Product Formulation Expert System

Turner J. Product formulation expert system. Manufacturing Intelligence 1991 14 13-15. 

Bentley P. Product Formulation Expert System (PEES). In Rowe RC, Roberts RJ, Intelligent software for product formulation. London Taylor and Erancis, 1998. pp. 27-41. 

Table 1 Published applications of product formulation expert systems in pharmaceuticals...

Turner, J. Manufacturing intelligence. 1991, 8, 12-14. Bentley, P. Product formulation expert system. In Intelligent Software for Product Formulation Rowe, R.C., Roberts, R.J., Eds. Taylor and Erancis London, 1998 27-41. Bradshaw, D. The computer learns from the experts. Einancial Times London April 27th 1989, 26. 

To build a pharmaceutical formulation expert system, the formulation process has to be broken down into a number of discrete elements in order to provide distinct problem-solving tasks, each of which can be reasoned about and manipulated. However, as the formulation process is so complex, none of these tasks can be treated independently. A means of representing interactions and communicating information between tasks is therefore required. For example, one task may result in certain preferences that must be taken into account by subsequent tasks. To achieve this level of communication between tasks, the information in an expert system has to be highly structured and is therefore often represented as a series of production rules. An example of a production rule is as follows ... 

The first recorded reference to the use of expert systems in pharmaceutical product formulation was in the London Financial Times in the spring of 1989 [3], closely followed by an article in the autumn of the same year [4], Both referred to the work then being undertaken by personnel at ICI Pharmaceuticals, UK (now AstraZeneca) to develop an expert system for formulating pharmaceuticals ab initio. Since that time several companies and academic institutions have reported their experiences. 

Although there is a great deal of interest in expert systems, there is still much uncertainty regarding tangible benefits. In a survey of 74 companies in the US in 1993 [28] the main benefits identified were improved productivity, more consistent decision making, increased accuracy, and improved competitiveness. However, it is more pertinent to discuss those benefits found by users of systems in pharmaceutical formulation. These include ... 

Freeing experts. The implementation of expert systems in product formulation has inevitably allowed expert formulators to devote more... 

Of all the systems in product formulation, only one has provided costings and undertaken a cost benefit analysis. The developers of SOLTAN estimated the overall cost of their system to be 10,400 for hardware and software, 6000 for consultancy, and 9000 for expert s time, making a total of 25,400. Annual cost savings in the region of 200,000 were reported, delivering a payback of approximately 3 months. 

It is interesting to note that where expert systems have been implemented in product formulation, early skepticism among potential users has generally changed to a mood of enthusiastic participation. It is unlikely that expert systems will ever replace expert formulators, but as a decision support tool they are invaluable, delivering many measurable and intangible benefits. 

The computerized system which helps most in product development resembles more the so-called expert system, which is a set of relationships quantified by an experiment for the purpose of similar products. Such systems are increasingly more effective with the amount of data (information) increasing. Considering such need, this book will have in the future a companion CD-ROM containing a base of available data which will be periodically updated to build an incremental wealth of information serving two purposes material selection and data processing for the needs of the formulator. 

To develop a product from inception to market, the product and process have to be optimised and the process scaled up and transferred to commercial production. Definitions and descriptions of the requirements for all these stages of development are discussed in Chapter 8, although the major discussion is on the preformulation/formulation input to product optimisation. The many factors which a formulator should consider in the selection of pharmaceutical excipients and packaging are discussed. Useful sources of information and techniques for selection such as expert systems and experimental design tools are included. 

Development of a solution formulation requires a number of key pieces of preformulation information. Of these, solubility (and any pH dependence) and stability are probably the most important. Since parenteral products probably represent the most common solution formulation type, these are discussed in more detail. The principles and practices governing the formulation development of parenteral products have been reviewed by Sweetana and Akers (1996) and are discussed in detail in Chapter 9 on Parenteral Dosage Forms. Rowe et al. (1995) have described an expert system for the development of parenteral products. 

Reference to the use of expert systems in pharmaceutical product formulation first appeared on 27 April 1989 in the London Financial Times (Bradshaw 1989). This article was closely followed by one in the same year by Walko (1989). Both these authors were describing the work being undertaken by ICI (now Zeneca) Pharmaceuticals and Logica UK Ltd. to develop an expert system for formulating pharmaceuticals using PFES. Since these first publications, many companies and academic institutions have published on work being conducted in this area, as shown in Table 8.3. 

Training aid for novice formulators. Inexperienced formulators can quickly learn about a product or formulation area using an expert system. A spin-off from this is to release the time of more experienced formulators currently involved in the training process. 

Lloyd readily agreed that maximizing jet fuel production was the correct goal for our expert system. He suggested we embark immediately on the software formulation phase of the project. "All crude units are pretty much the same," he said, "and as you re a crude unit expert, we shouldn t have to waste our time at the plant site."... 

---