Using data analysis to optimize a pharmaceutical process manufacturing cycle. (Data Analysis).

I Discoverant helps improve stability and cut costs

In the pharmaceutical and biotechnology manufacturing industry it has typically been the rule that in order to preserve or, in the best of situations, increase the bottom line, a company must choose between quality and efficiency. Between the increase in regulatory demands and greater market competition, companies are forced to find ways to sustain a competitive advantage, meet FDA mandates and maintain reasonably low costs. Compliance pressures, such as the need to resolve atypical performance, investigate deviations and maintain a validated process, could result in product recalls and FDA fines. Inefficient operations can slow time-to-market, increase lost batches and reduce throughput. General business and market pressures, including the increasing demand for research, shrinking windows of opportunity and rising marketing costs, are constantly threatening the bottom line of manufacturing companies. With these threats weighing equally in importance and urgency, it is frequently difficult for companies to find ways to balance their reactions, often opting to implement point solutions that provide symptomatic relief.

To see past the symptom, be it regulatory infractions, batch delays or lot failures, a company must be able to compile and analyze its data in order to pinpoint which parameters most impact performance and predictability. The required manufacturing process data is frequently scattered across the enterprise network in laboratory information management systems (LIMS), supervisory control and data acquisition systems (SCADA)/distributed control systems (DCS), manufacturing execution systems (MES), enterprise resource planning systems (ERP) and batch record systems. It is data that may only exist on paper, that can only by accessed through requests that can take weeks (and an SQL programmer) to fill or that requires a data analyst to interpret. This lack of integration makes it nearly impossible for manufacturers to overcome their inefficiencies or increase the quality of their products, highlighting the extreme need for the acquisition and synthesis of data.

Since data acquisition is such a pivotal requirement, pharmaceutical manufacturers have been impelled to employ systems that are only partial solutions at best. With today's technological possibilities, companies are demanding new, more comprehensive software to access the required information. Aegis Analytical Corporation has created Discoverant, an enterprise-class software solution that offers access to all of the data created in the manufacturing process. Discoverant integrates connectivity technology with analytical tools to produce a process-centric view of the manufacturing data located in disparate systems across the enterprise and gives decision-makers access to actionable intelligence. The following case study illustrates the benefits Discoverant can provide for pharmaceutical manufacturers.

The Situation

A leading pharmaceutical manufacturer wanted to find a more effective way of minimizing lot failures and increasing process stability. The management team knew this would have a significantly positive impact on their profitability. Stand-alone applications such as statistics and graphics packages had previously been used at the facility for this purpose, but provided less than ideal results. These partial solutions required that more than 50 percent of their analysis time be spent on non-analytical tasks such as gathering, conditioning, formatting, importing and exporting data between applications. This inefficiency translated into decreased plant capacity and lost opportunities for process stabilization. More importantly, they had not been able to resolve the problem of high failure rates.

Although the company already had a variety of measurement systems in place, each designed to record process parameters and store the acquired data, none of them compiled the information from the disparate databases and offered it in an intelligible format. Since the data was crucial to the running of the manufacturing plant, the company had to find a system that provided a comprehensive view of all process information, along with the ability to analyze it for decision-making purposes. The manufacturer needed to identify all the key process drivers to determine their combined effects on the process outcome, namely the Tablet Dissolution Rate. The team also wanted useful methods for reporting key process parameters and outcomes, including process signatures, for making informative comparisons between groups of lots.

The Solution

Using Discoverants' analysis and visualization capabilities, the manufacturer was able to efficiently analyze data from over 60 product batches from one pharmaceutical manufacturing campaign. The manufacturing-related data needed for statistical analysis and visualization at this facility was stored in several locations. SCADA and DCS were being used to monitor instruments, control process parameters at their set points, and to archive these measurements in a process data historian. Associated lot-history and product-quality data was found in several other locations such as in the LIMS and ERP systems, as well as on paper records. Historically, it had been very difficult and time-consuming to manually gather and analyze all the data for a particular lot or group of lots. Discoverant solved this problem by providing a single, process-centric view of the combined data with point-and-click access to all the manufacturing-related databases on the corporate network. It also allowed easier input of data from paper records. Implementing a system like Discoverant at the facility sped their ability to get useful information out of increasingly large manufacturing databases. In the end, Discoverant offered an integrated, user-friendly, enterprise-wide data analysis and visualization software solution to these barriers.

The Data Analysis

The following general work flows were used for the analysis reported in this study:

Correlated Variables Identified. Discoverant created a customized matrix to look for single pairs of correlated variables. The matrix used all available data. Missing values were replaced with the mean of the remaining values using data-conditioning routines. Discoverant's ability to do this type of data conditioning can be extremely valuable when compensating for the effects of missing data, a benefit not readily available in most statistics packages.

Outcome Modeled. Principal Component Analysis and Stepwise Multiple Linear Regression (PCA/SMLR) were used to condense the correlation information in the raw variables into a set of key factors. These factors were then used to model the outcome variables using SMLR with cross-validation. This multivariate analysis method is called "Principal Component Regression" or PCR.

Patterns Identified. Discoverant used static and animated multi-dimensional imaging techniques to show patterns in the data. This allowed examination of the behavior of key process parameters in groups of lots ranked either by lot number (production date) or by the process outcome parameter (Tablet Dissolution Rate). Cusum charts were used to analyze historical process performance. This analysis showed that several changes had occurred in the manufacturing process, perhaps inadvertently, which caused changes in the averages for the outcome variables at specific dates. Once this pattern of process drift was detected, Cusum plots helped target the lot numbers at which possible changes occurred. Standard control charts were already in use to monitor the manufacturing process at the facility, but using Cusum plots to supplement standard SPC charts proved to be much more informative.

Key Process Drivers Displayed. Discoverant created sophisticated Visual Process Signatures. These Signatures used a single, animated image to display the relationships of many factors to each other, to the rest of the data and to the process outcomes. Combining multi-dimensional visual enhancements of the tabular information along with the quantitative results of the PCR analysis, the Visual Process Signatures also provided a clear and independent confirmation of the major quantitative findings in a readily understandable form. This was especially beneficial for those whose core technical expertise was in areas other than statistics but who did have a high degree of influence over process outcomes. By illustrating how and why their process was performing the way it was, without resorting to tables of numbers and statistics, they quickly achieved significant enhancements in process performance.

Discoverant displayed the Process Signatures as dynamic images that were rotated in three dimensions on the screen to show additional information. Historical performance of the manufacturing process also was displayed as rolling average Visual Process Signatures for selected groups of lots, for the complete set of parameters and then as the selected group of parameters of most interest.

The Outcome

Using PCR, the combination of the most critical, controllable process parameters was identified. Discoverant found the smallest combination of process parameters that had the greatest effect on the process outcomes. There were only five such parameters and they were located in widely disparate parts of the process. Specific recommendations for process improvements were then formulated based on the combination of key process indicators that Discoverant had identified.

For all the data used in this study, the process parameters for each batch had been operated within their ranges. Therefore, the manufacturer was able to test Discoverant's findings directly within the manufacturing process without the need for additional small-scale experimentation--a major cost advantage of retrospective data analysis. Process improvement recommendations were derived from variations that occurred in the manufacturing process when operated under approved conditions. When implemented, the recommended changes allowed the manufacturing staff to bias their process toward the best possible outcomes without the need to change their manufacturing technology or to have their processes re-approved by the FDA, which equals a tremendous savings in time and money. The bottom line impact of this implementation included a significant reduction in atypicals by stabilizing table dissolution rates, lowering failure rates to increase yield by 25 percent--ultimately improving the bottom line by more than $5 million per plant per year.

The Future

Throughout the pharmaceutical and biotechnology sectors there are billions of dollars in unnecessary costs waiting to be reclaimed by holistically optimizing the process manufacturing cycles. The future success of each of these manufacturing companies will depend upon its ability to ensure lasting, corporate-wide improvement, predict quality, decrease time to market and reduce FDA regulatory failure risk.

Justin Neway, Ph.D., is Executive VP and Chief Science Officer at Aegis Analytical Corporation. He may be reached at editor@scimag.com.

Athleta coupon code