Home Computer-assisted detection of monoclonal components: results from the multicenter study for the evaluation of CASPER (Computer Assisted Serum Protein Electrophoresis Recognizer) algorithm
Article
Licensed
Unlicensed Requires Authentication

Computer-assisted detection of monoclonal components: results from the multicenter study for the evaluation of CASPER (Computer Assisted Serum Protein Electrophoresis Recognizer) algorithm

  • Agostino Ognibene , Maria S. Graziani , Anna Caldini , Alessandro Terreni , Gabriella Righetti , Maria C. Varagnolo , Ada Campanella , Marinella Martelli , Rita Mancini , Paolo Rizzotti , Mario Plebani , Marco Mori , Giovanni Gaspari , Roberto Motta , Gianni Galli , Massimiliano Fabris and Gianni Messeri
Published/Copyright: August 1, 2008

Abstract

Background: To investigate the potential use of Artificial Neural Network (ANN) in the evaluation of serum protein electrophoresis, we set up a multicenter study involving six Italian laboratories. For this purpose, we developed an algorithm named CASPER (Computer Assisted Serum Protein Electrophoresis Recognizer).

Methods: A total of 59,516 samples from the six centers were divided into three groups. Training and validation sets were used to develop the neural network, whereas evaluation set was used to test the performance of CASPER in recognizing abnormal electrophoretic profiles.

Results: CASPER showed 93.0% sensitivity and 47.4% specificity. CASPER sensitivity and specificity ranged in the six sites from 88% (site 3) to 97% (site 5) and from 36% (site 6) to 53% (site 3), respectively. Sensitivity for γ zone was 94.6%, for β zone 89.7% and for oligoclonal patterns 92.0%.

Conclusions: The sensitivity of the CASPER algorithm does not allow us to recommend its use as a replacement for the visual inspection, but it could be helpful in avoiding accidental misclassifications by the operator. Moreover, the CASPER algorithm may be a useful tool for training operators and students. This study evidenced a high inter-observer variability, which should be addressed in a dedicated study. Data set to train and validate ANNs should contain a huge range and an adequate number of different abnormalities.

Clin Chem Lab Med 2008;46:1183–8.


Corresponding author: Agostino Ognibene, Laboratorio Generale, Dipartimento di Laboratorio, Piastra dei Servizi, Azienda Ospedaliero Universitaria Careggi, Viale Morgagni 85, 50139 Florence, Italy Phone: +39-055-4279424, Fax: +39-055-4279416,

Received: 2007-11-30
Accepted: 2008-4-1
Published Online: 2008-08-01
Published in Print: 2008-08-01

©2008 by Walter de Gruyter Berlin New York

Articles in the same Issue

  1. Review
  2. Insulin-like growth factor-I and complications of prematurity: a focus on bronchopulmonary dysplasia
  3. Minireview
  4. Highly sensitive thyroglobulin measurements in differentiated thyroid carcinoma management
  5. Genetics and Molecular Diagnostics
  6. Proteomic pattern of plasma in off-pump coronary artery bypass surgery
  7. Association of CHRNA2 polymorphisms with overweight/obesity and clinical characteristics in a Korean population
  8. Relevance of glutathione S-transferase M1 and cytochrome P450 1A1 genetic polymorphisms to the development of head and neck cancers
  9. Association of the insertion/deletion gene polymorphism of the apolipoprotein B signal peptide with myocardial infarction in Tunisian patients
  10. The influence of smoking and homocysteine on subclinical atherosclerosis is modified by the connexin37 C1019T polymorphism – The Cardiovascular Risk in Young Finns Study
  11. Tests for the measurement of factor VII-activating protease (FSAP) activity and antigen levels in citrated plasma, their correlation to PCR testing, and utility for the detection of the Marburg I-polymorphism of FSAP
  12. An improved quality control for bisulfite-PCR-based DNA methylation analysis: cycle threshold value
  13. General Clinical Chemistry and Laboratory Medicine
  14. Can E-cadherin and CD34 be used as indicators of prognosis for hepatocellular carcinoma patients?
  15. Determination of serum creatinine by Jaffe method and how to calibrate to eliminate matrix interference problems
  16. Calcium oxalate stone formation risk – a case of disturbed relative concentrations of urinary components
  17. Half-lives of albumin and cholinesterase in critically ill patients
  18. Early detection of an early onset infection in the neonate based on measurements of procalcitonin and C-reactive protein concentrations in cord blood
  19. Serum neopterin, nitric oxide, inducible nitric oxide synthase and tumor necrosis factor-α levels in patients with ischemic heart disease
  20. Estimation of serum M-protein concentration from polyclonal immunoglobulins: an alternative to serum protein electrophoresis and standard immunochemical procedures
  21. Are serum lipids measured on stroke admission prognostic?
  22. Reference Values and Biological Variations
  23. Pre-analytical variation of some haematological quantities
  24. Long-term stability of endogenous B-type natriuretic peptide after storage at –20°C or –80°C
  25. Can both EDTA and citrate plasma samples be used in measurements of fibrinogen and C-reactive protein concentrations?
  26. Non-homogeneous separation of triglycerides, γ-glutamyltransferase, C-reactive protein and lactate dehydrogenase after centrifugation of lithium-heparin tubes
  27. Validation and Outcome Studies
  28. Computer-assisted detection of monoclonal components: results from the multicenter study for the evaluation of CASPER (Computer Assisted Serum Protein Electrophoresis Recognizer) algorithm
  29. Quality indicators and specifications for strategic and support processes in laboratory medicine
  30. Evaluation of the DCA Vantage analyzer for HbA1c assay
  31. Letters to the Editor
  32. Optimization of imprecision and cost saving on hemoglobin A1c controls through aliquot freezing
  33. Estimation of glomerular filtration rate by the modification of diet in renal disease (MDRD) equation in patients with sickle cell disease
  34. Abstracts
  35. Swiss MedLab 2008: International Congress, September 16–19, 2008, Montreux, Switzerland
  36. 4th Biologie Prospective Santorini Conference, September 21–23, 2008, Santorini, Greece
Downloaded on 10.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/CCLM.2008.221/html
Scroll to top button