Application of probabilistic neural network in the clinical diagnosis of cancers based on clinical chemistry data

As a recently developed and powerful classification tool, probabilistic neural network was used to distinguish cancer patients from healthy persons according to the levels of nucleosides in human urine. Two datasets (containing 32 and 50 patterns, respectively) were investigated and the total consistency rate obtained was 100% for dataset 1 and 94% for dataset 2. To evaluate the performance of probabilistic neural network, linear discriminant analysis and learning vector quantization network, were also applied to the classification problem. The results showed that the predictive ability of the probabilistic neural network is stronger than the others in this study. Moreover, the recognition rate for dataset 2 can achieve to 100% if combining, these three methods together, which indicated the promising potential of clinical diagnosis by combining different methods. (C) 2002 Elsevier Science B.V. All rights reserved.

Automation in clinical chemistry.

Bibliography: p. 115-125.

Biological and clinical chemistry,

Bibliography at end of each chapter.

Photelometric clinical chemistry,

Bibliography at end of each chapter.

Quantitative clinical chemistry

Mode of access: Internet.

Stabilization of troponin I for applications in clinical chemistry and forensic medicine. Cardiac troponin I: A time of death marker

Cardiac troponin I (cTnI) is one of the most useful serum marker test for the determination of myocardial infarction (MI). The first commercial assay of cTnI was released for medical use in the United States and Europe in 1995. It is useful in determining if the source of chest pains, whose etiology may be unknown, is cardiac related. Cardiac TnI is released into the bloodstream following myocardial necrosis (cardiac cell death) as a result of an infarct (heart attack). In this research project the utility of cardiac troponin I as a potential marker for the determination of time of death is investigated. The approach of this research is not to investigate cTnI degradation in serum/plasma, but to investigate the proteolytic breakdown of this protein in heart tissue postmortem. If our hypothesis is correct, cTnI might show a distinctive temporal degradation profile after death. This temporal profile may have potential as a time of death marker in forensic medicine. The field of time of death markers has lagged behind the great advances in technology since the late 1850's. Today medical examiners are using rudimentary time of death markers that offer limited reliability in the medico-legal arena. Cardiac TnI must be stabilized in order to avoid further degradation by proteases in the extraction process. Chemically derivatized magnetic microparticles were covalently linked to anti-cTnI monoclonal antibodies. A charge capture approach was also used to eliminate the antibody from the magnetic microparticles given the negative charge on the microparticles. The magnetic microparticles were used to extract cTnI from heart tissue homogenate for further bio-analysis. Cardiac TnI was eluted from the beads with a buffer and analyzed. This technique exploits banding pattern on sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS-PAGE) followed by a western blot transfer to polyvinylidene fluoride (PVDF) paper for probing with anti-cTnI monoclonal antibodies. Bovine hearts were used as a model to establish the relationship of time of death and concentration/band-pattern given its homology to human cardiac TnI. The final concept feasibility was tested with human heart samples from cadavers with known time of death. ^

A discussion of cases in the 2001 RCPA-AQAP chemical pathology case report comments program

Aim: We present a descriptive analysis of the 10 case reports distributed in the Royal College of Pathologists of Australasia (RCPA) and the Australasian Association of Clinical Biochemists (AACB) Chemical Pathology Patient Report Comments Program to assess the quality of interpretative commenting in clinical biochemistry in 2001. Method: Participants were asked to comment on a given set of biochemistry results attached with brief clinical details. All responses received were translated into key phrases and graphically presented on a histogram. An expert panel was asked to evaluate the appropriateness of the key phrases and to propose a suggested composite comment. Results: While the majority of comments received were felt to be acceptable by the expert panel, some comments were felt to be inappropriate or misleading. As comments on laboratory reports may affect clinical management of patients, it is important that these comments reflect accepted practice and current guidelines. Conclusion: The Patient Report Comments Program may play an important role in continuing education and possibly in quality assurance of interpretative commenting.

Vitamin A is associated with the inflammatory marker CRP in cystic fibrosis

We have observed that vitamin A levels, deficient in patients with severe disease, returned to normal post lungtransplant independent of oral supplementation or pancreatic sufficiency. We hypothesised that vitamin A is associated with disease severity and the inflammatory marker C-related peptide (CRP). Data from RCH paediatric and TPCH adult CF clinic subjects (ns138 CF, 138 control, aged 5–56 yr), who had participated in a study of bone mineral density (BMD) in which vitamins A, E, D, and CRP, height, weight and lung function had been measured was used. Groups were compared using t- or Wilcoxon-tests, and predictors of vitamin A examined usingmultiple regression. Vitamin A was lower in CF subjects (1.23"0.5 vs. 1.80"0.6 mmolyl, P-0.0001), increasingwith age in paediatric subjects but to a lesser extent in the CF group (Ps0.0007). CRP was correlated with age (rs0.6, P-0.0001). FEV1% predicted (FEV) (57.93"23.0 vs. 70.63"21.8, Ps0.0014), weight z-score (WTZ) (y0.76"0.9 vs. y0.12"1.0, Ps0.0002), lumbar spine BMD z-score (y1.08"1.3 vs. y0.50"1.2, Ps0.009) were lower, and CRP higher (median 7.0, IQR 2–4 vs. median 1.0, IQR 1–3 mgy l, P-0.0001) in vitamin A insufficient CF subjects (61 insufficient vs. 71 sufficient). In all subjects, control status (P-0.0001), WTZ (Ps0.02), vitamin E (Ps 0.0003), CRP (Ps0.001), 1,25 dihydroxy vitamin D (1,25 vit. D) (Ps0.0007), and child, adolescent or adult grouping (all P-0.0001) were predictive of vitamin A. In the CF group, CRP (Ps0.01), Vitamin E (P-0.0001) and 1.25 vit. D (Ps 0.006), but not FEV, were predictive. The normal increase in vitamin A with age was not observed in CF subjects, who had lower levels at any age. This failure of normal increase in vitamin A had a consistent association with increasingCRP , supportingthe hypothesis that increased inflammation may result in increased vitamin A consumption.