumable status (i.e., reagent levels) 550 can be input into the laboratory performance simulation module 510. Predicted laboratory performance events from the laboratory performance simulation module 510 are then displayed on a dashboard 220 for the laboratory operator. Predicted laboratory performance events may include, for example, predicted laboratory test result times, predicted times when the laboratory may run out of reagents or other consumables, predicted laboratory performance, and / or predicted times when the laboratory operator may need to intervene in the laboratory system, for example, for laboratory maintenance services or servicing. The laboratory operator can then decide when to replenish reagent cassettes or other consumables 530, have an estimate of when laboratory operator action may be required, and / or when laboratory test results will be ready.

[0077] Figure 10 shows an exemplary user interface dashboard display illustrating how laboratory problems can be identified. Laboratory bottlenecks 1020 (shown as triangular warning icons) can be identified by simulation, i.e., by comparing ideal laboratory performance with actual laboratory performance. Bottlenecks 1020 can be indicated, for example, by showing which laboratory module is experiencing delays (top of dashboard 1010) or by showing a workflow step where the step was not performed optimally (bottom of dashboard 1020). By selecting the bottleneck icon 1020 or by hovering the cursor over the bottleneck icon 102, a text window 1015 appears, displaying further details about the type of problem occurring at that location.

[0078] Figure 11 illustrates a graphical method for identifying laboratory problems. In this embodiment, the assumptions of the simulation (e.g., the test sample reach profile graphed as a box plot) can be compared with the actual data of the test sample reach profile (i.e., the dashed line). Based on the results of this type of comparison, a new simulation / optimization can be triggered.

[0079] Figure 12 shows a flowchart of simulated laboratory performance, run in parallel with actual laboratory performance to predict when reagents will run out, according to an embodiment of the present disclosure. In this embodiment, information on when reagent cassettes are loaded is automatically provided by the laboratory system 605 and can be input into the laboratory performance simulation module 610. In this embodiment, known order data 650 from the actual laboratory 640 is input into the laboratory performance simulation module 610. The predicted time at which the laboratory may run out of simulated reagents from the laboratory performance simulation module 610 is then displayed on a dashboard 620 for the laboratory operator. The laboratory operator can then decide when to replenish or replace the reagent cassettes 630.

[0080] Figure 13 shows an exemplary user interface dashboard display illustrating the difference between simulated performance and the current laboratory configuration. For example, if a laboratory operator wants to optimize the laboratory configuration because the current configuration is not currently optimized for current or planned test orders, the dashboard can display to the laboratory operator, for example, the difference between the simulated laboratory performance of the optimized laboratory and the current unoptimized laboratory design at the top of dashboard 1110. In this section of dashboard 1110, laboratory performance indicators can be shown as numbers such as TAT ​​1115, as well as graph comparisons 1120. The lower section of dashboard 1125 displays proposed laboratory changes, such as changes to the reagent cassette configuration of laboratory analytical instruments. In one embodiment, the dashboard provides only information. However, in another embodiment, the proposed laboratory configuration can be applied to the current laboratory configuration.

[0081] Furthermore, Figure 12 also shows how to further consider the future. If not all orders are known yet, or if the arrival time of test samples from those orders is unknown, the laboratory may run out of reagents. The laboratory performance simulation module 610 can use predicted order information based on the current laboratory situation and information provided from the past, such as similar days. Thus, the predicted number of orders expected on that day can be calculated 660 and input into the laboratory performance simulation module 610 665.

[0082] Figure 14 shows a flowchart of a laboratory performance simulation, according to embodiments of the present disclosure, which is run in parallel with actual laboratory performance to predict when test results can be expected or when test samples can be prepared. In this figure, pre-analytical instrument 705 and post-analytical instrument 710 are known to the laboratory system, i.e., there are event models available for these instruments. Laboratory analyzer 715 is also known, but laboratory analyzer 720 is unknown, i.e., there is no event model available for laboratory analyzer 720. The unknown element can lead to an unknown time, indicated by the question mark 730 in Figure 13. Since all time events of the actual laboratory system are communicated, this unknown instrument element can be replaced by a simulation machine learning model that gets better over time as it receives more input. The laboratory performance simulation model can then make predictions / forecasts of events t1...t3. The predictions / events can be displayed and updated on the laboratory dashboard.

[0083] Because the laboratory performance simulation model is not perfect, the times provided to the laboratory dashboard by the laboratory performance simulation module 740 can be updated by the actual times that occur, i.e., in Figure 13, when t01 (time when the sample leaves the pre-analytical instrument 705), t12 (time when the sample leaves the laboratory analytical instrument 715), and t23 (time when the sample leaves the laboratory analytical instrument 720) occur. Once real-time results are received and added to the laboratory performance simulation module 740, a better prediction / forecast of the remaining event times can be obtained.

[0084] Figure 15 shows an exemplary user interface dashboard display illustrating the prediction of important laboratory events through simulation. At the top of the dashboard display 1150, the laboratory operator can observe when, i.e., when, the test sample results for a specific test sample selected by the laboratory operator will be published, i.e., predicted. The lower section of the dashboard display 1155 displays events requiring manual intervention by the laboratory operator. This section of the dashboard is displayed to the laboratory operator, for example, when reagents may be running low or when the output buffer is full and the test sample rack needs to be removed from the laboratory system.

[0085] Technologies for providing predictive information may include integration of event simulations with dashboards and / or control software. Furthermore, models for event simulations can be mathematical, heuristic, statistical, or logical deterministic or partially probabilistic formulations, as known in the art. Models within simulations may include learning heuristics that can be trained in real-time with actual event data to gradually acquire realistic behavior over time. Different simulations of the same laboratory system, or parts of a laboratory system, may be run in parallel using different types of models and then compared, allowing the best predictive simulation model to be selected to provide results for the laboratory performance dashboard. For example, a non-learning simulation model might initially perform poorly but tend to perform better over longer training times; in this case, the non-learning simulation model would first provide information to the laboratory performance dashboard. The laboratory system can determine how well each simulation model is performing by comparing predicted events with actual laboratory data. Depending on which simulation model performs best, the laboratory system decides which results to include as information or how to weight the results to extract predictions or forecasts. Furthermore, the simulation model within the simulation can also include statistical descriptions, such as distributions.

[0086] For event simulation, software code is written and / or existing simulation software / libraries are incorporated. Examples of such existing simulation software / libraries may include Simio®, AnyLogic®, Arena®, Plant Simulation®, and the Python with Simpy® library.

[0087] When the program is executed on a computer or computer network, computer program products including computer-executable instructions for performing the disclosed methods are further disclosed and proposed in one or more embodiments included herein. Specifically, the computer program may be stored on a computer-readable data carrier or a server computer. Thus, specifically, one, two or more, or all of the method steps described above can be performed using a computer or computer network, preferably using a computer program.

[0088] As used herein, a computer program product refers to a program as a tradable product. The product may generally reside in any format, such as paper, or on a computer-readable data carrier located on-premises or remotely. Specifically, a computer program product may be distributed via a data network (such as a cloud environment). Furthermore, not only the computer program product, but also the execution hardware may be located on-premises or in a cloud environment.

[0089] Further disclosed and proposed is a computer-readable medium that, when executed by a computer system, contains instructions causing a laboratory automation system to perform a method according to one or more embodiments disclosed herein.

[0090] Further disclosed and proposed are modulated data signals that, when executed by a computer system, include instructions causing a laboratory automation system to perform a method according to one or more embodiments disclosed herein.

[0091] Referring to computer implementations of the disclosed methods, one or more or all method steps of a method relating to one or more embodiments of the methods disclosed herein can be performed using a computer or computer network. Therefore, generally, any method step involving data provision and / or manipulation can be performed using a computer or computer network. Generally, these method steps may include any method step, except typically method steps requiring manual work, such as certain embodiments that perform sample provision and / or actual measurements.

[0092] It should be noted that terms such as “preferably,” “generally,” and “typically” are not used herein to limit the scope of the claimed embodiments or to imply that certain features are important, essential, or even more important to the structure or function of the claimed embodiments. Rather, these terms are merely intended to highlight alternative or additional features that may or may not be utilized in the particular embodiments of this disclosure.

[0093] By describing this disclosure in detail and referring to its specific embodiments, it will be apparent that modifications and alterations are possible without departing from the scope of the disclosure as defined in the appended claims. More specifically, while certain aspects of the disclosure are identified herein as preferred or particularly advantageous, the disclosure is intended not to be limited to these preferred aspects.

Claims

1. A computer implementation method for predicting the future laboratory performance of a laboratory system comprising multiple laboratory devices configured to perform tests on laboratory test samples, laboratory middleware, a control unit, and a dashboard display, all of which are connected communicatively via a network communication connection, the system comprises: The laboratory operator's preferences and laboratory constraints are provided from the laboratory operator to the optimization module of the control unit, Providing laboratory input data and order data to the optimization module of the control unit, The optimization module of the control unit optimizes the laboratory configuration based on the preferences of the laboratory operator, the laboratory constraints, the laboratory input data, and the order data. Based on the optimized laboratory configuration provided by the optimization module and real-time laboratory input data and order data, the simulation module of the control unit simulates the future laboratory performance of the laboratory system. The simulated future laboratory performance and the actual laboratory performance are displayed to the laboratory operator on the dashboard display, Computer implementation methods, including those mentioned above.

2. The computer implementation method according to claim 1, wherein the laboratory input data and order data are continuously provided in real time by the laboratory middleware, and the real-time laboratory input data includes the timing of masking of analytical instruments, assignment and placement of reagent packs, sample loading scheduling, and / or combinations thereof.

3. The computer implementation method according to claim 1 or 2, wherein the simulated future laboratory performance includes predicting the arrival of test results from the plurality of laboratory devices.

4. The computer implementation method according to claim 1 or 2, wherein the displayed simulated future laboratory performance includes simulated throughput, sample TAT, time to result, buffer level, sample traffic intensity, laboratory operator equipment load and workload, idle time, number of samples, reagents, or tests exceeding performance tolerances, point-to-point travel time, buffer wait time, walkaway time, number of laboratory operator interactions per hour, number of laboratory operators required, power consumption, water consumption, operating costs, or a combination thereof.

5. The computer implementation method according to claim 1 or 2, wherein the displayed simulated future laboratory performance includes an indicator of the advantages of the simulated laboratory configuration compared to the current laboratory configuration.

6. The computer implementation method according to claim 1 or 2, further comprising modifying the current laboratory configuration of the laboratory via input from the laboratory operator based on the simulated future laboratory performance.

7. The system will trigger a warning if the simulated future laboratory performance and actual laboratory performance deviate from acceptable levels, and / or if the arrival of simulated test samples and actual test samples deviates from acceptable levels, and / or if an anomaly is detected. Displaying the potential cause of the deviation or abnormality on the dashboard display, The computer implementation method according to claim 1 or 2, further comprising:

8. The computer implementation method according to claim 1 or 2, further comprising calculating future orders estimated based on the optimized laboratory configuration.

9. The computer implementation method according to claim 1 or 2, further comprising calculating the sample loading effect on the simulated future laboratory performance.

10. The computer implementation method according to claim 1 or 2, further comprising scheduling manual interactions with the laboratory system based on the optimized laboratory configuration.

11. The computer implementation method according to claim 1 or 2, further comprising displaying the predicted future events, indicating when the predicted future events are expected to occur, wherein the predicted future events are estimates of when replenishment will be needed, and / or estimates of the start time of a maintenance event, and / or estimates of the duration of a maintenance event, and / or predictions of future laboratory maintenance events.

12. A computer implementation method for predicting the future laboratory performance of a laboratory system comprising multiple laboratory devices configured to perform tests on laboratory test samples, laboratory middleware, a control unit, and a dashboard display, all of which are connected communicatively via a network communication connection, the system comprises: The various configurations of the aforementioned laboratory system are provided from the laboratory operator to the simulation module of the control unit, To continuously provide real-time laboratory input data from the aforementioned multiple laboratory devices to the laboratory middleware, The real-time laboratory input data and order data are continuously provided from the laboratory middleware to the simulation module. Based on the real-time laboratory input data and order data, the simulation module of the control unit simulates the future laboratory performance of the various configurations of the laboratory system. The simulated future laboratory performance and actual laboratory performance of the various configurations of the laboratory system are displayed to the laboratory operator on the dashboard display, Computer implementation methods, including those mentioned above.

13. Based on the simulated future laboratory performance of the various configurations, the laboratory operator selects one of the various configurations of the laboratory system. Reconfiguring the laboratory system based on the selected configuration, The computer implementation method according to claim 12, further comprising:

14. The computer implementation method according to claim 12 or 13, further comprising optimizing the future laboratory performance of the various configurations based on laboratory operator preferences, laboratory constraints, real-time laboratory input data, and order data in the optimization module.

15. A laboratory system for predicting future laboratory performance, Multiple laboratory instruments configured to perform tests on laboratory test samples, Laboratory middleware that is communicatively connected to the aforementioned multiple laboratory devices, A dashboard display configured to display performance information of the aforementioned laboratory system, A control unit including an optimization module and a simulation module, connected to the plurality of laboratory equipment and the laboratory middleware via a network communication connection, The control unit is equipped with, The laboratory operator provides the optimization module with the laboratory operator's preferences and laboratory constraints. Real-time laboratory input data from the aforementioned multiple laboratory devices is continuously provided to the laboratory middleware. The real-time laboratory input data and order data are continuously provided from the laboratory middleware to the optimization module. In the optimization module, the laboratory configuration is optimized based on the preferences of the laboratory operator, the laboratory constraints, the real-time laboratory input data, and the order data. Based on the optimized laboratory configuration provided by the optimization module and the real-time laboratory input data and order data, the simulation module simulates the future laboratory performance of the laboratory system. The simulated future laboratory performance and the actual laboratory performance are displayed to the laboratory operator on the dashboard display. It is structured in such a way. Laboratory system.

Images