Supply prediction system and method

By integrating the RTSM system in the clinical trial supply prediction system, using API to automate data acquisition and status comparison, the problems of inaccurate and inefficient supply prediction in the prior art are solved, and more accurate and efficient drug supply management is achieved.

CN118886418APending Publication Date: 2024-11-014G CLINICAL LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410905473.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2017-09-26
Filing Date
2018-09-26
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

Existing clinical trial supply prediction systems have defects in accuracy and efficiency, often resulting in incorrect supply decisions due to algorithm differences from RTSM systems, resulting in waste or out of stock of drugs, and requires frequent manual mapping of research models, which is inefficient.

Method used

Through a computer-implemented method, using the server to receive clinical trial parameters, calculate supply demand and buffer quantity, generate supply plans, and integrate with the RTSM system to automatically obtain and compare trial status through the API, adjust supply plans in real time, and reduce manual intervention and Data mapping error.

Benefits of technology

Improves the accuracy and efficiency of supply forecasts, reduces the risks of drug waste and out of stock, achieves more flexible and robust supply planning management, and reduces 20% of excess drug coverage and supply chain inefficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886418A_ABST
    Figure CN118886418A_ABST
Patent Text Reader

Abstract

Provisioning prediction systems and methods are disclosed. An embodiment of a computer-implemented method may include receiving, by a server from a user, one or more electronic files containing parameters of a clinical trial, the parameters including a number of patients, a plurality of sites, and one or more confidence values; calculating, by the server, a respective demand profile for each of the plurality of sites according to the number of patients; calculating, by the server, a number of buffers for each of the plurality of sites according to the one or more confidence values; calculating, by the server, a supply plan of the clinical trials according to the demand profile and the number of buffers; and sending, by the server, the provisioning plan to the user.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application is a divisional application of Chinese Patent Application No. 201880069864.5, which is an international application number PCT / US2018 / 052952 filed on September 26, 2018 and an invention name of “System and Method for Demand and Supply Forecasting for Clinical Trials”. Technical Field

[0002] The presently disclosed embodiments relate to clinical trial supply and management, and more particularly, to systems and methods for demand and supply forecasting for clinical trials. Background Art

[0003] Over the past decade, systems have been developed for managing the supply of drugs in clinical trials, and these systems are now heavily relied upon by many pharmaceutical companies for production planning, cost optimization, management of patient recruitment activities, etc. For example, known systems include custom or template Excel spreadsheets, forecasting systems based on averages, and systems using Monte-Carlo simulations, which are usually the most accurate. Summary of the invention

[0004] The presently disclosed embodiments relate to systems and methods for demand and supply forecasting for clinical trials. An embodiment of a computer-implemented method may include: receiving, by a server, one or more electronic files containing parameters of a clinical trial from a user, the parameters including a number of patients, a plurality of sites, and one or more confidence values; calculating, by the server, a corresponding demand profile for each of the plurality of sites based on the number of patients; calculating, by the server, a buffer quantity for each of the plurality of sites based on the one or more confidence values; calculating, by the server, a supply plan for the clinical trial based on the demand profile and the buffer quantity; and sending, by the server, the supply plan to the user.

[0005] An embodiment of a computer-implemented method may include: receiving, by a server, one or more electronic files containing parameters of a clinical trial from a user, the parameters including the number of patients, multiple sites, and one or more confidence values; calculating, by the server, a supply plan for the clinical trial based on the parameters; sending, by the server, the supply plan to the user; establishing electronic communication with a computerized randomization and trial supply management (RTSM) system that operates the clinical trial after sending the supply plan to the user; outputting a command to the RTSM system via an application programming interface (API) associated with the RTSM system; receiving data from the RTSM system in response to the command; determining a status of the clinical trial based on the data received from the RTSM system; comparing the status of the clinical trial with the supply plan; determining that the clinical trial does not comply with the supply plan; and automatically sending an electronic notification to the user, the electronic notification including an indication that the clinical trial does not comply with the supply plan.

[0006] An embodiment of a computer-implemented method may include: receiving, by a server, one or more electronic files containing parameters of a clinical trial from a user, the parameters including the number of patients, multiple sites, and one or more confidence values, wherein the one or more electronic files include an electronic spreadsheet file and one or more text files; converting data in the electronic spreadsheet file into one or more electronic text-based tables; inserting the one or more electronic text-based tables into one or more text files to create one or more supplementary text files; performing natural language processing on the one or more text files to determine the parameters of the clinical trial; calculating, by the server, a supply plan for the clinical trial based on the parameters of the clinical trial; and sending, by the server, the supply plan to the user.

[0007] An embodiment of a non-transitory computer-readable medium may store instructions that, when executed by a processor, cause the processor to: receive one or more electronic files containing parameters of a clinical trial from a user, the parameters including a number of patients, a plurality of sites, and one or more confidence values; calculate a corresponding demand profile for each of the plurality of sites based on the number of patients; calculate a buffer quantity for each of the plurality of sites based on the one or more confidence values; calculate, by a server, a supply plan for the clinical trial based on the demand profile and the buffer quantity; and send the supply plan to the user.

[0008] The present disclosure provides a computer-implemented method, which includes: predicting a supply plan for a clinical trial by a computer, including: obtaining a plurality of parameters of the clinical trial by the computer, the parameters involving a plurality of patients, a plurality of sites, and a plurality of actions associated with the clinical trial; determining a corresponding statistical distribution of demand for each patient included in the plurality of patients based on a plurality of actions associated with the clinical trial by the computer; determining a corresponding supply demand profile for each site included in the plurality of sites, wherein the supply demand profiles of the plurality of sites are determined based on the statistical distribution of demand of the plurality of patients; and calculating the supply plan of the clinical trial by the computer according to the supply demand profile; re-forecasting the supply plan of the clinical trial by the computer based on variability in the respective treatment processes of the plurality of patients; and transmitting the re-forecasted supply plan to a user by a server.

[0009] The present disclosure provides a supply forecasting system, the system comprising: a processor; and a computer-readable medium storing instructions, the instructions, when executed by the processor, causing the system to perform the above-mentioned computer-implemented method.

[0010] The present disclosure provides a computer-implemented method, which includes: predicting a supply plan for a clinical trial by a computer, including: obtaining a plurality of parameters of the clinical trial by the computer, the parameters involving a plurality of patients, a plurality of sites, and a plurality of actions associated with the clinical trial; determining a corresponding statistical distribution of demand for each patient included in the plurality of patients based on a plurality of actions associated with the clinical trial by the computer; determining a corresponding supply demand profile for each site included in the plurality of sites, wherein the supply demand profiles of the plurality of sites are determined based on the statistical distribution of demand of the plurality of patients; and calculating the supply plan of the clinical trial according to the supply demand profile by the computer; re-predicting the supply plan of the clinical trial by the computer when a specific mark is reached; and transmitting the re-predicted supply plan to a user by a server.

[0011] The present disclosure provides a supply forecasting system, the system comprising: a processor; and a computer-readable medium storing instructions, the instructions, when executed by the processor, causing the system to perform the above-mentioned computer-implemented method. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a diagrammatic view of an example system for predicting and managing drug trials.

[0013] Figure 2 is a flow chart illustrating an example method of operating a trial supply forecasting system.

[0014] Figure 3A and Figure 3B is a sample graphical display of a sample pilot supply plan.

[0015] Figure 4 is a flow chart illustrating an example method of determining parameters for a proposed drug trial.

[0016] Figure 5 is a diagrammatic view of an example electronic specification interpreter that applies natural language processing.

[0017] Figure 6 is a flow chart illustrating an example method of determining a trial supply forecast.

[0018] Figure 7 is a flow chart illustrating an example method of monitoring a trial for supply forecasts regarding the trial.

[0019] Figure 8 is a diagrammatic view of an illustrative computing system that includes a general computing system environment. DETAILED DESCRIPTION

[0020] RTSM systems can predict the need for clinical supplies at research sites where patients are participating in clinical trials, pre-seed those sites with appropriate medications for distribution, and send additional medications to those sites when needed. This functionality is often referred to as a "resupply algorithm." The resupply algorithm can be controlled by parameters such as minimum level or safety stock, maximum level or resupply level, short window, look-ahead window, etc. The management of these parameters—calculating expected parameter values ​​around the world in a given clinical trial, and then tracking and updating those values—is a burden for pharmaceutical companies.

[0021] Over the past decade, forecasting tools have been developed to help plan supply needs in advance and continuously adjust resupply parameters in clinical trials (and understand what is coming). Existing forecasting systems have many shortcomings. Some of these forecasting tools use simulation techniques as the basis of their forecasting capabilities. Since the forecasting tools need to approximate the performance of the RTSM resupply algorithm they want to predict, the forecasting tools usually need to have the same or similar parameters as many different RTSM offerings, and they almost never accurately match the RTSM resupply algorithm. Therefore, using known forecasting systems, key supply decisions may be made based on incorrect information (e.g., forecasts that do not match actual trial use due to algorithmic differences between the forecasting system and the management system), which may lead to wasteful oversupply or out-of-stock. In addition, since RTSM and clinical trial supply management systems are usually different systems, it is usually not frequently (every 1 to 6 months) to predict the later stages of the trial when the trial is ongoing, and users must manually map between the research models in each of the two systems. Reports in current systems are strict and data utilization can usually only be further performed in external systems such as Excel. Most systems are not validated or compliant with CFR Part 11 in the sense that clinical trial software often further creates potential mismatches and poor recommendations for critical supply decisions.

[0022] A forecasting system should typically consider many interrelated variables to model the supply required throughout a drug trial. For example, the patient's visit schedule and the drug's distribution schedule must be considered, including any changes to the visit schedule of the protocol that the patient may follow during the study. The distribution of patients in time and space should also be considered, including when and where patients are enrolled and how quickly sites will be activated. Forecasts should also consider the logistics of the supply network, including issues such as how inventory arrives at the site, how frequently inventory is shipped, and how long it takes for inventory to arrive at the trial site. Inventory constraints should also be considered, including country-specific constraints (e.g., labeling requirements), per-unit production costs and values, shelf life, and expiration dates of batches.

[0023] Resupply algorithms (and predictors) typically deal with two types of demand: predictable demand and unpredictable demand. Predictable demand includes demand that will be consumed by existing known patients at any time in the future, where the treatment type and dose level are known in advance. Unpredictable demand includes requirements that will be consumed by unknown (non-existent) patients ("irrelevant unpredictable demand"), known patients who have not yet received the treatment assigned by randomization, or known patients who received the assigned general course of treatment, but the study design itself includes variability in future doses ("relevant unpredictable demand").

[0024] Capable RTSM forecasters will usually handle predictable demand appropriately, but only the most robust and powerful forecasters can handle unpredictable demand whose nature is unknown in advance. The simulator can produce a statistically realistic upper bound on unpredictable demand within some time window, the result of which can be used to create safety stock or floor-ceiling buffers (stock that is placed at the site in advance without knowing whether it will be used). Such buffers and settings are usually set manually in a labor-intensive process.

[0025] For RTSM, two time frames are important. The first time frame is sometimes referred to as a "short window", and is usually equal to or slightly greater than the delivery lead time from the supply warehouse to the site in question. For example, a buffer or safety stock can be set to meet all or almost all expected needs within this time window, thus preventing out-of-stock or missed patient distribution. Since it may not be expected that supplies are delivered whenever the drug is consumed, a second window (sometimes referred to as a "pre-emptive window" or "long window") is needed, which tells the system how long the inventory should be kept before shipping again. For example, the long window setting can be 30 days.

[0026] In some cases, a good prediction tool can be kept in sync with a good RTSM system (via regular data feeds) and can provide ongoing recommendations to the sponsor company to set parameter values ​​as described above. In other cases, however, this does not happen. The complexity of the many aspects of this process, all focused on a deep understanding of the resupply algorithm and its parameters, overwhelms many clinical supply professionals (or others responsible for this function).

[0027] The supply forecasting system according to the present disclosure may improve some or all of the above-mentioned deficiencies.

[0028] Referring now to the drawings, in which like reference numerals designate like or similar features throughout the various views, for example, Figure 11 is a diagrammatic view of an example system 10 for forecasting and managing clinical trials, such as randomized drug trials. The system 10 may include a supply forecasting system 12 and a randomization and trial supply management (RTSM) system 14, one or both of which may be connected to a plurality of user computing devices 16 (in Figure 1 One of which is shown in the figure) for electronic communication.

[0029] Typically, the prediction system 12 and the RTSM system 14 may be involved in different aspects of planning and management for a drug trial. As will be described in more detail below, the RTSM system 14 may typically guide and manage the trial, while the prediction system 12 may generate a trial plan before the trial stage where complete trial information is available or not yet available.

[0030] In an embodiment, the RTSM system 14 may include one or more computing devices and may perform many operations for organizing and choreographing a drug trial, such as patient randomization, blinding, drug distribution, and automatic drug resupply. The RTSM system 14 may communicate electronically with one or more user computing devices 16 to receive input from a user (e.g., parameters of a trial) and provide output to the user (e.g., an order for one or more drugs, the identity of the patients participating in the trial, relevant information about the trial site, etc.).

[0031] The RTSM system 14 can be configured to communicate and exchange information with a variety of different user types (i.e., one or more user computing devices related to such user types communicate). For example, in a given trial, the RTSM system 14 can provide an input / output interface for a clinical trial sponsor 18 (e.g., a pharmaceutical company). In an embodiment, the trial sponsor 18 can input complete parameters for a clinical trial or a phase of a clinical trial for the RTSM system 14. Such a complete parameter set can include, for example, patient visits or other actions about patients, batches and operations on batches, inventory at site or warehouse level and operations about inventory, shipping and operations about shipping, temperature excursions and their management, the return of distributed or undistributed drugs and related approvals and parameters, the destruction status of inventory, actions about alarms or notifications, the addition and parameterization of sites and warehouses, countries, prediction parameters such as the settings of confidence dials and long window dials, the settings of site group registration rates, the settings of users and their access rights, the settings of peers, the loading of test kits and randomization lists, the unblinding of patients or test kits. The RTSM system 14 can then determine the resupply actions that may have to be taken and output them to the trial sponsor. As will be described below, the RTSM system 14 can also track and record the status of the trial based on data from one or more warehouses, sites, doctors, and patients, and can make this information available to the trial sponsor.

[0032] For example, the RTSM system 14 can be in electronic communication with one or more trial sites 20, such as hospitals or clinics. For example, the RTSM system 14 can output instructions, such as dispensing instructions for a particular patient, to the trial site 20. The RTSM system 14 can also receive data, such as patient information, dispensing records, etc., from the trial site 20, so that the RTSM system 14 has data indicating which patients involved in the trial took which drugs and which sites, and at what time.

[0033] The RTSM system 14 may also communicate with one or more distribution facilities 22, such as warehouses, depots, or other facilities involved in distributing batches of drugs and placebos involved in the trial to the trial sites 20. For example, the RTSM system 14 may issue shipping instructions to such facilities 22. In an embodiment, such shipping instructions may be automatically generated and / or transmitted by the RTSM system 14 based on the supply plan. The RTSM system may also receive data such as shipping records and inventory information from such facilities 22, so that the RTSM system 14 has data indicating the distribution inventory and remaining inventory of the drugs involved in the trial and the location of these inventories.

[0034] One or more doctors 24 may also be in electronic communication with the RTSM system 14. The RTSM system 14 may output information about the drugs involved in the trial and information about the trial to these doctors 24 so that the doctors can notify patients about the trial as appropriate. The RTSM system 14 may receive enrollment information (e.g., the number of patients the doctor recommended for the trial, characteristics of those patients, specific patients who have been enrolled, etc.) from these doctors so that the RTSM system 14 has data indicating the enrollment volume and characteristics of the enrolled patients.

[0035] The supply forecasting system 12 may include a processor 28 and a non-transitory computer-readable memory 30 including instructions that, when executed by the processor 28, cause the processor 28 to perform one or more methods, algorithms, processes, etc. of the present disclosure. The memory 30 may store one or more modules in the form of executable instructions (e.g., software) for execution by the processor 28. Example modules are described below.

[0036] In an embodiment, the memory 30 may store a supply planning module 32. Based on the supply planning module 32, the supply forecasting system 12 may typically generate a plan regarding the supply of the drug in the trial and the placebo for the trial before complete trial information (or trial phase) is available. The supply forecasting system 12 may then output the supply plan regarding the trial to the trial sponsor 18 so that the trial sponsor 18 can correctly budget for the trial, obtain appropriate sites and logistics channels for the trial, etc. For such communications, the supply forecasting system 12 may electronically communicate with one or more user computing devices 16, including a user computing device 16 associated with the trial sponsor 18.

[0037] In an embodiment, the memory 30 may also store a specification interpretation module 34. A user (e.g., via a user computing device, which may be associated with a trial initiator, as described above) may submit information indicating trial parameters, and the supply forecasting system 12 may receive the information indicating the trial parameters. The specification interpretation module 34 may process and parse the received information to extract and determine the trial parameters. Based on the trial parameters received from the user, the supply planning module 32 may generate a supply plan.

[0038] The forecasting system 12 may provide an electronic user interface for use by a trial sponsor, one or more trial sites, one or more warehouses, one or more physicians, and / or one or more patients. For example, in an embodiment, the forecasting system 12 may provide an electronic user interface including one or more dials to enable a user to set certain constraints on a supply plan to be calculated by the forecasting system by adjusting the dials. As discussed below, the supply forecasting system 12 may receive user input based on user actuation of such a dial or other input device.

[0039] In some embodiments, the forecasting system 12 may receive from a user a confidence level at which, for example, the total demand (e.g., predictable, relevant unpredictable, irrelevant unpredictable, etc.) that is expected should be supported. In some embodiments, the user may present a variety of different confidence levels, and the forecasting system may calculate a supply plan forecast for each of those confidence levels. In embodiments, the forecasting system may receive from a user a number of confidence levels for different trial parameters, e.g., a first confidence level for total demand, a second confidence level for relevant unpredictable demand, etc.

[0040] The forecasting system may also receive one or more time lengths from the user for the study. For example, the user may provide the length of the trial, the length of one or more specific phases of the trial, etc. In some embodiments, the user may present a variety of different time lengths, and the forecasting system may calculate a supply plan forecast for each of those time lengths.

[0041] The supply forecasting system 12 may also be in electronic communication with the RTSM system 14. During the trial, the supply forecasting system 12 may retrieve data related to the trial from the RTSM system 14. For such information retrieval, the supply forecasting system 12 may communicate with the RTSM system 14 via an application programming interface (API) 36 of the RTSM system 14. Based on the plan comparison module 36, the supply forecasting system 12 may compare the retrieved information about the trial status with the forecast supply plan; and when the trial status deviates significantly from the forecast supply plan, the supply forecasting system 12 may generate an alert to the trial initiator.

[0042] In an embodiment, one or both of the RTSM system 14 and the supply forecasting system 12 may be implemented on a Software as a Service (SaaS) basis. Thus, the supply forecasting system and / or the RTSM system 14 may be implemented in one or more servers, databases, etc. that are electronically accessible to users via the Internet. Additionally or alternatively, one or both of the supply forecasting system 12 and the RTSM system 14 or one or more aspects or functions of the supply forecasting system 12 and the RTSM system 14 may be implemented in a local copy stored, for example, on a local server of a trial sponsor or on a user computing device associated with a trial sponsor, trial site, warehouse, etc.

[0043] In embodiments, although the RTSM system 14 and the supply forecasting system 12 are shown and described as separate systems, the RTSM system 14 and the supply forecasting system 12 or some functionality thereof may be implemented in a single system or common computing resources.

[0044] The supply forecasting system according to one or more aspects of the present disclosure can improve the known supply forecasting methods and systems. First, known supply forecasting systems are usually used to calculate comprehensive forecasts about the entire experiment. Such forecasting systems usually require a lot of information about the experiment in order to achieve a comprehensive plan. Therefore, when relatively little information about the experiment can be obtained, known forecasting systems may not provide a lot of utility in the early stages of the experiment planning process, and a lot of assumptions must be made to use these systems. In contrast, in an embodiment, the supply forecasting system according to the present disclosure can be configured to calculate the supply plan or a part thereof based on any information available to the user, and the supply forecasting system according to the present disclosure can also be configured to: determine and notify the user of specific signs (e.g., dates, availability of certain information, etc.) that may trigger the recalculation of the supply plan or the calculation of other aspects of the supply plan, so that the user can make changes to the plan during the experiment without expensive experiment delays. As known, the supply forecasting system according to the present disclosure can provide users with a method for conveying different levels of information in a flexible manner. Therefore, the supply forecasting system according to the present disclosure can provide more flexible and robust forecasts for supply planning, thereby enabling improved logistics when performing drug trials, and the supply forecasting system according to the present disclosure can enable more accurate forecasts of drug demand, avoiding expensive waste, expected stockouts or other problematic situations. For example, the supply forecasting system according to the present disclosure can reduce excess (drugs required for trials that exceed actual patient demand to cover uncertainty and supply chain inefficiencies) by 20%.

[0045] Secondly, known forecasting systems are typically separate from the RTSM system and therefore must obtain information from the RTSM system through inefficient file transfers, which often require manual user intervention and may include the exchange of more data than necessary, both of which may be less efficient than desired and risk incorrect mapping between data from the two systems. In contrast, in an embodiment, a supply forecasting system according to the present disclosure may be integrated with the RTSM system via an API exposed by the RTSM system. Therefore, instead of inefficient file transfers, the supply forecasting system may issue requests and commands to the RTSM system via the API to collect specific information required by the forecasting system without manual intervention, thereby improving the functionality and efficiency of the computer-implemented forecasting system. Data mapping may also be largely automated and become less error-prone than manual intervention.

[0046] Third, as described above, known supply forecasting systems typically require specific types of information to generate a plan. Known forecasting systems also typically require such information in a specific, single form. In contrast, in embodiments, a forecasting system according to the present disclosure can accept aspects of the test information in multiple formats, such as one or more text files and one or more spreadsheets, and can process and parse the submitted information to extract and determine the test parameters upon which the supply plan is based.

[0047] Figure 2 is a flow chart illustrating an example method 40 of operating a test supply forecasting system. For example, the method 40 or one or more aspects of the method may be performed by a system such as Figure 1 The supply forecasting system 12 is executed by the supply forecasting system. Figure 2 The method 40 includes testing various relatively high-level functions of the supply forecasting system. Figure 4 , Figure 5 , Figure 6 and Figure 7 Describe some of these functions in detail.

[0048] Continue to refer to Figure 2, method 40 may include step 42, which includes receiving one or more specification files from a user. The user may be, for example, a trial sponsor (e.g., a pharmaceutical company). The specification file may include one or more file types. For example, in an embodiment, the specification file may include one or more text files and one or more spreadsheet files. In an embodiment, the text may be entered in a free or natural form rather than in response to a structured prompt. The specification file may include information about the proposed drug trial available to the sponsor, such as the start and duration, the number of patients required, the proportion of patients expected to participate in the study, whether screening is performed and the proportion of such screening failures, a description of the treatment of the patient, in particular any events in which the distribution of the drug may occur or the patient may reduce or change the dose, and how these events are related to each other in terms of time and probability, the number of sites, the number of countries listed, the number of site groups, the number of regions, the number of warehouses, a description of the supply network including supply lines and delivery times, a description of different drugs to be tested, different doses of the drug to be tested, drug supply constraints such as expiration, remaining shelf life, maximum batch or maximum release frequency, etc.

[0049] The method 40 may also include a step 44, which includes converting and merging the specification file to extract or otherwise determine the test parameters included in the specification file. Figure 4 and Figure 5 An example method for performing step 44 is described below.

[0050] The method 40 may also include a step 46, which includes generating a test supply plan based on the test parameters determined from the specification file. Figure 5 4 is used to describe an example method for performing step 46. One or more trial provisioning plans may be determined at step 46. For example, multiple trial provisioning plans may be determined for different confidence levels associated with the duration of the trial, or different confidence levels associated with the number of patients required for the trial, or different numbers of doses to be tested in the trial, etc.

[0051] The method 40 may also include a step 48 that includes generating a trial supply plan and one or more graphical representations of inputs used to calculate the trial supply plan. Figure 3A and Figure 3B 60, 70 are example graphical representations of a trial supply plan or inputs used to calculate the trial supply plan. Figure 3A , the first graphical representation 60 may include a plurality of nodes 62 (in Figure 3A621, 622, 623 are shown in the figure; for clarity, not all nodes 62 are shown), where each node 62 represents an action in the trial represented by the graphical representation 60, such as randomization of the trial population, distribution of the drug, etc. The graphical representation can also include one or more branches 64 extending from each node. Each branch 64 can show the result of the action of the node 62 from which the branch 64 extends. For example, three branches 641, 642, 643 can extend from an initial node 621 representing randomization of a patient population, where the first branch 641 indicates that fifty percent (50%) of the randomized patient population will be assigned to the ABC portion of the trial, the second branch 642 indicates that twenty-five percent (25%) of the patient population will be included in the placebo portion of the trial, and the third branch 643 indicates that twenty-five percent (25%) of the patient population will be included in the XYZ portion of the trial.

[0052] Reference Figure 3B , the second graphical representation 70 may include a plurality of nodes 72 (in Figure 3B , three nodes 721, 722, 723 are shown; for clarity, not all nodes 72 are shown), wherein each node 72 represents a location or set of locations in the trial, such as a warehouse, a trial site, or other facilities involved. For example, the first node 721 represents a warehouse for the United States (which can also serve Canada), the second node 722 represents the U.S. trial population, and the third node 723 represents a low-dose U.S. trial population. The graphical representation can also include one or more branches 74 extending from each node 72. Each branch 74 can show a distribution channel for a sub-portion of the drug included in the node 72 from which the branch 74 extends. For example, three branches 741, 742, 743 can extend from the U.S. trial population node 722 representing a patient population, wherein the first branch 741 indicates that the supply portion specified for the U.S. trial population will reach the low-dose U.S. trial population 723, the second branch 742 indicates that the supply portion specified for the U.S. trial population will reach the medium-dose U.S. trial population, and the third branch 743 indicates that the supply portion specified for the U.S. trial population will reach the high-dose U.S. trial population.

[0053] Refer again Figure 2, method 40 may also include step 50, which includes sending the trial supply plan to the user. Sending the supply plan to the user may include: sending data including one or more graphical representations of the supply plan to the user computing device for display on the user computing device. Sending the supply plan to the user may additionally or alternatively include: sending a tabular or text form of the supply plan and / or some other form of the supply plan or one or more parts thereof to the user. The sending may, for example, be in the form of a hosted web page delivered to the user computing device. Additionally or alternatively, the sending may be in the form of an email or other electronic form, such as a downloadable electronic file.

[0054] The method 40 may also include step 52, which includes: after the trial begins, monitoring the trial status over time. Monitoring the trial status may include: periodically and automatically retrieving data related to the trial from the RTSM system and comparing the data with the trial plan. Any or all aspects of the trial may be compared to the supply plan forecast in step 52. For example, the inventory of the drug being tested at each test site may be compared to the supply plan forecast to determine whether the ordering schedule should or must be changed or the distribution schedule should or must be changed to ensure that each test site has sufficient inventory to provide to its test patients.

[0055] The method 40 may further include step 54, which includes: alerting the user when the test status deviates from the test supply plan. Figure 7 Examples and further details of steps 52 and 54 are described below.

[0056] Figure 4 80 is a flow chart illustrating an example method 80 for determining parameters for a proposed drug trial. For example, the method 80 or one or more aspects of the method 80 may be performed by, for example, Figure 1 The supply forecasting system 12 is executed by the supply forecasting system.

[0057] Method 80 may include step 82, which includes: receiving a spreadsheet file and one or more text files from a user. The files may include information about the research to be conducted that is available to the user at that time. The text file may be, for example, an HTML file. For example, the spreadsheet and text file may be received via files uploaded through a website provided by the supply forecasting system. In an embodiment, the supply forecasting system may provide an interface in which a user may enter free-form text to describe the proposed research (the entered free-form text may be or may become one or more text files of step 82), and further upload one or more spreadsheets through the interface.

[0058] Method 80 may also include step 84, which includes converting the electronic form into one or more text-based forms. In an embodiment, the electronic form may be converted into, for example, one or more HTML-based forms or into any format that provides a text-based file.

[0059] Method 80 may also include step 86, which includes inserting a text-based table into one or more text files, and step 88, which includes performing natural language processing on the one or more text files to determine the test parameters. Figure 5 An example of natural language processing that may be performed at step 88 is described below. Further details regarding natural language processing are provided in U.S. Patent 20170154168, entitled “Generating RTSM Systems for Clinical Trials,” assigned by inventor Edward A. Tourtellotte to 4G Clinical, LLC, which is hereby incorporated by reference in its entirety. By using natural language processing (NLP), users can describe their trials in plain English, independent of the level of detail of available information, and the prediction system can determine the available details of the trial for further processing.

[0060] Figure 5 is a diagrammatic view of an example electronic specification interpreter 34 that applies natural language processing. In an embodiment, the specification interpreter 34 may perform Figure 4 In the method 80, specifically, the specification interpreter 34 may perform step 88. The specification interpreter 34 may include a main interpreter 92, one or more special interpreters 94, one or more information extractors 96, one or more special natural language processing (NLP) tools 98, and one or more core NLP libraries 100. In an embodiment, the specification interpreter 34 may also include additional components.

[0061] The core NLP library such as core NLP library 100 may include information of natural language (e.g., English), such as vocabulary and grammar, corpus, tagger, tokenizer, stem analyzer, lemmatizer, learning algorithm, etc. The specification interpreter 34 may use the core NLP library 100 to check the specification input by the specification writer. For example, the specification interpreter 34 may rely on the core NLP library 100 to identify words and stems, mark incorrect spellings, analyze grammar and meaning, detect logical operations and data definitions and / or suggest alternative terms. In some cases, the core NLP library 100 may be provided by a third party, such as from some programming languages ​​(e.g., Java or Python) development toolkits (e.g., natural language toolkits or NLTK) provide.

[0062] Special NLP tools such as special NLP tools 98 can provide system-specific extensions to the core NLP library 100. For example, the special NLP tool 98 can include additional information such as words, phrases, terms, grammar, reserved words / phrases, keywords and operators that can be commonly used in the context of certain fields (e.g., clinical trials). The special NLP tool 98 can also include advanced language analysis functions such as tokenization, stemming, grammar, collocation, language corpus, sentence structure and meaning analysis and other natural language processing features. The special NLP tool 98 can also include artificial neural networks.

[0063] The specification interpreter 34 can also use a special NLP tool 98 to check the specification input by the specification writer. For example, the specification interpreter 34 can rely on a special NLP tool 98 to identify system-specific words, mark incorrect spellings and / or suggest alternative terms. The special NLP tool 98 can be provided by a third party or developed internally. Information extractors such as information extractors 96 can extract certain information from the specification. A type of information extracted can include a matrix (for example, information constructed in a tabular manner). When organizing data in a matrix form is more convenient than organizing data in a natural language form, a matrix can be used in specification development. For example, a matrix can be used to define a patient's visit schedule and associated dosage regimens or other visit events; a matrix can also be used to define a patient's test kit type, a supply chain relationship and delivery time, or any other data naturally defined in a matrix.

[0064] Another type of information extracted may include certain patterns of sentences, such as definitions. Definitions may be structured, for example, as [subject of definition][verb proposal][item or list of items], but the structure may be different or made more flexible to enable the use of a free English style in writing and extraction of relevant information. Other patterns of sentences may be defined as needed.

[0065] A master interpreter 92 may receive a test specification. The master interpreter 92 may perform a top-level analysis of the specification and may organize the interpretation in a logical order of subject matter. A subject matter may include one or more defined test headings that may be throughout one or more sections of the specification document. A particular subject matter of an interpretation may correspond to a dedicated interpreter 94 that is configured to analyze the entire specification document (in one or more sections) for information related to the particular subject matter. The master interpreter 92 may call different dedicated interpreters through the specification to handle different subjects of the test.

[0066] The dedicated interpreter 94 may include a research level interpreter, a randomization interpreter, an action interpreter, a drug supply interpreter, a manufacturing interpreter, a registration interpreter or other required interpreters. The research level interpreter may explain the high-level information in the specification. For example, the high-level information may include some research level information, such as the total number of patients expected to be screened and randomized, randomization schemes and methods, and other required parameters. The randomization interpreter may explain the randomization information in the specification. The action interpreter may explain the event action information in the specification. For example, the event action may include information such as what drug distribution may occur under the background of each patient visit. The drug supply interpreter may explain the drug supply information in the specification. For example, the drug supply information may include supply networks, transportation rules, distribution kit information, etc. The manufacturing interpreter may explain various production steps and intermediate manufacturing delivery times to convert the investigation material into a kit that can be distributed to the patient. The registration interpreter may explain the rate at which the patient enters the study at various levels (e.g., research level, regional level, etc.). The list of dedicated interpreters is not exhaustive. Other dedicated interpreters may be added when necessary.

[0067] In some cases, the main interpreter 92 can be an entry point into the specification interpreter 34. For example, the main interpreter 92 can receive the specification and divide the interpretation into different parts or topics. The main interpreter 92 can then call the appropriate dedicated interpreter 94 to analyze each part or topic. Each dedicated interpreter 94 can call one or more information extractors 96 as needed to extract information such as matrices and definitions from each part or topic of the specification. Each information extractor 96 can call one or more dedicated NLP tools 98 as needed. Each dedicated NLP tool 98 can then call one or more core NLP libraries 100 to help process each part or topic of the specification.

[0068] The output result of the core NLP library 100 may be returned to the dedicated NLP tool 98 that calls the core NLP library 100. The output result of the dedicated NLP tool 98 may be returned to the information extractor 96 that calls the dedicated NLP library 100. The output result of the information extractor 96 may be returned to the dedicated interpreter 94 that calls the information extractor 96. The output result of the dedicated interpreter 94 may be returned to the main interpreter 92 that calls the dedicated interpreter 94.

[0069] In some embodiments, the output of the specification interpreter 34 may include basic data structures and driving logic. The basic data structures and driving logic may include logical containers and other necessary or related structures. For example, the data structure may hold: planned patient visits and dosage information; data driver information (e.g., BMI for dosage); data related to supply chain organization, supply shipments, and / or patient kits; or any other data that is expected to be collected or acted upon during the trial. The logical container may hold specific processing instructions for the prediction system to comply with the specification, as necessary.

[0070] Figure 6 is a flow chart illustrating an example method 110 for determining a trial supply forecast. The method 110 or one or more aspects of the method 110 may be performed by, for example, Figure 1 The supply forecasting system 12 is executed by the supply forecasting system.

[0071] Method 110 may include step 112, which includes: calculating a statistical distribution of demand for each of a plurality of hypothetical patients. Demand may include the amount of drug, drug dose, and / or placebo required at one or more time points during the patient's treatment. The distribution of demand may be, for example, a discrete distribution driven by a randomization rate. In other embodiments, other statistical distribution types may be used to determine patient demand. The result of the patient demand calculation step may be a time series for which each point will expand the probability of demand to a certain amount cumulatively or within a given time period. For example, after 1 month, the probability that the cumulative demand of a new patient using a KT-12mg kit may be 0 is 40%; the probability that the cumulative demand of a new patient using a KT-12mg kit may be 1 is 30%; the probability that the cumulative demand of a new patient using a KT-12mg kit may be 2 is 25%; the probability that the cumulative demand of a new patient using a KT-12mg kit may be 3 is 5%.

[0072] Method 110 may also include step 114, which includes calculating the registration pattern across sites. In an embodiment, the site registration pattern may be calculated based on Monte Carlo simulation. The result of the simulated registration step may be the most likely set of numbers of patients that will be registered at each of the multiple test sites.

[0073] The method 110 may also include step 116, which includes calculating a supply demand profile for each site based on the simulated registration pattern and the demand profile of each patient. That is, assuming a patient accrual rate that can be represented as a Poisson distribution as estimated above, and based on the patient-level distribution, step 116 may include calculating a composite statistical distribution of demand for all patients who are susceptible to registration at each particular site.

[0074] The method 110 may also include step 118, which includes calculating a supply buffer for each site. In an embodiment, the supply buffer may be calculated based on user input. For example, as described above, the user may actuate one or more dials to set a confidence rating. The lower the user sets the confidence rating, the higher the supply buffer may be set, and vice versa.

[0075] The method 110 may also include step 120, which includes calculating site group level demand based on the site demand profile and the supply buffer. The site group level demand may include, for example, demand for each supply type (e.g., one or more drug doses and placebo) at each testing site. In an embodiment, a site-specific buffer may be added to the demand calculated for each site to determine the group level demand.

[0076] Method 110 may also include: step 122, which includes calculating regional demand based on site group demand; step 124, which includes calculating warehouse demand based on regional demand; and step 126, which calculates total supply demand based on warehouse demand. In an embodiment, steps 122, 124, and 126 may include simple arithmetic and statistical calculations, such as adding the demand of each site group in a region to determine the total demand for the region, adding the demand of each region served by a particular warehouse to determine the total demand for the warehouse, etc., whether it is an expected value or a statistical distribution.

[0077] The method 110 may also include step 128, which includes determining appropriate manufacturing / packaging timing and quantity during the study and triggering of a re-forecast for calculating the supply plan. This may be one of a minimum frequency, calculation based on expiration date, user-provided external constraints such as drug availability, or a combination of a minimum frequency, calculation based on expiration date, user-provided external constraints such as drug availability, and may rely on operations research techniques such as constraint programming, neural networks, mixed integer programming, etc.

[0078] Figure 71 is a flow chart showing an example method 130 for monitoring a trial with respect to a supply forecast for the trial. For example, the method or one or more aspects of the method may be performed by, for example, Figure 1 The supply forecasting system 12 is executed by the supply forecasting system.

[0079] Method 130 may include: step 132, which includes (e.g., electronically) connecting to the RTSM system; step 134, which includes issuing one or more commands to the RTSM system via an API exposed by the RTSM system. The command can request a specific data type and can eliminate the need for the RTSM system to exchange entire files with the prediction system, thereby improving the efficiency of the RTSM system and the prediction system. The command can request a number of patients registered at one or more sites or one or more groups, regions, etc. Additionally or alternatively, the command can request a list of available supplies at one or more sites, warehouses, etc. Additionally or alternatively, the command can request to record patient doses, patient information, or any other information related to the status of the trial.

[0080] The method 130 may also include step 136, which includes receiving the status of the supply of one or more drugs under study in response to the command issued in step 134. As described above, due to the use of the RTSM system API, the status information can be provided to the prediction system by the RTSM system without using an entire file exchange, instead, the requested data can be sent and received directly without packaging the data into one or more files and without manually selecting or opening such files.

[0081] The method 130 may also include step 138, which includes comparing the status of the study supply with a previously calculated supply plan related to the study. As described above, the forecasting system may compare any or all aspects of the study regarding the progress - inventory levels in one or more warehouses or at one or more sites, enrollment at one or more sites, etc., with a supply plan previously calculated by the forecasting system, which may be used by the study sponsor in terms of logistics and financial commitments regarding the study.

[0082] Method 130 may also include step 140, which includes determining that the trial supply status is different from the supply plan. The trial status may be determined to be different from the supply plan when the difference between the trial status and the supply plan may result in, for example, a site or warehouse out of stock or, in another example, an inability to complete the trial within the desired amount of time due to low registrations at one or more sites. Step 140 may include determining that the trial supply is different from the supply plan forecast when the difference is, for example, greater than a threshold percentage, such as a few percent (e.g., five percent (5%)). Of course, any suitable threshold percentage may be used.

[0083] The method 130 may also include step 142, which includes: generating an electronic alert in response to determining that the test supply status is different from the supply plan and sending the electronic alert to the user. In an embodiment, the electronic alert can be sent via an email, a text message, or other message. For example, in an embodiment where the forecasting system provides an electronically accessible interface, the alert can be sent to a user account associated with a user of the interface for the user to view when accessing the interface. The alert may include, for example, a notification that the test status has deviated from the forecast plan. Additionally or alternatively, the alert may include a corrective action, such as a correction to one or more shipments to one or more sites, a correction to the manufacturing volume of one or more supplies, a correction to a registration cap at one or more sites, etc. In an embodiment, the forecasting system may automatically generate a document such as an order, a shipping instruction, or an instruction to the test site, and include the automatically generated document in the alert so that the user of the forecasting system can cause the alert to be sent when corrective action is required.

[0084] Figure 8 is a diagrammatic view of an illustrative computing system that includes a general computing system environment 150 such as a desktop computer, laptop computer, smart phone, tablet computer, or any other such device having the ability to execute instructions, such as instructions stored in a non-transitory computer-readable medium. In addition, although described and illustrated in the context of a single computing system 150, those skilled in the art will also understand that the various tasks described below may be practiced in a distributed environment having multiple computing systems 150 linked via a local area network or a wide area network in which executable instructions may be associated with and / or executed by one or more of the multiple computing systems 150. The computing environment or portions thereof may include Figure 1 One or more of the supply forecasting system 12, the RTSM system 14 and one or more user computing devices 16.

[0085] Continue to refer to Figure 8In its most basic configuration, the computing system environment 150 typically includes at least one processing unit 152 and at least one memory 154, which may be linked via a bus 156. Depending on the exact configuration and type of the computing system environment, the computer-readable memory 154 may be volatile (e.g., RAM 160), non-volatile (e.g., ROM 158, flash memory, etc.), or some combination of the two. The computing system environment 150 may have additional features and / or functionality. For example, the computing system environment 150 may also include additional storage devices (removable and / or non-removable), including, but not limited to, magnetic or optical disks, tape drives, and / or flash drives. Such additional storage devices may be made accessible to the computing system environment 150 through, for example, a hard drive interface 162, a magnetic disk drive interface 164, and / or an optical disk drive interface 166. As will be understood, these devices, which will be linked to the system bus 156 respectively, allow: reading from and writing to the hard disk 168, reading from or writing to the removable disk 170, and / or reading from or writing to the removable optical disk 172, such as a CD / DVD ROM or other optical media. The drive interface and its associated computer-readable media allow non-volatile storage of computer-readable instructions, data structures, program modules, and other data for the computing system environment 150. Those skilled in the art will also understand that other types of computer-readable media that can store data can be used for this same purpose. Examples of such media devices include, but are not limited to, magnetic tape cassettes, flash memory cards, digital video disks, Bernoulli cassettes, random access memories, nano drives, memory sticks, other read / write and / or read-only memories, and / or any other methods or technologies for storing information such as computer-readable instructions, data structures, program modules, or other data. Any such computer storage media can be part of the computing system environment 150.

[0086] Many program modules may be stored in one or more of the memory / media devices. For example, a basic input / output system (BIOS) 174 may be stored in ROM 158, which contains basic routines such as those that help transfer information between elements within the computing system environment 150 during startup. Similarly, RAM 160, hard disk drive 168, and / or peripheral storage devices may be used to store computer executable instructions including an operating system 176, one or more application programs 178 (e.g., a web browser and / or other applications that perform the methods and processes of the present disclosure), other program modules 180, and / or program data 182. In addition, computer executable instructions may also be downloaded to the computing environment 150 as needed, for example, via a network connection.

[0087] An end user may enter commands and information into the computing system environment 150 through input devices such as a keyboard 184 and / or a pointing device 186. Although not shown, other input devices may include a microphone, a joystick, a game controller, a scanner, and the like. These and other input devices will typically be connected to the processing unit 152 through a peripheral interface 188, which in turn will be coupled to the bus 156. The input devices may be connected to the processor 152 directly or indirectly via an interface such as a parallel port, a game port, FireWire, or a universal serial bus (USB). To view information from the computing system environment 150, a monitor 190 or other type of display device may also be connected to the bus 156 via an interface, such as via a video adapter 192. In addition to the monitor 190, the computing system environment 150 may also include other peripheral output devices not shown, such as speakers and printers.

[0088] The computing system environment 150 may also utilize logical connections to one or more computing system environments. Communications between the computing system environment 150 and a remote computing system environment may be exchanged via another processing device responsible for network routing, such as a network router 202. Communications with the network router 202 may be performed via a network interface component 204. Thus, in such a networked environment, such as the Internet, the World Wide Web, a LAN, or other similar types of wired or wireless networks, it will be understood that program modules or portions thereof described with respect to the computing system environment 150 may be stored in (one or more) memory storage devices of the computing system environment 150.

[0089] The computing system environment 150 may also include positioning hardware 206 for determining the location of the computing system environment 150. In implementations, the positioning hardware 206 may simply include, for example, a GPS antenna, an RFID chip or reader, a WiFi antenna, or other computing hardware that may be used to capture or send signals that may be used to determine the location of the computing system environment 150.

[0090] According to the implementation methods including the above embodiments, the following technical solutions are also disclosed:

[0091] (1) A computer-implemented method comprising:

[0092] receiving, by a server from a user, one or more electronic files containing parameters of a clinical trial, the parameters including a number of patients, a plurality of sites, and one or more confidence values;

[0093] calculating, by the server, a corresponding demand profile for each of the plurality of sites based on the number of patients;

[0094] Calculating, by the server, a buffer quantity for each of the plurality of sites according to the one or more confidence values;

[0095] calculating, by the server, a supply plan for the clinical trial based on the demand profile and the buffer quantity; and

[0096] The server sends the supply plan to the user.

[0097] (2) The method according to (1), wherein the one or more electronic files include one or more electronic spreadsheet files and one or more text files, wherein the method comprises:

[0098] converting data in the one or more electronic spreadsheet files into one or more electronic text-based tables;

[0099] inserting the one or more electronic text-based tables into the one or more text files to create one or more supplemental text files; and

[0100] Natural language processing is performed on the one or more text files to determine parameters of the clinical trial.

[0101] (3) The method according to (1), wherein calculating the demand profile of a site among the plurality of sites comprises:

[0102] A respective average value of the demand of the site and a respective statistical distribution of the demand at each time point in a plurality of time points are calculated.

[0103] (4) The method according to (1), wherein the parameters further include corresponding patient registration restrictions for each of the plurality of sites, and the method further includes:

[0104] calculating, for each of the plurality of sites, a respective date that would satisfy the respective patient enrollment restriction;

[0105] Wherein, a corresponding demand profile of each of the plurality of sites is also calculated according to the corresponding date.

[0106] (5) The method of (4), wherein calculating the corresponding date that will satisfy the corresponding patient registration restriction includes applying a Monte Carlo simulation.

[0107] (6) The method according to (1), wherein calculating the supply plan includes:

[0108] determining a corresponding uncertainty value at each time point in a plurality of time points;

[0109] A corresponding demand quantity at each of the plurality of time points is calculated according to the corresponding uncertainty value.

[0110] (7) The method according to (1), further comprising:

[0111] establishing electronic communication with a computerized randomization and trial supply management (RTSM) system after sending the supply plan to the user;

[0112] outputting a command to the RTSM system via an application programming interface (API) associated with the RTSM system to determine the status of the clinical trial;

[0113] comparing the status of the clinical trial with the supply plan;

[0114] Determining that the clinical trial does not comply with the supply plan; and

[0115] An electronic notification is automatically sent to the user, the electronic notification including an indication that the clinical trial does not comply with the supply plan.

[0116] (8) A computer-implemented method comprising:

[0117] receiving, by a server from a user, one or more electronic files containing parameters of a clinical trial, the parameters including a number of patients, a plurality of sites, and one or more confidence values;

[0118] The server calculates a supply plan for the clinical trial based on the parameters;

[0119] The server sends the supply plan to the user;

[0120] After sending the supply plan to the user, establishing electronic communication with a computerized randomization and trial supply management (RTSM) system operating the clinical trial;

[0121] outputting commands to the RTSM system via an application programming interface (API) associated with the RTSM system;

[0122] receiving data from the RTSM system in response to the command;

[0123] determining the status of the clinical trial based on data received from the RTSM system;

[0124] comparing the status of the clinical trial with the supply plan;

[0125] Determining that the clinical trial does not comply with the supply plan; and

[0126] An electronic notification is automatically sent to the user, the electronic notification including an indication that the clinical trial does not comply with the supply plan.

[0127] (9) The method according to (8), wherein:

[0128] Outputting commands to the RTSM system via the API includes: outputting corresponding commands to determine a list of sites involved in the trial, corresponding inventories at each of the sites, corresponding check-in quantities at each of the sites, and corresponding check-in speeds at each of the sites; and

[0129] Determining that the clinical trial does not comply with the supply plan includes determining that the available supply based on the corresponding inventory at each of the sites, the corresponding registration quantity at each of the sites, and the corresponding registration speed at each of the sites is lower than the planned available supply in the supply plan.

[0130] (10) The method according to (8), further comprising:

[0131] Identify changes to the supply plan that will cause the clinical trial to comply with the modified supply plan;

[0132] Wherein, the notification also includes the supply plan modification.

[0133] (11) The method of (10), wherein the supply plan modification includes additional medication orders for one or more of the sites.

[0134] (12) The method according to (8), wherein:

[0135] Outputting commands to the RTSM system via the API includes: outputting corresponding commands to determine a list of sites involved in the trial, corresponding inventory at each of the sites, corresponding upcoming usage at each of the sites, and corresponding inventory at one or more warehouses, wherein the one or more warehouses supply a corresponding subset of the one or more sites; and

[0136] Determining that the clinical trial does not comply with the supply plan includes determining that the available supply based on the corresponding inventory at each of the sites, the corresponding upcoming usage at each of the sites, and the corresponding inventory at the one or more warehouses is lower than the planned available supply in the supply plan.

[0137] (13) The method according to (8), further comprising:

[0138] Calculating, by the server, a buffer quantity for each of the plurality of sites according to the one or more confidence values; and

[0139] The server calculates a supply plan for the clinical trial based on the demand profile and the buffer quantity.

[0140] (14) The method according to (8), wherein the one or more electronic files include an electronic spreadsheet file and one or more text files, and wherein the method comprises:

[0141] converting data in the electronic spreadsheet file into one or more electronic text-based tables;

[0142] inserting the one or more electronic text-based tables into the one or more text files to create one or more supplemental text files; and

[0143] Natural language processing is performed on the one or more text files to determine parameters of the clinical trial.

[0144] (15) A computer-implemented method comprising:

[0145] Receiving, by a server from a user, one or more electronic files containing parameters of a clinical trial, the parameters including a number of patients, a plurality of sites, and one or more confidence values, wherein the one or more electronic files include one or more electronic spreadsheet files and one or more text files;

[0146] converting data in the electronic spreadsheet file into one or more electronic text-based tables;

[0147] inserting the one or more electronic text-based tables into the one or more text files to create one or more supplemental text files;

[0148] performing natural language processing on the one or more text files to determine parameters of the clinical trial;

[0149] The server calculates a supply plan for the clinical trial based on parameters of the clinical trial; and

[0150] The server sends the supply plan to the user.

[0151] (16) The method according to (15), further comprising:

[0152] establishing electronic communication with a computerized randomization and trial supply management (RTSM) system after sending the supply plan to the user;

[0153] outputting a command to the RTSM system via an application programming interface (API) associated with the RTSM system to determine the status of the clinical trial;

[0154] comparing the status of the clinical trial with the supply plan;

[0155] Determining that the clinical trial does not comply with the supply plan; and

[0156] An electronic notification is automatically sent to the user, the electronic notification including an indication that the clinical trial does not comply with the supply plan.

[0157] (17) The method according to (16), wherein:

[0158] Outputting commands to the RTSM system via the API includes: outputting corresponding commands to determine a list of sites involved in the trial, corresponding inventories at each of the sites, corresponding check-in quantities at each of the sites, and corresponding check-in speeds at each of the sites; and

[0159] Determining that the clinical trial does not comply with the supply plan includes determining that the available supply based on the corresponding inventory at each of the sites, the corresponding registration quantity at each of the sites, and the corresponding registration speed at each of the sites is lower than the planned available supply in the supply plan.

[0160] (18) The method according to (16), wherein:

[0161] Outputting commands to the RTSM system via the API includes: outputting corresponding commands to determine a list of sites involved in the trial, corresponding inventory at each of the sites, corresponding upcoming usage at each of the sites, and corresponding inventory at one or more warehouses, wherein the one or more warehouses supply a corresponding subset of the one or more sites; and

[0162] Determining that the clinical trial does not comply with the supply plan includes determining that the available supply based on the corresponding inventory at each of the sites, the corresponding upcoming usage at each of the sites, and the corresponding inventory at one or more warehouses is lower than the planned available supply in the supply plan.

[0163] (19) The method according to (15), wherein:

[0164] Identify changes to the supply plan that will cause the clinical trial to comply with the modified supply plan;

[0165] Wherein, the notification also includes the supply plan modification, wherein the supply plan modification includes additional medication orders for one or more of the sites.

[0166] (20) A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to:

[0167] receiving from a user one or more electronic files containing parameters of a clinical trial, the parameters including a number of patients, a plurality of sites, and one or more confidence values;

[0168] calculating a corresponding demand profile for each of the plurality of sites based on the number of patients;

[0169] calculating a buffer quantity for each of the plurality of sites based on the one or more confidence values;

[0170] calculating a supply plan for the clinical trial based on the demand profile and the buffer quantity; and

[0171] The supply plan is sent to the user.

[0172] Although the present disclosure has described certain embodiments, it should be understood that, except as explicitly stated in the claims, the claims are not intended to be limited to these embodiments. On the contrary, the present disclosure is intended to cover substitutions, modifications, and equivalents that may be included in the spirit and scope of the present disclosure. In addition, in the detailed description of the present disclosure, many specific details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, it is obvious to those of ordinary skill in the art that systems and methods consistent with the present disclosure can be practiced without these specific details. In other cases, well-known methods, processes, components, and circuits are not described in detail to avoid unnecessarily obscuring various aspects of the present disclosure.

[0173] Some parts of the detailed description of the present disclosure have been presented according to the process, logic block, processing and other symbolic representations of the operation of the data bit in the computer or digital system memory. These descriptions and representations are the means by which the technical personnel in the field of data processing use the essence of their work to convey to other technical personnel in the field most effectively. In this article, process, logic block, processing, etc. are generally conceived as a self-consistent sequence of steps or instructions that produce a desired result. These steps are the steps required for physical manipulation of physical quantities. Usually, although not necessarily, these physical manipulations take the form of electrical data or magnetic data that can be stored, transmitted, combined, compared and otherwise manipulated in a computer system or similar electronic computing device. For convenience and with reference to common usage, with reference to various embodiments of the present invention, such data are referred to as bits, values, elements, symbols, characters, items, numbers, etc.

[0174] However, it should be remembered that these terms should be interpreted as referring to physical manipulations and quantities, and are merely convenient labels that should be further interpreted according to terms commonly used in the art. Unless otherwise specifically stated, as is apparent from the discussion herein, it should be understood that throughout the discussion of this embodiment, discussions utilizing terms such as "determine" or "output" or "send" or "record" or "locate" or "store" or "display" or "receive" or "identify" or "utilize" or "generate" or "provide" or "access" or "check" or "notify" or "deliver" refer to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data. Data is represented as physical (electronic) quantities within the registers and memories of a computer system, and data is transformed into other data similarly represented as physical quantities within computer system memories or registers, or other such information storage devices, transmission devices, or display devices as described herein or otherwise understood by those of ordinary skill in the art.

Claims

1. A computer-implemented method comprising: Computer-based prediction of supply plans for clinical trials, including: obtaining, by the computer, a plurality of parameters of the clinical trial, the parameters relating to a plurality of patients, a plurality of sites, and a plurality of actions associated with the clinical trial; determining, by the computer, for each patient included in the plurality of patients, a respective statistical distribution of needs based on a plurality of actions associated with the clinical trial; determining, by the computer, a corresponding supply demand profile for each site included in the plurality of sites, wherein the supply demand profiles of the plurality of sites are determined based on a statistical distribution of the needs of the plurality of patients; and calculating, by the computer, a supply plan for the clinical trial based on the supply demand profile; Re-forecasting, by the computer, a supply plan for the clinical trial based on variability in respective treatments of the plurality of patients; and The server transmits the re-forecasted supply plan to the user.

2. The method according to claim 1, wherein: The plurality of parameters of the clinical trial include: a proportion of expected patients participating in the clinical trial, a proportion of patients failing screening, randomization of the plurality of patients, a description of treatment of the plurality of patients, and a change in dosage of the plurality of patients.

3. The method according to claim 1, wherein: The plurality of parameters of the clinical trial include respective visit schedules and treatment courses for the plurality of patients.

4. The method according to claim 1, wherein: The plurality of patients includes a specific patient, and wherein the statistical distribution of the specific patient's needs indicates one or more drug quantities, drug doses, and / or placebos determined to be required at one or more time points during treatment of the specific patient.

5. The method according to claim 1, wherein: The multiple actions associated with the clinical trial include: screening one or more potential patients, assigning the multiple patients to respective treatment courses, dispensing medication to one or more patients, reducing one or more patients from the study, and / or changing the medication dosage for one or more patients.

6. The method according to claim 1, wherein: Forecasting the supply plan includes forecasting a first supply plan based on information available at a first time, and wherein re-forecasting the supply plan includes forecasting a second supply plan based on information available at a second time.

7. The method according to claim 1, wherein: The variability in the respective treatments of the plurality of patients includes the variability in the dosages of the plurality of patients.

8. The method according to claim 1, wherein: Supply demand profiles for the plurality of sites are also determined based on respective registration patterns at the plurality of sites.

9. A supply forecasting system comprising: processor; as well as A computer readable medium storing instructions which, when executed by the processor, cause the system to perform the method according to any one of claims 1 to 8.

10. A computer-implemented method comprising: Computer-based prediction of supply plans for clinical trials, including: obtaining, by the computer, a plurality of parameters of the clinical trial, the parameters relating to a plurality of patients, a plurality of sites, and a plurality of actions associated with the clinical trial; determining, by the computer, for each patient included in the plurality of patients, a respective statistical distribution of needs based on a plurality of actions associated with the clinical trial; determining, by the computer, a corresponding supply demand profile for each site included in the plurality of sites, wherein the supply demand profiles of the plurality of sites are determined based on a statistical distribution of the needs of the plurality of patients; and calculating, by the computer, a supply plan for the clinical trial based on the supply demand profile; When a specific milestone is reached, re-forecasting, by the computer, the supply plan for the clinical trial; and The server transmits the re-forecasted supply plan to the user.

11. The method according to claim 10, wherein: The plurality of parameters of the clinical trial include: a proportion of expected patients participating in the clinical trial, a proportion of patients failing screening, randomization of the plurality of patients, a description of treatment of the plurality of patients, and a change in dosage of the plurality of patients.

12. The method according to claim 10, wherein: The plurality of parameters of the clinical trial include respective visit schedules and treatment courses for the plurality of patients.

13. The method according to claim 10, wherein: The plurality of patients includes a specific patient, and wherein the statistical distribution of the specific patient's needs indicates one or more drug quantities, drug doses, and / or placebos determined to be required at one or more time points during treatment of the specific patient.

14. The method according to claim 10, wherein: The multiple actions associated with the clinical trial include: screening one or more potential patients, assigning the multiple patients to respective treatment courses, dispensing medication to one or more patients, reducing one or more patients from the study, and / or changing the medication dosage for one or more patients.

15. The method according to claim 10, wherein: Forecasting the supply plan includes forecasting a first supply plan based on information available at a first time, and wherein re-forecasting the supply plan includes forecasting a second supply plan based on information available at a second time.

16. The method according to claim 10, wherein: The re-forecast of the supply plan for the clinical trial is based on variability in the respective treatment courses of the plurality of patients.

17. The method according to claim 16, wherein: The variability in the respective treatments of the plurality of patients includes the variability in the dosages of the plurality of patients.

18. The method according to claim 10, wherein: The specific indicia include the availability of specific dates or specific information.

19. The method according to claim 10, wherein: Supply demand profiles for the plurality of sites are also determined based on respective registration patterns at the plurality of sites.

20. A supply forecasting system comprising: processor; as well as A computer readable medium storing instructions which, when executed by the processor, cause the system to perform the method according to any one of claims 10 to 19.