Home Medicine Classification tree analysis for the discrimination of pleural exudates and transudates
Article
Licensed
Unlicensed Requires Authentication

Classification tree analysis for the discrimination of pleural exudates and transudates

  • Aureli Esquerda , Javier Trujillano , Ignacio López de Ullibarri , Silvia Bielsa , Ana B. Madroñero and José M. Porcel
Published/Copyright: January 24, 2007
Clinical Chemistry and Laboratory Medicine (CCLM)
From the journal Volume 45 Issue 1

Abstract

Background: Classification and regression tree (CART) analysis is a non-parametric technique suitable for the generation of clinical decision rules. We have studied the performance of CART analysis in the separation of pleural exudates and transudates.

Methods: Basic demographic, radiologic and laboratory data were retrospectively evaluated in 1257 pleural effusions (204 transudates and 1053 exudates, according to standard clinical criteria) and submitted for CART analysis. The model's discriminative ability was compared with that of Light's criteria, in both the original formulation and an abbreviated version, i.e., deleting the pleural fluid (PF)/serum lactate dehydrogenase (LDH) ratio from the triad.

Results: A first CART model built starting from all available data identified PF/serum protein ratio and PF LDH ratios as the two best discriminatory parameters. This algorithm achieved a sensitivity of 96.8%, slightly lower than that of classical Light's criteria (98.5%) and comparable to that of the abbreviated Light's criteria (97.0%), and significantly better specificity (85.3%) compared to both classical (74.0%) and abbreviated (79.4%) Light's criteria. A second CART model developed after excluding serum measurements selected PF protein and PF LDH as the most discriminatory variables, and correctly classified 97.2% of exudates and 77.0% of transudates.

Conclusions: CART-based algorithms can efficiently discriminate between pleural exudates and transudates.

Clin Chem Lab Med 2007;45:82–7.

:

Corresponding author: Aureli Esquerda, Department of Clinical Laboratory, Arnau de Vilanova University Hospital, Rovira Roure, 80, 25198 Lleida, Spain Phone: +34-973-601363, Fax: +34-973-221775,

References

1. Porcel JM, Light RW. Diagnostic approach to pleural effusion in adults. Am Fam Physician2006;73:1211–20.Search in Google Scholar

2. Kinasewitz GT. Transudative effusions. Eur Respir J1997;10:714–8.10.1183/09031936.97.10030714Search in Google Scholar

3. Villena V, López Encuentra J, Echave-Sustaeta J, Álvarez Martínez C, Martín Escribano P. Prospective study of 1,000 consecutive patients with pleural effusion. Etiology of the effusion and characteristics of the patients. Arch Bronconeumol2002;38:21–6.10.1016/S0300-2896(02)75142-9Search in Google Scholar

4. Light RW, MacGregor MI, Luchsinger PC, Ball WC. Pleural effusions: the diagnostic separation of transudates and exudates. Ann Intern Med1972;77:507–13.10.7326/0003-4819-77-4-507Search in Google Scholar

5. Gázquez I, Porcel JM, Vives M, Vicente de Vera MC, Rubio M, Rivas MC. Comparative analysis of Light's criteria and other biochemical parameters for distinguishing transudates from exudates. Respir Med1998;92:762–5.10.1016/S0954-6111(98)90009-9Search in Google Scholar

6. Porcel JM, Peña JM, Vicente de Vera C, Esquerda A. Reevaluación del método estándar (criterios de Light) para identificar exudados pleurales. Med Clin (Barc)2006;126:211–3.10.1157/13084870Search in Google Scholar PubMed

7. Burgess LJ, Maritz FJ, Taljaard JJ. Comparative analysis of the biochemical parameters used to distinguish between pleural transudates and exudates. Chest1995;107:1604–9.10.1378/chest.107.6.1604Search in Google Scholar PubMed

8. Romero S, Martínez A, Hernández L, Fernández C, Espasa A, Candela A, et al. Light's criteria revisited: consistency and comparison with new proposed alternative criteria for separating pleural transudates from exudates. Respiration2000;67:18–23.10.1159/000029457Search in Google Scholar PubMed

9. Vives M, Porcel JM, Vicente de Vera MC, Ribelles E, Rubio M. A study of Light's criteria and possible modifications for distinguishing exudative from transudative pleural effusions. Chest1996;109:1503–7.10.1378/chest.109.6.1503Search in Google Scholar PubMed

10. Heffner JE, Brown LK, Barbieri CA. Diagnostic value of tests that discriminate between exudative and transudative pleural effusions. Chest1997;111:970–80.10.1378/chest.111.4.970Search in Google Scholar PubMed

11. Romero S, Candela A, Martín C, Hernández L, Trigo C, Gil J. Evaluation of different criteria for the separation of pleural transudates and exudates. Chest1993;104:399–404.10.1378/chest.104.2.399Search in Google Scholar PubMed

12. Hamm H, Brohan U, Bohmer R, Missmahl HP. Cholesterol in pleural effusions. A diagnostic aid. Chest1987;92:296–302.10.1378/chest.92.2.296Search in Google Scholar PubMed

13. Roth BJ, O'Meara TF, Cragun WH. The serum-effusion albumin gradient in the evaluation of pleural effusions. Chest1990;98:546–9.10.1378/chest.98.3.546Search in Google Scholar

14. García-Pachón E, Padilla-Navas I, Sánchez JF, Jiménez B, Custardoy J. Pleural fluid to serum cholinesterase ratio for the separation of transudates and exudates. Chest1996;110:97–101.10.1378/chest.110.1.97Search in Google Scholar

15. Porcel JM, Vives M, Esquerda A, Rivas MC. Pleural protein capillary electrophoresis for the separation of transudates and exudates [letter]. Clin Chem2001;47:975–6.10.1093/clinchem/47.5.975Search in Google Scholar

16. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Pacific Grove: Wadsworth, 1984.Search in Google Scholar

17. Lewis RJ. An introduction to classification and regression tree (CART) analysis. In: 2000 Annual Meeting of the Society for Academic Emergency Medicine, May 23, 2000, San Francisco, CA. Available at http://www.saem.org/download/lewis1.pdf. Accessed Dec 28, 2005.Search in Google Scholar

18. Podgorelec V, Kokol P, Stiglic B, Rozman I. Decision trees: an overview and their use in medicine. J Med Syst2002;26:445–63.10.1023/A:1016409317640Search in Google Scholar

19. Deutsche Gesellschaft für Klinische Chemie. Empfehlungen der Deutschen Gesellschaft für Klinische Chemie (DGKC). J Clin Chem Clin Biochem 1972;10:182–93.Search in Google Scholar

20. Heffner JE. Evaluating diagnostics tests in the pleural space. Differentiating transudates from exudates as a model. Clin Chest Med1998;19:277–93.10.1016/S0272-5231(05)70077-0Search in Google Scholar

21. Mair J, Smidt J, Lechleitner P, Dienstl F, Puschendorf B. A decision tree for the early diagnosis of acute myocardial infarction in nontraumatic chest pain patients at hospital admission. Chest1995;108:1502–9.10.1378/chest.108.6.1502Search in Google Scholar

22. Poon TC, Chan AT, Zee B, Ho SK, Mok TS, Leung TW, et al. Application of classification tree and neural network algorithms to the identification of serological liver marker profiles for the diagnosis of hepatocellular carcinoma. Oncology2001;61:275–83.10.1159/000055334Search in Google Scholar

23. Garzotto M, Beer TM, Hudson RG, Peters L, Hsieh Y-C, Barrera E, et al. Improved detection of prostate cancer using classification and regression tree analysis. J Clin Oncol2005;23:4322–9.10.1200/JCO.2005.11.136Search in Google Scholar

24. Broaddus VC. Diuresis and transudative effusions – changing the rules of the game [editorial]. Am J Med2001;110:732–5.10.1016/S0002-9343(01)00728-8Search in Google Scholar

25. Romero-Candeira S, Hernández L. The separation of transudates and exudates with particular reference to the protein gradient. Curr Opin Pulm Med2004;10:294–8.10.1097/01.mcp.0000128430.34150.80Search in Google Scholar PubMed

26. Terrin N, Schmid C, Griffith JL, D'Agostino RB, Selker HP. External validity of predictive models: a comparison of logistic regression, classification trees, and neural networks. J Clin Epidemiol2003;56:721–9.10.1016/S0895-4356(03)00120-3Search in Google Scholar

Published Online: 2007-01-24
Published in Print: 2007-01-01

©2007 by Walter de Gruyter Berlin New York

Articles in the same Issue

  1. CCLM: Bringing advances in laboratory medicine to the “New World”
  2. Diagnostic approach to inherited bleeding disorders
  3. Linking laboratory and medication data: new opportunities for pharmacoepidemiological research
  4. Association between polymorphisms of ACE, B2AR, ANP and ENOS and cardiovascular diseases: a community-based study in the Matsu area
  5. Anti-thyroid-stimulating hormone receptor antibodies determined by second-generation assay
  6. Serum levels of granulocyte colony-stimulating factor (G-CSF) and macrophage colony-stimulating factor (M-CSF) in pancreatic cancer patients
  7. Surrogate markers of insulin resistance in assessing individuals with new categories “prehypertension” and “prediabetes”
  8. Evaluation of pre-analytical, demographic, behavioural and metabolic variables on fibrinolysis and haemostasis activation markers utilised to assess hypercoagulability
  9. Hyperhomocysteinaemia and immune activation in patients with cancer
  10. The effect of homocysteine reduction by B-vitamin supplementation on inflammatory markers
  11. Lipid peroxidation in Down syndrome caused by regular trisomy 21, trisomy 21 by Robertsonian translocation and mosaic trisomy 21
  12. Pregnancy-associated plasma protein A in dialysis patients
  13. L-Cysteine supplementation prevents exercise-induced alterations in human erythrocyte membrane acetylcholinesterase and Na+,K+-ATPase activities
  14. Assessment of homocysteine, neopterin and nitric oxide levels in Behcet's disease
  15. Increased adenosine deaminase in hydatidiform mole
  16. Classification tree analysis for the discrimination of pleural exudates and transudates
  17. External quality assessment of hemoglobin A2 measurement: data from an Italian pilot study with fresh whole blood samples and commercial HPLC systems
  18. Comparison of four commercial quantitative HIV-1 assays for viral load monitoring in clinical daily routine
  19. Interchangeability of measurements of CA 19-9 in serum with four frequently used assays: an update
  20. Analytical validation of the new version of the Liaison N-Tact PTH assay
  21. Validation of an automated sensitive immunoassay for quantitation of cytokines in the sputum of cystic fibrosis patients
  22. Strong interference of hemoglobin concentration on CSF total protein measurement using the trichloroacetic acid precipitation method
  23. Correction of patient results for Beckman Coulter LX-20 assays affected by interference due to hemoglobin, bilirubin or lipids: a practical approach
  24. Acquiring a measurement system within the framework of standard ISO 15189
  25. Six Sigma and laboratory consultation
  26. ESR or LSRB, that is the question!
  27. Reply to the Letter written by Hardeman
  28. Natriuretic peptides. The hormones of the heart
Downloaded on 30.12.2025 from https://www.degruyterbrill.com/document/doi/10.1515/CCLM.2007.001/html
Scroll to top button