Peter Wilding

Application of backpropagation neural networks to diagnosis of breast and ovarian cancer

Neural network programs have been developed in an attempt to improve the diagnosis of breast and ovarian cancer using a group of laboratory tests and the age of the patient. The laboratory tests employed in this study include albumin, cholesterol, HDL-cholesterol, triglyceride, apolipoproteins A1 and B, NMR linewidth (the Fossel Index) and a tumor marker (i.e., CA 15-3 or CA 125). The breast cancer study involved 104 patients (45 malignant and 59 benign subjects). The ovarian cancer study involved 98 individuals (35 malignant, 36 benign and 27 control subjects). Methods are outlined for identification of the most influential input parameters and optimization of network structure and training. Network characteristics were contrasted with the test results of the appropriate serum tumor marker assay. For the breast cancer study, the best neural network program, using six input parameters, had a sensitivity of only 55.6% and a specificity of 72.9%. The tumor marker CA 15-3 alone gave results of 61.3% and 64.4%, respectively. For the ovarian cancer study, the best neural network program, using six input parameters, had a sensitivity of 80.6% and a specificity of 85.5%. The tumor marker CA 125 alone gave results of 77.8% and 82.3%, respectively. These methods provide an objective approach to neural network optimization and parameter selection applicable to other data bases of clinical and laboratory data.

Analysis of ligase chain reaction products amplified in a silicon-glass chip using capillary electrophoresis.

Ligase chain reaction (LCR) is a useful molecular technique for detecting known point mutations. We report the first example of the use of a disposable silicon-glass micro-chip for LCR and the first application of capillary electrophoresis (CE) to analyze samples amplified by LCR in a chip. Silicon-glass chips were manufactured using conventional photolithography and anodic bonding. The chips provide three distinct advantages for LCR: excellent thermal conductivity, a micro reaction volume ( < 10 microliters), and reproducible, low-cost manufacturing. Investigation and quantitation of amplification efficiency of LCR in a chip or in a tube requires an analytical technique that is faster and more convenient than the conventional slab gel methods. Slab gel electrophoresis uses relatively large amounts of sample and is labor-intensive and time-consuming, and thus is unsuitable for the separation and detection of LCR products. In contrast CE requires sample volume (original LCR products) of less than 1 microliter and is therefore well-suited to analysis of the micro-volume reaction mixture from chips. We combined CE with a sensitive laser induced fluorescence (LIF) detection system for the rapid separation and quantitative detection of LCR products amplified from the lacI gene in a silicon-glass chip. Comparative studies were made with LCR between tubes and silicon-glass chips. CE-LIF analysis is ideally suited to examination of micro-LCR amplification with high throughput. The technologies may find medical uses in disease diagnosis and research.

Micromachining: A new direction for clinical analyzers

Conventional analytical reactions are performed in test tubes, but in the future, reactions may be routinely performed in minute chambers micromachined in small silicon or glass chips. Disposable micromachined devices are : easily designed, low cost, small, portable, easy and fast to operate, use micro volumes of sample and reagents, are adaptable for simultaneous multiple-assays, and provide system integration. We have constructed micromachined devices for semen analysis, in vitro fertilization (IVF), PCR, and immunoassay. The key structural element of the sperm chips (silicon-glass and glass-glass) is a tortuous channel for assessment of sperm motility. IVF chips consist of a semen application chamber and an egg nesting chamber separated by a tortuous sperm selection channel. Chips were evaluated for IVF using the mouse model, and fertilization and growth from 2 cell to the blastocyst stage was successfully demonstrated. Silicon-glass chips containing 4080 um deep micro-chambers were effective for PCR reactions. Excellent thermal conductivity of the silicon, plus the high surface/volume ratio (>20 mm2/uL) provides efficient heat transfer. This PCR chip (volume, approx 10 uL) was successfully used to amplify a range of targets (e.g., bacteriophage lambda, Campylobacter jejuni) .

The application of thin-layer gel filtration chromatography in the rapid assessment of protein-protein coupling reactions

The use of enzymes as markers when covalently coupled to various antigens or antibodies has wide application in medical science. A variety of bifunctional reagents has been used to produced the conjugates, and there have been some attempts to investigate the conditions of reaction necessary to obtain good coupling, whilst preserving the biological function of the molecules. The present study describes the influence of coupling conditions on the coupling of a alpha-amylase and albumin by a range of commercially available bifunctional coupling reagents, and the application of thin-layer gel filtration chromatography for the rapid qualitative/semi-quantitative assessment of coupling reactions.

Opportunities and Obstacles to the Routine Implementation of Microchips

Miniaturization is an important and active area of development in the analytical sciences. Small, portable, inexpensive micro miniature analyzers (microchips, lab-on-a-chip, micro arrays, gene chips, bio electronic chips) are advantageous and have been developed to perform a number of analytical techniques. Despite the opportunities for microchip analyzers in the clinical laboratory, there are still important obstacles associated with their use, such as user-friendly interfaces between a human and a microchip and the level of micro miniaturization that is desirable or practical. This chapter examines the opportunities and obstacles to the routine implementation of microchips, with an emphasis on the clinical and biomedical applications.