Data analysis and reporting system and method

Abstract

A system and method are provided for automated data analysis and reporting of pharmaceutical batch production records. In response to receiving a user command to generate a batch report, the method includes automatically performing one or more statistical analyses on raw batch data extracted from one or more batch production records, generating one or more charts and one or more tables using the analyzed data, identifying one or more review boxes associated with the analyzed data, compiling a batch report that includes the one or more identified review boxes, storing the batch report in a memory, and displaying the batch report on a user device.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Application No. 63 / 336,035, filed April 28, 2022, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to systems and methods for automated data analysis and reporting of pharmaceutical batch production records. [Background technology]

[0003] When manufacturing a pharmaceutical composition, part of drug development is to perform a feasibility study of the manufacturing process. Performing a feasibility study involves reviewing and analyzing batch production records that provide a complete history of each step of the manufacturing process for a given drug lot or batch produced. Batch production records are used to ensure soundness, safety, and quality, and provide an auditable record detailing compliance with federal regulations. The results of a given feasibility study will identify whether the manufactured drug product complies with or deviates from the drug product specifications. Thus, feasibility studies can be used to prove compliance with a given drug product's specifications or to evaluate variances from those specifications. Summary of the Invention [Problem to be solved by the invention]

[0004] The process of preparing a feasibility report typically includes batch testing, batch data collection, data analysis, and drafting. A given feasibility report may include not only the analyzed batch data, but also a discussion of the results, including a discussion of compliance with specifications, and a description of the manufacturing and analytical processes.

[0005] Currently, each of the batch data collection, data analysis, and report drafting steps of the report drafting process are performed manually. Batch data is collected from batch production records, which generally take the form of printed or portable document format (PDF) documents. Such document formats are necessary to ensure that the batch production records meet regulatory requirements and can be audited periodically. Collecting batch record data from printed or PDF documents requires manually reading the documents, identifying the relevant data, and then copying that data into a computing system so that it can be analyzed. This process is generally performed by two individuals, one individual manually copying the data values ​​into a spreadsheet and another individual reviewing both the production record and the spreadsheet values ​​to ensure that the individuals copied the values ​​accurately.

[0006] After copying the batch record data into a spreadsheet, one or more individuals may then perform the data analysis. Such data analysis may include, for example, evaluating physical properties such as tablet weight, hardness, and / or thickness, as well as evaluating blend uniformity, stratified content uniformity, dissolution, moisture content, and / or disintegration time. The sophistication of the data analysis is individual driven. That is, highly skilled data scientists provide more sophisticated analysis than less skilled data scientists. More sophisticated analysis leads to higher quality reports, so more highly trained data scientists are needed to ensure that high quality reports are generated. This leads to increased training costs and increased demand for more highly trained individuals. Furthermore, because manual data analysis is individual driven, there is a lack of consistency between data analyses performed by different individuals.

[0007] Variability due to the person-driven nature of manual data analysis carries over into the report drafting stage of the feasibility report process. Thus, the person-driven nature of the feasibility report process can result in inconsistencies in both the data analysis included in the report and any discussion of that analysis within the report. Such inconsistencies can undermine both the scientific quality of the feasibility report and the goodwill of the entity preparing the report.

[0008] Thus, a system and method for automated data analysis and reporting of pharmaceutical batch production records is presented herein. By automating the report generation process, companies can realize significant time savings, improve the quality and consistency of reports, and ensure that reports meet scientific standards of analysis and formatting. In addition, companies can improve customer satisfaction by reducing turnaround time for generating reports and providing higher quality reports. Companies can also minimize the need for highly skilled individuals, reduce training costs, increase productivity, and increase the company's goodwill. [Means for solving the problem]

[0009] In one or more examples, a computer-implemented method for generating a batch report includes extracting raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices and storing the extracted raw batch data in memory; receiving a user command at the user device to automatically generate the batch report; in response to receiving the user command, performing one or more statistical analyses on the stored raw batch data; generating one or more figures and one or more tables using the analyzed data and storing the one or more figures and the one or more tables in memory; identifying one or more review boxes associated with the analyzed data; compiling a batch report including the identified one or more associated review boxes, the one or more figures, and the one or more tables; saving the compiled batch report in memory; and displaying the compiled batch report on the user device.

[0010] Optionally, the computer-implemented method includes identifying one or more outliers in the analyzed data and determining whether the one or more outliers are caused by a manufacturing process error or a post-manufacturing data analysis error.

[0011] In one or more examples, when the one or more batch manufacturing reports are received, raw batch data can be extracted in real time from the one or more batch manufacturing reports, and the computer-implemented method can include providing one or more guidelines for adjusting one or more settings of the one or more manufacturing devices if the outlier is caused by a manufacturing process error.

[0012] The one or more batch manufacturing reports may include a plurality of batch pages, and the step of extracting the raw batch data may include the steps of receiving one or more image coordinates corresponding to one or more border areas within the pages, photoscanning each of the plurality of batch pages, collecting raw batch data located within the one or more border areas on each of the plurality of photoscanned batch pages, and generating a ledger including the collected raw batch data.

[0013] Optionally, compiling the batch report includes generating one or more instruction codes including instructions for populating one or more modifiable handles in one or more associated review boxes with one or more statistical data values ​​from the analyzed data, embedding one or more figures and one or more tables in one or more appropriate locations based on the associated review boxes, and generating a data report including the one or more populated associated review boxes, the one or more embedded figures, and the one or more embedded tables.

[0014] In one or more examples, the one or more instruction codes include LaTeX code.

[0015] Optionally, the one or more changeable handles may each correspond to a data metric, and the one or more review boxes include pre-written text relating to the one or more data metrics, and populating the one or more changeable handles includes replacing each of the changeable handles with a corresponding data metric from the analyzed data.

[0016] In one or more examples, the compiled batch report can indicate whether the analyzed data falls within one or more defined batch specifications.

[0017] In one or more examples, a system for generating a batch report, the system comprising: a memory; one or more processors; and one or more programs, the one or more programs configured to be stored in the memory and executed by the one or more processors, the one or more programs, when executed by the one or more processors, cause the processor to: extract raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices and store the extracted raw batch data in memory; receive a user command at the user device to automatically generate a batch report; in response to receiving the user command, perform one or more statistical analyses on the stored raw batch data; generate one or more charts and one or more tables using the analyzed data and store the one or more charts and one or more tables in memory; identify one or more review boxes associated with the analyzed data; compile a batch report including the one or more associated review boxes, the one or more charts, and the one or more tables;

[0018] Optionally, the one or more programs, when executed by the one or more processors, cause the processors to identify one or more outliers in the analyzed data and determine whether the one or more outliers were caused by a manufacturing error or a post-manufacturing data analysis error.

[0019] In one or more examples, when one or more batch production reports are received, raw batch data can be extracted in real time from the one or more batch production reports.

[0020] The one or more programs, when executed by the one or more processors, cause the processors to provide one or more guidelines for adjusting one or more settings of one or more manufacturing devices if the outlier is caused by a manufacturing process error.

[0021] Optionally, the one or more batch manufacturing reports may include a plurality of batch pages, and extracting the raw batch data may include receiving one or more image coordinates corresponding to one or more border areas within the pages, photoscanning each page of the plurality of batch pages, collecting raw batch data located within the one or more border areas on each page of the plurality of photoscanned batch pages, and generating a ledger including the collected raw batch data.

[0022] In one or more examples, compiling the batch report includes generating one or more instruction codes including instructions for populating one or more modifiable handles in one or more associated review boxes with one or more statistical data values ​​from the analyzed data, embedding one or more figures and one or more tables in one or more appropriate locations based on the associated review boxes, and generating a data report including the one or more populated associated review boxes, the one or more embedded figures, and the one or more embedded tables.

[0023] Optionally, the one or more instruction codes may include LaTeX code.

[0024] In one or more examples, the one or more changeable handles can each correspond to a data metric, the one or more review boxes can include pre-written text related to the one or more data metrics, and populating the one or more changeable handles can include replacing each of the changeable handles with a corresponding data metric from the analyzed data.

[0025] In one or more examples, the compiled batch report can indicate whether the analyzed data falls within one or more defined batch specifications.

[0026] In one or more examples, a computer-readable storage medium storing one or more programs for generating a batch report, the one or more programs including instructions, when executed by an electronic device having a display and a user input interface, to cause the device to extract raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices and store the extracted raw batch data in memory; receive a user command at the user device to automatically generate the batch report; in response to receiving the user command, perform one or more statistical analyses on the stored raw batch data; generate one or more charts and one or more tables using the analyzed data and store the one or more charts and one or more tables in memory; identify one or more review boxes associated with the analyzed data; compile a batch report including the one or more associated review boxes, the one or more charts, and the one or more tables;

[0027] Optionally, the one or more programs, when executed by the electronic device, cause the device to identify one or more outliers in the analyzed data and determine whether the one or more outliers were caused by a manufacturing error or a post-manufacturing data analysis error.

[0028] In one or more examples, when one or more batch production reports are received, raw batch data can be extracted in real time from the one or more batch production reports.

[0029] In one or more examples, the one or more programs, when executed by the electronic device, can cause the device to provide one or more guidelines for adjusting one or more settings of one or more manufacturing devices if the outlier is caused by a manufacturing process error.

[0030] The one or more batch manufacturing reports can include a plurality of batch pages, and extracting the raw batch data can include receiving one or more image coordinates corresponding to one or more border areas within the pages, photoscanning each of the plurality of batch pages, collecting raw batch data located within the one or more border areas on each of the plurality of photoscanned batch pages, and generating a ledger including the collected raw batch data.

[0031] In one or more examples, compiling the batch report may include generating one or more instruction codes including instructions for populating one or more modifiable handles in one or more associated review boxes with one or more statistical data values ​​from the analyzed data, embedding one or more figures and one or more tables in one or more appropriate locations based on the associated review boxes, and generating a data report that includes the one or more populated associated review boxes, the one or more embedded figures, and the one or more embedded tables.

[0032] Optionally, the one or more instruction codes may include LaTeX code.

[0033] In one or more examples, the one or more changeable handles can each correspond to a data metric, the one or more review boxes can include pre-written text related to the one or more data metrics, and populating the one or more changeable handles can include replacing each of the changeable handles with a corresponding data metric from the analyzed data.

[0034] In one or more examples, the compiled batch report can indicate whether the analyzed data falls within one or more defined batch specifications.

[0035] It will be understood that any of the variations, aspects, features, and options described in view of the system may be combined.

[0036] Additional advantages will become readily apparent to those skilled in the art from the following detailed description. The embodiments and descriptions herein are to be regarded as illustrative in nature and not restrictive.

[0037] All publications, including patent documents, scientific articles, and databases, referred to in this application are incorporated by reference in their entirety for all purposes to the same extent as if each individual publication was individually incorporated by reference. To the extent that a definition set forth herein is contrary to or inconsistent with a definition set forth in a patent, application, published application, or other publication incorporated herein by reference, the definition set forth herein shall take precedence over the definition incorporated herein by reference.

[0038] The invention will now be described, by way of example only, with reference to the accompanying drawings in which: [Brief description of the drawings]

[0039] [Figure 1] FIG. 1 illustrates an example automated process for generating batch reports, according to one or more examples of the present disclosure. [Diagram 2] FIG. 13 illustrates an exemplary user interface for a user to indicate automatic generation of a batch report, in accordance with one or more examples of the present disclosure. [Diagram 3] FIG. 1 illustrates an exemplary user interface for a user to input data required for an automated process for generating batch reports, in accordance with one or more examples of the present disclosure. [Figure 4] FIG. 1 illustrates an exemplary user interface including a diagram generated using an automated data analysis method, according to one or more examples of the present disclosure. [Diagram 5] FIG. 1 illustrates an exemplary user interface including an exemplary table of contents page generated using an automated data analysis method, according to some examples of the present disclosure. [Figure 6] FIG. 13 illustrates an exemplary user interface including exemplary pages from the manufacturing steps and results section of a report generated using an automated data analysis method, according to some examples of the present disclosure. [Figure 7]A diagram illustrating an exemplary user interface including an exemplary page from the analysis results section of a report generated using an automated data analysis method in accordance with one or more examples of the present disclosure. [Figure 8] FIG. 1 illustrates an example automated process for extracting raw batch data from printed or PDF batch production reports, in accordance with one or more examples of the present disclosure. [Figure 9] FIG. 1 illustrates an example user interface including a batch production report, according to one or more examples of the present disclosure. [Figure 10] FIG. 1 illustrates an example process for a user to direct automatic generation of a batch rate, in accordance with one or more examples of the present disclosure. [Figure 11] FIG. 2 illustrates an example of a computing device in accordance with one or more examples of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0040] As explained above, current methods of generating feasibility reports require manual data collection, analysis, and report drafting. The individual-driven nature of these methods can result in substandard data analysis, substandard graphical and / or typesetting quality, poor scientific quality, and long turnaround periods for the production of a given report.

[0041] Traditional manual processes for generating feasibility reports required an individual to (1) manually collect data values ​​from batch production reports, (2) verify the manually collected data values, (3) perform data analysis, (4) create charts and tables, and (5) draft the feasibility report. While manually generating a report previously required a user to follow a five-step process, automating report generation can simplify the process to only two steps by an individual (1) running a program and (2) reviewing the generated batch data report. Such automation can significantly reduce the amount of time a given user must spend creating a report. For example, manually drafting a given report may take weeks from start to finish, whereas automatically generating the same report may take only a few hours to a few days.

[0042] An automated report generator can perform each step necessary to generate a high quality report without requiring extensive input from a user. For example, an automated report generator can accurately extract data values ​​from batch production records, automatically perform complex data analysis, automatically generate high quality charts and tables based on that analysis, incorporate associated discussion of the analysis, and compile a report that includes the data analysis and discussion and the automatically generated charts and tables. In this manner, an automated report generator can reduce the required human interaction to simply running a program and reviewing the report.

[0043] In addition to reducing the time and effort required to draft a report, an automated report generator can also improve the quality and consistency of the generated reports. For example, as explained above, highly skilled data scientists provide more sophisticated analyses than less skilled or newer data scientists. Furthermore, manually drafted reports will lack consistency when drafted by multiple individuals, since the data analysis and written review performed by the individuals may differ. However, this problem is completely eliminated by an automated report generator, since the automated report generator can repeat the same sophisticated analysis and review the results in the same way each time it is run, resulting in a consistently high quality report.

[0044] Thus, by automating the report generation process, companies can realize significant time savings, improve the quality and consistency of reports, and ensure that reports meet scientific standards for analysis and formatting. Additionally, companies can improve customer satisfaction by reducing turnaround time for generating reports and providing higher quality reports. Companies can also minimize the need for highly skilled individuals, reduce training costs, increase productivity, and enhance the company's business goodwill.

[0045] In the following description of the disclosure and examples, reference is made to the accompanying drawings in which are shown, by way of illustration, specific examples which may be practiced. It is to be understood that other examples can be practiced and changes can be made without departing from the scope of the disclosure.

[0046] In addition, it should be understood that the singular forms "a," "an," and "the" used in the following description are intended to include the plural forms unless the context clearly indicates otherwise. The term "and / or" as used herein should also be understood to refer to and include any and all possible combinations of one or more of the associated listed items. Furthermore, it should be understood that the terms "comprise," "including," "comprising," and / or "comprising," as used herein, specify the presence of stated features, integers, steps, operations, elements, components, and / or units, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, units, and / or groups thereof.

[0047] Some of the detailed descriptions which follow are presented in terms of algorithms and symbolic representations of operations performed on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm here is generally conceived to be a self-consistent sequence of steps (instructions) leading to a desired result. The steps are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical, magnetic, or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It is sometimes convenient, primarily for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like. Further, without loss of generality, it is also convenient to refer to certain arrangements of steps requiring physical manipulations of physical quantities as modules or code devices.

[0048] However, all of these similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless otherwise clear from the discussion below, throughout the description, discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," and the like should be understood to refer to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data that are represented as physical (electronic) quantities within the computer system memory or registers, or other information storage, transmission, or display devices.

[0049] Certain aspects of the present disclosure include process steps and instructions written in the form of an algorithm. It should be noted that the process steps and instructions of the present disclosure may be embodied in software, firmware, or hardware, and if embodied in software, may be downloaded to reside on and operate from a variety of platforms used by a variety of operating systems.

[0050] The present disclosure also relates to a device for performing the operations herein. The device may be specially constructed for the required purpose or may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a non-transitory computer-readable storage medium, such as, but not limited to, any type of disk, including floppy disk, optical disk, CD-ROM, magneto-optical disk, read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic or optical card, application specific integrated circuit (ASIC), or any type of medium suitable for storing electronic instructions, each coupled to a computer system bus. Furthermore, the computer referred to herein may include a single processor or may be an architecture that uses a multi-processor design to increase computing power.

[0051] The methods, devices, and systems described herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will appear from the description that follows. In addition, the present disclosure is not described with reference to any particular programming language. It will be understood that a variety of programming languages ​​may be used to implement the teachings of the present disclosure, as described herein.

[0052] 1 illustrates an exemplary automated process 100 for generating batch reports, according to one or more examples. The automated process 100 can be executed by any suitable type of microprocessor-based device, such as a personal computer, a workstation, a server, or a handheld computing device (portable electronic device) such as a phone or tablet.

[0053] As shown in FIG. 1, the automated process 100 begins with extracting raw batch data in step 102. The raw batch data can be extracted from batch production reports received from various manufacturing devices. Exemplary devices can include, in non-limiting examples, tablet testers, fluid bed processors, vertical granulators, v-blenders / bin blenders, capsule weight sorters, roller compactors, extruders, pan coating process testers, and / or high performance liquid chromatography (HPLC) devices. The extracted raw data can include, in non-limiting examples, tablet weight, thickness, and / or hardness measurements, air flow, inlet air temperature, product temperature, exhaust temperature, and / or dew point measurements, blade speed, chopper speed, water addition rate, and / or blade / chopper torque in-process measurements. In one or more examples, the raw data extracted in step 102 can be stored in memory in a location and / or format that can be accessed by scientists and / or users. In one or more examples, extracting the raw batch data in step 102 can occur in response to a user command to extract the batch data. Extracting the raw batch data in step 102 can also occur automatically upon receiving a batch production report.

[0054] After extracting the raw batch data at step 102, the automation process 100 may move to step 104 to receive a user command to generate a batch report. The user command received at step 104 of the automation process 100 may be received via a command from a user interacting with a user interface of any suitable computing device. The computing device receiving the user command may be the same as the computing device executing the automation process 100 or may be communicatively coupled to the computing device executing the automation process 100. In one or more examples, extracting the raw batch data at step 102 may occur in response to receiving a user command to generate a batch report.

[0055] FIG. 2 illustrates an exemplary user interface for a user to direct the automatic generation of a batch report, according to one or more examples. The user interface illustrated in FIG. 2 can be used by a user to generate a user command to be received in step 104 of the automated process 100. As illustrated in FIG. 2, the user interface 200 allows the user to select an analysis type, production 201 or analysis 202. The production user interface 204 and analysis user interface 206 then allow the user to select a specific analysis based on the selected analysis. For example, if the user selects production 201, then the user can be presented with a production user interface 204 having a list of possible specific production analyses, such as analyses of blending, granulation, extrusion, spheronization, drying, compression, pan coating, encapsulation, roller compaction, packaging, etc. If the user selects analysis 202, then the user can be presented with an analysis user interface 206 having a list of possible specific analytical analyses, such as analyses of content uniformity, stratified content uniformity, dissolution, moisture content, impurities, X-ray powder diffraction (XRPD) analysis, etc.

[0056] In one or more examples, upon selecting the analysis type, the user may be prompted to provide some project information related to the batch report that the user instructed to be generated in step 104. FIG. 3 illustrates an exemplary user interface 300 for a user to input data required for an automated process to generate a batch report, according to one or more examples. The user interface 300 may be displayed after the user selects an analysis type and a particular analysis, as discussed above. As shown in FIG. 3, the user interface 300 includes a window 301 that includes a data field 302 for the user to add required data, a product name field 304, and a directory field 306. The required data that the user can add in the data field 302 may differ based on the particular analysis type. The directory field 306 may allow the user to specify where files generated by the automated process are persisted. Such files may include, for example, spreadsheets, charts, documents, etc. After inputting the information in the window 301, the user may select a button or area of ​​the user interface 300 to execute the automated process. When a button to run the automated process is selected, a command may be received at step 104 of the automated process 100 .

[0057] Returning to FIG. 1 , in response to the user command received in step 104, the automated process 100 may move to step 106 and perform a statistical analysis on the stored raw batch data extracted in step 102. The statistical analysis may be pre-determined by one or more scientists before being performed by the automated process 100. The statistical analysis may include, for example, evaluating changes over time in physical properties such as tablet weight, hardness, and / or thickness. In one or more examples, the statistical analysis may include evaluating blend uniformity, stratified content uniformity, dissolution, moisture content, and / or disintegration time. In one or more examples, data corresponding to the statistical analysis performed in step 106 may be stored in memory in a location and / or format that can be accessed by the scientists and / or users to allow them to review the data used to generate the final batch report. Thus, the scientists and / or users may make any necessary or desired edits to the analysis and use the edits to generate a new version of the batch report.

[0058] After performing the statistical analysis on the stored raw batch data in step 106, the automated process 100 may move to step 108 and generate one or more charts and / or tables. In one or more examples, generating the charts and / or tables in step 108 may be included as part of performing the statistical analysis in step 106. The one or more tables created by the automated process 100 may, in one or more examples, tabulate the data used in the charts, various parameters, analysis summaries, etc. The one or more charts may, in non-limiting examples, include visualizations of particle size analysis, statistics of various in-process parameters over time, and / or physical properties.

[0059] FIG. 4 illustrates an exemplary user interface including a diagram page 400 generated using an automated data analysis method, according to one or more examples. The diagram page 400 can be generated via the automated process 100. As shown in FIG. 4, the diagram page 400 provides a visualization of the tablet thickness characteristics of a given batch. For example, the diagram page 400 includes a graph 402 of tablet weight over time, which graphically represents tablet thickness values ​​over time compared to target tablet thickness specifications, including upper and lower specification limits. In one or more examples, the diagrams and / or tables generated in step 108 can be stored in memory in a location and / or format that can be accessed by the scientist and / or user. Thus, the scientist and / or user can review the tables and / or figures separately from the final report, make any necessary or desired edits to the tables and / or figures, and use the edits to generate a new version of the batch report.

[0060] As explained above, the sophistication of data analysis previously performed by manual processes was personally driven, and the sophistication correlated with the proficiency of a given individual. However, in the automated process 100, the data analysis can be designed by one or more highly skilled individuals, and the automated process 100 is configured to report the same analysis each time it generates a report. Thus, the automated process 100 can ensure that the sophistication of the analysis is high. Furthermore, by standardizing the analysis method and scope, and repeating the same analysis in an automated manner, the automated process 100 eliminates inconsistencies inherent in the previous personally driven manual process. By eliminating these inconsistencies, the automated process 100 can improve customer satisfaction, thereby improving business confidence.

[0061] Returning to FIG. 1, after generating the charts and / or tables in step 108, the automated process 100 can move to step 110 and identify relevant review boxes. Review boxes are pre-filled text boxes. In one or more examples, the review boxes can be filled in to generally discuss the general analysis being performed. For example, if feasibility reports of a given type generally include a review of tablet weights, the review of tablet weights can be standardized so that reviews included in the report always follow the same format and discuss tablet weight results in the same manner.

[0062] In one or more examples, a study box can include one or more modifiable handles. The modifiable handles can function as modifiable whitespace that defines a particular location within a given study box where a particular data value should be considered. The modifiable handles can thus function as variables into which appropriate data values ​​are entered. For example, a study box can include the following:

[0063] Table _ shows the tablet weight of _. It is observed that the tablet weight was _ throughout the sample time with an average value of _ (target: _).

[0064] Thus, when typing into the changeable handle of a review box, appropriate information and data can be automatically entered into the appropriate location within the text of the review box.

[0065] In step 110, in one or more examples, identifying the relevant review boxes may include evaluating what type of data has been collected and what analyses have been performed, and selecting the corresponding review boxes associated with the data and / or analyses.

[0066] In one or more examples, the automated process 100 can generate different types of reports based on the type of analysis performed, as discussed above. Review boxes can be written to provide appropriate review for each type of report. In one or more examples, certain review boxes are only relevant for certain types of reports. Thus, in one or more examples, not all pre-written review boxes are identified as relevant in step 110.

[0067] In one or more examples, the review boxes can be pre-written by one or more highly skilled individuals, and the automated process 100 is configured to include each relevant review box each time it generates a report. Thus, by including reviews written by highly skilled individuals, the automated process 100 can improve the quality of the reports generated. Furthermore, by standardizing the reviews included in each report and automatically including the relevant reviews in each report, the automated process 100 eliminates inconsistencies inherent in previous individual-driven manual processes. By eliminating these inconsistencies and generating high quality reports, the automated process 100 can improve customer satisfaction, thereby improving business confidence.

[0068] After identifying the relevant review boxes in step 110, the automated process 100 may move to step 112 and compile a batch report (e.g., a feasibility report). In one or more examples, to compile the batch report in step 112, the automated process 100 may develop one or more typesetting instructions. The typesetting instructions may include specific instructions for populating the relevant review boxes identified in step 110, embedding the figures and / or tables generated in step 108 in appropriate locations based on the relevant review boxes, and generating the batch report. In one or more examples, the typesetting instructions may be compiled using a typesetting document preparation system. The document preparation system may be configured to standardize the format of the batch report according to scientific standards and formats, which may improve the quality of the report. In one or more examples, the typesetting instructions may be stored in memory in a location and / or format that may be accessed by scientists and / or users. Thus, a scientist and / or user can review the typesetting instructions used to generate the final batch report, make any necessary or desired edits to the instructions, and use the edits to generate a new version of the batch report. For example, the typesetting instructions can be stored in a format such as LaTeX™ code, a Microsoft® Word® document, or an Excel® spreadsheet.

[0069] After compiling the batch report in step 112, the automation process 100 may move to step 114 and display the batch report. The batch report may be displayed at a user device and / or any suitable computing device. The involvement of any individual in the automation process 100 may be limited to running the automation process and reviewing the displayed batch report. Thus, the automation process 100 may significantly reduce the effort required by each individual to generate a quality report. Furthermore, while the report is being generated, employees may be able to focus their attention elsewhere, thus increasing productivity.

[0070] The batch report displayed in step 114 of the automated process 100 can include various sections. Such sections can include, for example, a business plan overview section, a section discussing the process flow, equipment, and master formulation, a section discussing the manufacturing steps and results, a section discussing analytical results, a section discussing conclusions, and a section containing references to reports. In one or more examples, the sections included in the batch report can be presented in a table of contents.

[0071] FIG. 5 illustrates an exemplary user interface including an exemplary table of contents page 500 generated using an automated data analysis method, according to some examples. The table of contents page 500 can be part of a report generated and displayed via the automated process 100. As shown in FIG. 5, the table of contents page 500 includes a list of sections 502 of the batch report. The list of sections of the batch report can include page numbers for each section as well as any other relevant details. In one or more examples, the table of contents page 500 can precede a list of figures and / or a list of tables included within the report. The list of figures and the list of tables can include the number of the figure / table, the name of the figure / table, and the page number of the figure / table where the corresponding figure / table can be found within the report.

[0072] The business plan summary section of the report displayed in step 114 of the automated process 100 may include a review of the purpose of a given report, relevant background information, and information regarding the scope of the report. For example, the purpose of the report may include documenting the results of a process development study of a particular pharmaceutical composition. Alternatively, the purpose of the report may include summarizing observations during the manufacture of a particular pharmaceutical composition. The relevant background information may include, in non-limiting examples, information regarding the drug product that is the focus of the report and / or a review or summary of the manufacturing history of the drug product. Information regarding the scope of a given report may include specific information regarding the batch number and / or batch size (number of tablets) of a particular drug product. The scope section may include a table containing summary information regarding one or more manufacturing processes, such as, for example, granulation, compression, pan coating, etc.

[0073] The process flow, equipment, and master formulation review sections of the report displayed in step 114 of the automated process 100 can include diagrams illustrating the process flow of a given manufacturing process. For example, the process flow diagram can show a timeline view of the various manufacturing steps, including the duration of each step, the constituent ingredients and composition percentages, the manufacturing process, etc. The process flow, equipment, and master formulation sections can also include one or more tables containing information regarding the number and type of equipment used, the pharmaceutical formulation composition of each type of pharmaceutical product (i.e., granulated tablets, compressed tablets, and / or pan coated tablets). The process flow, equipment, and master formulation sections can include reviews, tables, and / or figures based on data extracted in step 102 of the automated process 100, generated in step 108 of the process 100, and compiled in step 112 of the process 100.

[0074] The section of the report displayed in step 114 of the automated process 100 that reviews the production steps and results may include reviews of blending, grinding, granulation, and / or lubrication. For example, Figure 6 shows an exemplary user interface including an exemplary page 600 from the production steps and results section of a report generated using the automated data analysis method, according to some examples. Page 600 may be part of the production steps and results section of a report generated and displayed via the automated process 100.

[0075] As shown in FIG. 6, page 600 includes a table 602 showing various in-process parameters for a given pharmaceutical batch, including solution volume, spray rate, atomization air pressure, inlet air temperature, product temperature, etc. In one or more examples, the in-process parameters can be graphically illustrated in one or more figures. For example, figure 604 of page 600 shows various parameters graphically illustrated over time. Other figures that may be included within the manufacturing steps and results section can include, in non-limiting examples, figures related to particle size, in-process compression force, tablet weight statistics, tablet hardness statistics, tablet thickness statistics, etc. The manufacturing steps and results section can include studies, tables, and / or figures based on data extracted in step 102 of the automated process 100, generated in step 108 of the process 100, and compiled in step 112 of the process 100.

[0076] The section of the report that discusses the analytical results, displayed in step 114 of the automated process 100, may include subsections for blend uniformity, assay, stratified content uniformity, dissolution, moisture content, disintegration time, enhanced sampling, etc. In each subsection, the report may include discussions, tables, and / or figures based on the data extracted in step 102 of the automated process 100, generated in step 108 of the process 100, and compiled in step 112 of the process 100.

[0077] FIG. 7 illustrates an exemplary user interface including an exemplary page 700 from an analysis results section of a report generated using an automated data analysis method, according to some examples. The page 700 can be part of the analysis results section of a report generated and displayed via the automated process 100. As shown in FIG. 7, the page 700 includes a subsection 702 related to blend uniformity and a subsection 704 related to assays. Each subsection of the analysis results section can include a discussion, table, and / or figure based on data extracted in step 102 of the automated process 100, generated in step 108 of the process 100, and compiled in step 112 of the process 100. In one or more examples, the subsections can also include conclusions of the analysis automatically generated via the automated process 100. For example, as shown in subsection 704, this report page 700 provides a calculated average assay of a first percentage 706 that is characterized as a “significant improvement” compared to the average value of a second percentage 708 from a different manufacturing batch. Thus, the report displayed in step 114 of the automated process 100 not only includes the results of the automatically performed statistical assays, but also automatically provides a meaningful review of those results.

[0078] The reviewing conclusions section of the report displayed in step 114 of the automation process 100 can, in one or more examples, include a review of one or more recommendations generated based on the report's conclusions. For example, the report may determine that the data analysis revealed a low assay problem, and the report may include one or more recommendations for modifying the granulation process to minimize the likelihood of the low assay problem recurring.

[0079] The section of the report displayed in step 114 of the automated process 100 that includes a reference to a given report may include a reference to one or more documents used to develop the report. Such documents may include, for example, a particular batch report identified by a document number, regulatory and / or company protocols and / or standards identified by a document number.

[0080] As discussed above, the raw data required to generate a given batch report may be contained within the batch production records in either printed or PDF document format due to regulatory needs. Whereas previously this raw data was extracted by two individuals, one copying the values ​​into a spreadsheet and one verifying the accuracy of the process, the automated process 100 may perform such extraction completely independently. In one or more examples, the raw data required to generate a given batch report may be contained within the batch production records exported from a machine in comma separated values ​​(CSV) format. The automated process 100 may be configured to extract such values ​​directly from the CSV file.

[0081] FIG. 8 illustrates an exemplary automated process 800 for extracting raw batch data from a printed or PDF batch production report, according to one or more examples. The automated process 800 may be executed as part of step 102 of the automated process 100. The automated process 800 may begin at step 802 by receiving image coordinates corresponding to one or more bounded page regions. In one or more examples, batch production records exported from a particular type of machine are exported with associated raw data values ​​located within a particular region of the page. Thus, the image coordinates may correspond to the region within the page in which the raw data values ​​were recorded. In one or more examples, a user may be able to edit the image coordinates corresponding to any changes to the particular region within which the associated raw data values ​​are located within the batch production record. In one or more examples, a user may be able to perform such changes in real time as the batch production record is received.

[0082] 9 illustrates an example batch production report 900, according to one or more examples. As shown in FIG 9, relevant raw data regarding sampled values ​​of weight, thickness, and hardness are included within a particular region 902 of the batch production report 900. Thus, the image coordinates received in step 802 of the automated process 800 may include image coordinates corresponding to that region 902.

[0083] 8, after receiving the image coordinates in step 802, the automated process 800 may move to step 804 and scan each page of the batch production record. The scanning of the batch production record may be performed with any conventional scanning technique known in the art.

[0084] After scanning each page of the batch production record in step 804, the automated process 800 may move to step 806 to collect raw batch data located within one or more border page areas. The one or more border page areas may correspond to the image coordinates received in step 802.

[0085] After collecting the raw batch data in step 806, the automated process 800 may move to step 808 and generate a ledger containing the raw data. The ledger may be stored in a location and / or format accessible to scientists and / or users. For example, the raw data may be stored as a spreadsheet in a commercially available spreadsheet software program such as Microsoft Excel.

[0086] In one or more examples, automated process 800 and automated process 100 can be performed in real-time as data production records are output from one or more manufacturing devices. Thus, step 106 of automated process 100, which performs statistical analysis on stored raw batch data, can be performed in real-time as a given batch is being manufactured. As part of performing the statistical analysis in step 106, automated process 100 can include identifying any outlying data values ​​in the data. Identifying one or more outlying data values ​​can, in one or more examples, involve performing a variance component analysis.

[0087] Upon identifying an outlier data value, the automated process 100 can be configured to provide a warning to a user. In one or more examples, the automated process 100 can be configured to determine whether the outlier was caused by the manufacturing process or a post-manufacturing data analysis error. In one or more examples, the automated process 100 can be configured to provide one or more guidelines for adjusting settings of one or more manufacturing devices. For example, the automated process 100 can be configured to provide guidelines for stopping a manufacturing device upon identifying an outlier due to a manufacturing process error.

[0088] Previously, if a data analysis for a given production batch contained an outlier data value, the entire batch may have been discarded. Thus, by determining whether the outlier is due to a data analysis error, the automated process 100 may ensure that any batch having such a value is not discarded. Additionally, by identifying the outlier in real-time, the automated process 100 may enable a user to immediately address any manufacturing process errors. Previously, an outlier due to a manufacturing error may have been identified after the entire batch had been produced, thus leading to the discarding of that batch. However, by enabling a user to address the manufacturing error in real-time and / or by providing guidelines for adjusting one or more settings of a manufacturing device, the automated process 100 may ensure that a given process is stopped and additional resources are not used to produce the batch until the error is addressed.

[0089] As discussed above, whereas manually drafting reports was previously a time-consuming and analytically challenging process for users, using an automated process such as process 100 can enable users to generate better, more consistent reports in a much shorter period of time. User interaction in an automated process can be reduced to simply inputting some data, telling the automated process to run, and reviewing the output.

[0090] 10 illustrates an exemplary process 1000 for a user to direct the automatic generation of a batch report, according to one or more examples. The process 1000 can be used to direct the automatic generation of a batch report using the automated process 100. The process 1000 can be implemented using one or more suitable computing devices capable of displaying a user interface to a user and recording and / or transmitting user input to the user interface. The computing device that enables the user to perform the method 1000 can be the same as the computing device that executes the automated process 100 or can be communicatively coupled to the computing device that executes the automated process 100.

[0091] In one or more examples, process 1000 may begin at step 1002 with a user selecting an analysis type. The user may use a user interface, such as user interface 200 of FIG. 2, to select the analysis type. After selecting the analysis type at step 1002, process 1000 may move to step 1004, where the user inputs required data based on the selected analysis type. The user interface through which the user inputs the required data may be user interface 300 of FIG. 3. As discussed above, the user interface that the user uses to input the required data based on the analysis type selected at step 1004 may allow the user to input, for example, a directory location, a product name, one or more data fields based on the selected analysis type, etc.

[0092] After inputting the necessary data based on the analysis type selected in step 1004, process 1000 can move to step 1006, where the user runs the program. Selecting to run the program in step 1006 can generate a user command that triggers an automated process, such as process 100, to generate a batch report. In one or more examples, selecting to run the program in step 1006 can generate and receive a user command in step 104 of process 100 of FIG. 1. After running the program in step 1006, process 1000 can move to step 1008, where the user reviews the generated report. As discussed above, the reports generated by the automated process 100 can include more sophisticated analyses and more standardized analyses and presentations of the analyses, and can be generated in a fraction of the time of manually drafted reports.

[0093] FIG. 11 illustrates an example of a computing device 1100 according to an example. The device 1100 may be a host computer connected to a network. The device 1100 may be a client computer or a server. As illustrated in FIG. 11, the device 1100 may be any suitable type of microprocessor-based device, such as a personal computer, a workstation, a server, or a handheld computing device (portable electronic device) such as a phone or tablet. The device may include, for example, one or more of a processor 1102, an input device 1106, an output device 1108, a storage 1110, and a communication device 1104. The input device 1106 and the output device 1108 may generally correspond to those described above and may be connectable to or integrated with the computer.

[0094] The input device 1106 may be any suitable device that provides input, such as a touch screen, a keyboard or keypad, a mouse, or a voice recognition device. The output device 1108 may be any suitable device that provides output, such as a touch screen, a tactile device, or a speaker.

[0095] Storage 1110 can be any suitable device that provides storage, such as electrical, magnetic, or optical memory, including RAM, cache, a hard drive, or a removable storage disk. Communications device 1104 can include any suitable device that can send and receive signals over a network, such as a network interface chip or device. The components of a computer can be connected in any suitable manner, such as via a physical bus or wirelessly.

[0096] The software 1112 that can be stored in the storage 1110 and executed by the processor 1102 can include, for example, programming that embodies functions of the present disclosure (e.g., as embodied in the devices described above).

[0097] The software 1112 may also be stored and / or transferred in any non-transitory computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as those described above, that can fetch and execute instructions associated with the software from the instruction execution system, apparatus, or device. In the context of the present disclosure, a computer-readable storage medium may be any medium, such as storage 1110, that can contain or store programming for use by or in connection with an instruction execution system, apparatus, or device.

[0098] The software 1112 may also be propagated in any transmission medium for use by or in connection with an instruction execution system, apparatus, or device, such as those described above, that can fetch instructions associated with the software from the instruction execution system, apparatus, or device and execute the instructions. In the context of this disclosure, a transmission medium may be any medium that can communicate, propagate, or transmit programming for use by or in connection with an instruction execution system, apparatus, or device. Transmission-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, or infrared wired or wireless propagation media.

[0099] The device 1100 may be connected to a network, which may be any suitable type of interconnected communication system. The network may implement any suitable communication protocol and may be protected by any suitable security protocol. The network may comprise any suitable arrangement of network links capable of effecting transmission and reception of network signals, such as wireless network communications, T1 or T3 lines, cable networks, DSL, or telephone lines.

[0100] The device 1100 may implement any operating system suitable for operating on a network. The software 1112 may be written in any suitable programming language, such as C, C++, Java, or Python. In various embodiments, application software embodying the functionality of the present disclosure may be deployed in a variety of configurations, such as, for example, in a client / server arrangement or via a web browser as a web-based application or web service.

[0101] Although the present disclosure and examples have been fully described with reference to the accompanying drawings, it should be noted that various changes and modifications will become apparent to those skilled in the art. Such changes and modifications should be understood to be included within the scope of the present disclosure and examples as defined by the claims.

[0102] Although features are described herein as part of the same or separate embodiments for clarity and concise description, it will be understood that the scope of the disclosure includes embodiments having all or any combination of the described features.

[0103] Unless otherwise defined, all technical terms, notations, and other technical and scientific terms or terminology used herein are intended to have the same meaning as commonly understood by one of ordinary skill in the art to which the claimed subject matter belongs. In some cases, terms having a commonly understood meaning are defined herein for clarity and / or ease of reference, and the inclusion of such definitions herein should not necessarily be construed as representing a substantial difference to what is commonly understood in the art.

[0104] The above description is presented to enable those skilled in the art to make and use the present disclosure, and is provided in the context of a particular application and its requirements. Various modifications to the preferred embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein. [Explanation of symbols]

[0105] 200 User Interface 201 Manufacturing 202 Analysis 204 Manufacturing User Interface 206 Analysis User Interface 300 User Interface 301 Window 302 Data Field 304 Product Name Field 306 Directory Fields 400 figure pages 402 Graph 500 Table of Contents Page Section 502 600 pages 602 table 604 Figure 700 pages, report pages 702 Subsection on Blend Uniformity 704 Assay Subsection 706 1st Percentage 708 Second Percentage 900 Batch Production Report 902 area 1100 Computing device, device 1102 Processor 1104 Communication Devices 1106 Input Devices 1108 Output Device 1110 Storage 1112 Software

Claims

1. The steps include extracting raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices, and storing the extracted raw batch data in memory. The steps include receiving a user command on a user device to automatically generate a batch report, and responding to the receipt of the user command, The steps include performing one or more statistical analyses on the stored raw batch data, The steps include generating one or more figures and one or more tables using the analyzed data, and storing the one or more figures and one or more tables in the memory, The steps include identifying one or more consideration boxes related to the analyzed data, A step of compiling a batch report including the identified one or more related consideration boxes, the one or more figures, and the one or more tables, The steps include saving the compiled batch report in memory, The steps include displaying the compiled batch report on the user device and A computer implementation method for generating batch reports, including the above.

2. The steps include identifying one or more outliers in the analyzed data, The step of determining whether the one or more outliers were caused by a manufacturing process error or by a post-manufacturing data analysis error. The computer implementation method according to claim 1, including the method described in claim 1.

3. The computer implementation method according to claim 2, wherein when one or more batch manufacturing reports are received, the raw batch data is extracted from the one or more batch manufacturing reports in real time.

4. The computer implementation method according to claim 3, further comprising the step of providing one or more guidelines for adjusting one or more settings of the one or more manufacturing devices if the outlier is caused by a manufacturing process error.

5. The one or more batch manufacturing reports include multiple batch pages, and the step of extracting the raw batch data is: The steps include receiving one or more image coordinates corresponding to one or more boundary regions within a page, The steps include: photographing each page of the aforementioned batch of pages, The steps include: collecting raw batch data located within one or more boundary regions on each of the plurality of photo-scanned batch pages; The steps include generating a ledger containing the collected raw batch data and The computer implementation method according to claim 1, including the method described in claim 1.

6. The step of compiling the aforementioned batch report is, Enter one or more statistical data values ​​from the analyzed data into one or more modifiable handles within the one or more associated consideration boxes, Based on the aforementioned related consideration box, embed the one or more figures and the one or more tables in one or more appropriate locations, To generate a data report including the one or more input related consideration boxes, the one or more embedded figures, and the one or more embedded tables. The step of generating one or more instruction codes that include instructions for, The computer implementation method according to claim 1.

7. The computer implementation method according to claim 6, wherein the one or more instruction codes include LaTeX code.

8. The computer implementation method according to claim 6, wherein one or more modifiable handles each correspond to a data metric, one or more consideration boxes contain prewritten text relating to one or more data metrics, and inputting into one or more modifiable handles includes replacing each of the modifiable handles with the corresponding data metric from the analyzed data.

9. The computer implementation method according to claim 1, wherein the compiled batch report indicates whether the analyzed data falls within the range of one or more defined batch specifications.

10. A system for generating batch reports, wherein the system Memory and One or more processors, The system comprises one or more programs, the one or more programs being stored in the memory and configured to be executed by the one or more processors, and when the one or more programs are executed by the one or more processors, the processors are configured to: Extracting raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices, and storing the extracted raw batch data in memory, The system receives user commands on the user device to automatically generate batch reports, and in response to the receipt of said user commands, Performing one or more statistical analyses on the stored raw batch data, Using the analyzed data, generate one or more figures and one or more tables, and store the one or more figures and one or more tables in the memory. Identifying one or more consideration boxes related to the analyzed data, Compiling a batch report including the one or more related study boxes, the one or more figures, and the one or more tables, The compiled batch report is stored in the memory, Display the compiled batch report on the user device. A system that makes something happen.

11. When the one or more programs are executed by the one or more processors, the processors will: Identifying one or more outliers in the analyzed data, The determination of whether the one or more outliers were caused by a manufacturing error or by a post-manufacturing data analysis error. The system according to claim 10, which causes the following:

12. The system according to claim 11, wherein when one or more batch manufacturing reports are received, the raw batch data is extracted from the one or more batch manufacturing reports in real time.

13. The system according to claim 12, wherein when the one or more programs are executed by the one or more processors, the processors are caused to provide one or more guidelines for adjusting one or more settings of the one or more manufacturing devices if the outlier is caused by a manufacturing process error.

14. The one or more batch manufacturing reports include multiple batch pages, and the raw batch data can be extracted. Receiving one or more image coordinates corresponding to one or more boundary regions within the page, The process involves photographically scanning each page of the aforementioned batch of pages, Collecting raw batch data located within one or more boundary regions on each of the plurality of photo-scanned batch pages, To generate a ledger containing the collected raw batch data and The system according to claim 10, including the system described in claim 10.

15. Compiling the aforementioned batch report Enter one or more statistical data values ​​from the analyzed data into one or more modifiable handles within the one or more associated consideration boxes, Based on the aforementioned related consideration box, embed the one or more figures and the one or more tables in one or more appropriate locations, To generate a data report including the one or more input related consideration boxes, the one or more embedded figures, and the one or more embedded tables. Includes generating one or more instruction codes that include instructions for, The system according to claim 10.

16. The system according to claim 15, wherein the one or more instruction codes include LaTeX code.

17. The system according to claim 15, wherein one or more modifiable handles each correspond to a data metric, and one or more consideration boxes contain prewritten text relating to one or more data metrics, and inputting into one or more modifiable handles includes replacing each of the modifiable handles with the corresponding data metric from the analyzed data.

18. The system according to claim 10, wherein the compiled batch report indicates whether the analyzed data falls within the range of one or more defined batch specifications.

19. A computer-readable storage medium for storing one or more programs for generating batch reports, wherein when the one or more programs are executed by an electronic device having a display and a user input interface, the device contains: Extracting raw batch data from one or more batch manufacturing reports received from one or more manufacturing devices, and storing the extracted raw batch data in memory, The system receives user commands on the user device to automatically generate batch reports, and in response to the receipt of said user commands, Performing one or more statistical analyses on the stored raw batch data, Using the analyzed data, generate one or more figures and one or more tables, and store the one or more figures and one or more tables in the memory. Identifying one or more consideration boxes related to the analyzed data, Compiling a batch report including the one or more related study boxes, the one or more figures, and the one or more tables, The compiled batch report is stored in the memory, Display the compiled batch report on the user device. A computer-readable storage medium containing instructions that cause something to happen.

Images