Application of pattern recognition for discrimination between routine analytical methods used in clinical laboratories

1981 ◽  
Vol 133 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Rob.T.P. Jansen ◽  
Frans W. Pijpers ◽  
Geert A.J.M. De Valk
Keyword(s):  
Pattern Recognition ◽  
Analytical Methods ◽  
Clinical Laboratories

A Technique for the Objective Assessment of Routine Analytical Methods in Clinical Laboratories Using Pattern Recognition

1981 ◽  
Vol 18 (4) ◽  
pp. 218-225 ◽  
Author(s):  
Rob T P Jansen ◽  
F W Pijpers ◽  
G A J M De Valk
Keyword(s):  
Pattern Recognition ◽  
Analytical Method ◽  
Analytical Methods ◽  
Dimensional Space ◽  
Objective Assessment ◽  
Control Programme ◽  
Internal Quality ◽  
Bias Drift ◽  
Clinical Laboratories

A technique is presented to assess objectively the reliability of analytical methods used routinely in clinical laboratories. From the Netherlands National Coupled External/Internal Quality Control Programme information can be gathered about the performance of routine analytical methods. The performance of a method in a trial is described by four ‘features’: the accuracy of a method; its day to-day precision; its susceptibility to give erroneous results (eg, extreme bias, drift, extreme week-to-week variations); and its susceptibility to give systematic errors for different laboratories. These four features obtained in a trial for a given analytical method determine the position of a ‘pattern’ in the four-dimensional space. The results of six trials discussed in this paper provided six ‘patterns' per analytical method. Using pattern recognition techniques, clusters of patterns were detected in the four-dimensional space. A weighting procedure revealed the relative importance of the various features for discrimination between the detected clusters. For various blood components, different features are of importance for this discrimination. Patterns belonging to the same clusters appeared to be patterns of the same (or comparable) analytical methods; thus analytical methods could be distinguished from each other. The means of the feature values of the patterns in a cluster determine the quality of that cluster. Thus the quality of an analytical method can be objectively assessed. Some tentative conclusions on the validity of analytical methods are given.

Comparison of Routine Analytical Methods in the Netherlands for Seven Serum Constituents Using Pattern Recognition

1983 ◽  
Vol 20 (1) ◽  
pp. 41-51 ◽  
Author(s):  
Rob T P Jansen
Keyword(s):  
Pattern Recognition ◽  
The Netherlands ◽  
Calcium Chloride ◽  
Analytical Method ◽  
Analytical Methods ◽  
Inorganic Phosphate ◽  
Dimensional Space ◽  
Control Program ◽  
Internal Quality ◽  
Quality Control Program

Routine analytical methods for seven serum analytes (calcium, chloride, cholesterol, glucose, inorganic phosphate, urate, and urea) are assessed using data from the Netherlands coupled external/internal quality control program. From the results of a trial each method can be described by four features: measures of bias, between-day precision, tendency to give erroneous results, interlaboratory variance. These four features of each trial determine a vectorpoint in the four-dimensional space for a particular method. From 12 trials a maximum of 12 vectorpoints per analytical method was obtained. Pattern recognition techniques allowed the detection of clusters of vectorpoints. Analytical methods having vectorpoints classified in different clusters perform differently. The mean feature values of the vectorpoints forming a cluster determine the quality of that cluster. A weighting procedure reveals the importance of the respective features for discriminating the clusters. For all of the seven analytes, clusters of vectorpoints were found. Different features appeared to contain discriminatory power for different analytes. For six analytes (calcium, chloride, cholesterol, glucose, inorganic phosphate, and urea) an analytical method was found to classify predominantly in the qualitative best cluster. One analytical method for the determination of chloride and one for glucose, inorganic phosphate, and urea did not cluster at all.

scholarly journals Benchmarking workflows to assess performance and suitability of germline variant calling pipelines in clinical diagnostic assays

2019 ◽  
Author(s):  
Vandhana Krishnan ◽  
Sowmi Utiramerur ◽  
Zena Ng ◽  
Somalee Datta ◽  
Michael P. Snyder ◽  
...  
Keyword(s):  
Analytical Methods ◽  
Variant Calling ◽  
Regions Of Interest ◽  
Diagnostic Assays ◽  
Clinical Laboratories ◽  
Germline Variant ◽  
Clinical Diagnostic ◽  
Reference Samples

AbstractBenchmarking the performance of complex analytical pipelines is an essential part of developing Laboratory Developed Assays (LDT). Reference samples and benchmark calls published by Genome in a Bottle (GIAB) Consortium have enabled the evaluation of analytical methods. However, the performance of such methods is not uniform across the different regions of the genome/exome and different variant types and lengths. Here we present a scalable and reproducible, cloud-based benchmarking workflow that can be used by clinical laboratories to rapidly access and validate the performance of LDT assays, across their regions of interest and reportable range, using a broad set of benchmarking samples.

Proficiency testing for creatine kinase isoenzyme CK-2 (CK-MB) in Ontario

1990 ◽  
Vol 36 (12) ◽  
pp. 2102-2105 ◽  
Author(s):  
M J McQueen ◽  
R L Patten ◽  
A R Henderson ◽  
S Krishnan ◽  
D E Wood ◽  
...  
Keyword(s):  
Creatine Kinase ◽  
Proficiency Testing ◽  
Analytical Methods ◽  
Immunological Methods ◽  
Reference Ranges ◽  
Testing Material ◽  
Creatine Kinase Isoenzyme ◽  
Clinical Laboratories ◽  
Frequency Of Use ◽  
Survey Results

Abstract Three surveys of the measurement and interpretation of creatine kinase (CK; EC 2.7.3.2) isoenzyme 2 (CK-MB) were conducted in Ontario, Canada, in 1989. Of the clinical laboratories participating, 66% used immunological methods and 24% used electrophoretic methods. Although reference ranges and interpretative routines varied widely, 95% of the laboratories reported correct interpretations for 10 of the 15 vials tested. The only major problems occurred with samples with very low total CK activity. Within-survey duplicate results compared well, and 89% of the laboratories had consistent between-survey results, even for specimens with low total CK activity. Errors were proportional to the frequency of use of the different analytical methods. The lyophilized testing material gave higher results with methods for measuring the mass of CK-2, suggesting that the material contained inactive but immunologically intact CK-2. The surveys indicate that laboratories should review their protocols for measuring CK-2 when only a single sample from the patient is available.

Automated antinuclear immunofluorescence antibody analysis is a reliable approach in routine clinical laboratories

2017 ◽  
Vol 55 (12) ◽  
Author(s):  
Bing Zheng ◽  
Enling Li ◽  
Haoming Zhu ◽  
Jingbo Lu ◽  
Xinming Shi ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Value Added ◽  
Recognition System ◽  
Automated System ◽  
Serum Samples ◽  
Gold Standard Method ◽  
Cutoff Value ◽  
Clinical Laboratories ◽  
Automatic Pattern Recognition ◽  
Immunofluorescence Antibody

AbstractBackground:Indirect immunofluorescence (IIF) assays are recommended as the gold standard method for the detection of antinuclear antibodies (ANAs). This study aimed to investigate the reliability of an automated system.Methods:We compared 3745 serum samples using NOVA View archived images with manual analysis via microscopy. A custom cutoff value was established to distinguish ANA titers and was validated in two clinical laboratories. The automatic ANA pattern recognition system was evaluated, and all ANA-positive sera were subjected to two commercial ANA IIF kits to compare the consistency of the pattern interpretation results. For inconsistent patterns, a third ANA IIF testing kit was utilized.Results:Agreement of the interpretation of the ANA IIF test using the platform of NOVA View and manual microscopy was 96.9%. The local cutoff value to discriminate ANA titers in four main ANA patterns was calculated based on 1390 serum samples. In our laboratory, the titer prediction accuracy was superior to the preset cutoff in NOVA View (p<0.01); the performance was similar in another laboratory (p=0.11). The automatic pattern recognition accuracies of speckled, homogeneous, centromere, nucleolar and nuclear dot patterns were 62.7%, 57.4%, 92.6%, 30.5% and 27.3%, respectively. The consistency of the pattern interpretation results between INOVA and MBL kits was 95.3%.Conclusions:It is necessary to establish a custom value-added ANA report. However, confirmation of the digital immunofluorescence images by expert technicians was essential, and suspect results of an ANA pattern should be reconfirmed by another commercial ANA IIF kit to achieve more reliable results.

Utilizing Dark Field Electron Microscopy to Produce Lantern Slides

1974 ◽  
Vol 32 ◽  
pp. 116-117
Author(s):  
J. N. Meador ◽  
C. N. Sun ◽  
H. J. White
Keyword(s):  
Electron Microscope ◽  
Electron Micrographs ◽  
Dark Field ◽  
Limiting Factor ◽  
Clinical Laboratories ◽  
Field Electron ◽  
Time Element ◽  
Field Electron Microscopy ◽  
Dark Field Electron ◽  
Dark Field Micrographs

The electron microscope is being utilized more and more in clinical laboratories for pathologic diagnosis. One of the major problems in the utilization of the electron microscope for diagnostic purposes is the time element involved. Recent experimentation with rapid embedding has shown that this long phase of the process can be greatly shortened. In rush cases the making of projection slides can be eliminated by taking dark field electron micrographs which show up as a positive ready for use. The major limiting factor for use of dark field micrographs is resolution. However, for conference purposes electron micrographs are usually taken at 2.500X to 8.000X. At these low magnifications the resolution obtained is quite acceptable.

Software pattern recognition applied to nanodiffraction patterns from a STEM instrument

1986 ◽  
Vol 44 ◽  
pp. 694-695
Author(s):  
G.Y. Fan ◽  
J.M. Cowley
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Computer Software ◽  
Processing System ◽  
Light Level ◽  
Host Computer ◽  
Low Light ◽  
Image Processing System ◽  
Recent Developments ◽  
On Line

In recent developments, the ASU HB5 has been modified so that the timing, positioning, and scanning of the finely focused electron probe can be entirely controlled by a host computer. This made the asynchronized handshake possible between the HB5 STEM and the image processing system which consists of host computer (PDP 11/34), DeAnza image processor (IP 5000) which is interfaced with a low-light level TV camera, array processor (AP 400) and various peripheral devices. This greatly facilitates the pattern recognition technique initiated by Monosmith and Cowley. Software called NANHB5 is under development which, instead of employing a set of photo-diodes to detect strong spots on a TV screen, uses various software techniques including on-line fast Fourier transform (FFT) to recognize patterns of greater complexity, taking advantage of the sophistication of our image processing system and the flexibility of computer software.

Sign in / Sign up

Export Citation Format

Share Document