Towards properly controlled analytical measurement methods

It is of great practical importance to develop simple methods for the automatic detection ofthe controlled state of the analytical method being applied. The key point is to find quantities that greatly affect the quality of the analytical results and that can be easily estimated during the measurement process from the measured data. The signal-to-noise ratio has proved to be such a quantity in gas chromatographic methods. The statistical properties of the estimation of the signal-to-noise ratio from gas chromatographic data have been investigated. The suggested practical method for estimating the signal-to-noise ratio proved to be biased from a mathematical statistical point of view, but the bias is usually not greater than 10%. It has been shown by practical examples that the signal-to-noise ratio affects the quality of the analytical results and it is easy to estimate its value from practical data.     

The role of the automation development group in analytical research and development at Dupont Merck

Laboratory robotics has been firmly established in many non-QC laboratories as a valuable tool for automating pharmaceutical dosage form analysis. Often a single project or product line is used to justify an initial robot purchase thus introducing robotics to the laboratory for the first time. However, to gain widespread acceptance within the laboratory and to justify further investment in robotics, existing robots must be used to develop analyses for existing manual methods as well as new projects beyond the scope off the original purchase justification. The Automation Development Group in Analytical Research and Development is a team of analysts primarily devoted to developing new methods and adapting existing methods for the robot. This team approach developed the expertise and synergy necessary to significantly expand the contribution of robotics to automation in the authors'' laboratory.     

Use of artificial intelligence in analytical systems for the clinical laboratory

The incorporation of information-processing technology into analytical systems in the form of standard computing software has recently been advanced by the introduction of artificial intelligence (AI), both as expert systems and as neural networks.This paper considers the role of software in system operation, control and automation, and attempts to define intelligence. AI is characterized by its ability to deal with incomplete and imprecise information and to accumulate knowledge. Expert systems, building on standard computing techniques, depend heavily on the domain experts and knowledge engineers that have programmed them to represent the real world. Neural networks are intended to emulate the pattern-recognition and parallel processing capabilities of the human brain and are taught rather than programmed. The future may lie in a combination of the recognition ability of the neural network and the rationalization capability of the expert system.In the second part of the paper, examples are given of applications of AI in stand-alone systems for knowledge engineering and medical diagnosis and in embedded systems for failure detection, image analysis, user interfacing, natural language processing, robotics and machine learning, as related to clinical laboratories.It is concluded that AI constitutes a collective form of intellectual propery, and that there is a need for better documentation, evaluation and regulation of the systems already being used in clinical laboratories.     

Integrated laboratory information system in a large hospital laboratory in Singapore

This paper describes an integrated approach to the computerization of all major disciplines of laboratory medicine and pathology. Installed in the Department of Pathology, Singapore General Hospital (SGH), the computer system discussed comprises a RISC-based Data General Aviion 6200 computer and Meditech MAGIC software. The system has been interfaced with the hospital host IBM computer and supports patient information transfer, result reporting, phlebotomy management, and compilation of laboratory and financial management reports. The main functions of the system include: on-line and off-line acquisition of patient information and test data; preparation of single/combined/cumulative reports; transmission of reports within and between laboratories; instantaneous provision of data in response to telephone enquiries; calculations of quality control/workload/productivity statistics and indices; and generation of billing lists. The computer enables reports to be provided on patient tests results in individual wards, at various specialist out-patient clinics, and in the Accident and Emergency Department of the SGH through the IBM mainframe, as well as to remote printers installed at several other major hospitals.The use of the MAGIC integrated laboratory information system has resulted in a significant increase in laboratory efficiency and productivity.