BazEkon - The Main Library of the Cracow University of Economics

BazEkon home page

Main menu

Ochab Marcin (AGH University of Science and Technology Kraków, Poland), Wajs Wiesław (AGH University of Science and Technology Kraków, Poland)
Bronchopulmonary Dysplasia Prediction Using Support Vector Machine and LIBSVM
Annals of Computer Science and Information Systems, 2014, vol. 2, s. 201 - 208, rys., tab., bibliogr. 32 poz.
Medycyna, Choroby, Dzieci, Algorytmy, System MATLAB
Medicine, Illness, Children, Algorithms, MATLAB system
The paper presents BPD (Bronchopulmonary Dysplasia) prediction for extremely premature infants after their first week of life. SVM (Support Vector Machine) algorithm implemented in LIBSVM was used as classifier. Results are compared to others gathered in previous work where LR (Logit Regression) and Matlab environment SVM implementation were used. Fourteen different risk factor parameters were considered and due to the high computational complexity only 3375 random combinations were analysed. Classifier based on eight feature model provides the highest accuracy which was 82.60%. The most promising 5-feature model which gathered 82.23% was reasonably immune to random data changes and consistent with LR results. The main conclusion is that unlike Matlab SVM implementation, LIBSVM can be successfully used in considered problem but it is less stable than LR. In addition, the article discusses influence of the model parameters selection on prediction quality.(original abstract)
Full text
  1. Ali, Z., Schmidt, P., Dodd, J., Jeppesen, D. L.: Bronchopulmonary dysplasia: a review. Archives of gynecology and obstetrics, 2013, 1-9 doi: 10.1007/s00404-013-2753-8
  2. Ambalavanan N, Van Meurs KP, Perritt R, Carlo WA, Ehrenkranz RA, Stevenson DK, Lemons JA, Poole WK, Higgins RD. NICHD Neo- natal Research Network, Bethesda, MD. Predictors of death or bronchopulmonary dysplasia in preterm infants with respiratory failure. J Perinatol 2008;28:420-426 doi: 10.1038/jp.2008.18
  3. Bhering CA, Mochdece CC, Moreira ME, Rocco JR, Sant'Anna GM. Bronchopulmonary dysplasia prediction model for 7-day-old infants. J Pediatr (Rio J) 2007;83:163-170. doi: 10.1590/S0021- 75572007000200011
  4. Bhutani VK, Abbasi S. Relative likelihood of bronchopulmonary dysplasia based on pulmonary mechanics measured in preterm neonates during the first week of life. J Pediatr 1992;120:605-613. doi: 10.1016/S0022-3476(05)82491-6
  5. Burges, C. J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 2, Kluwer Academic Publishers, Boston 1998, pp. 121-167 doi: 10.1023/A:1009715923555
  6. Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2011, 2:27:1-27:27. Software available at cjlin/libsvm doi: 10.1145/1961189.1961199
  7. Corcoran JD, Patterson CC, Thomas PS, Halliday HL. Reduction in the risk of bronchopulmonary dysplasia from 1980-1990: results of a multivariate logistic regression analysis. Eur J Pediatr 1993;152:677-681. doi: 10.1007/BF01955247
  8. Cunha, G.S., Mezzacappa-Filho, F., Ribeiro, J. D.: Risk Factors for Bronchopulmonary Dysplasia in very Low Birth Weight Newborns Treated with Mechanical Ventilation in the First Week of Life. Journal of Tropical Pediatrics, 2005, 51(6), 334-340 doi: 10.1093/tropej/fmi051
  9. Farstad, T., Bratlid, D., Medbø, S., Markestad, T.: Bronchopulmonary dysplasia-prevalence, severity and predictive factors in a national cohort of extremely premature infants. Acta Paediatrica, 2011, 100(1), pp. 53-58 doi: 10.1111/j.1651-2227.2010.01959.x
  10. Gilbert R., Keighley J., The arterial/alveolar oxygen tension ratio. An index of gas exchange applicable to varying inspired oxygen concentrations., Am Rev Respir Dis., 1974, 109, 142-145.
  11. Groothuis, J. R., Makari, D.: Definition and outpatient management of the very low-birth-weight infant with bronchopulmonary dysplasia. Advances in therapy, 2012, 29(4), 297-311 doi: 10.1007/s12325-012-0015-y
  12. Horbar JD, Badger GJ, Carpenter JH, Fanaroff AA, Kilpatrick S, La-Corte M, Phibbs R, Soll RF; Members of the Vermont Oxford Network. Trends in mortality and morbidity for very low birth weight infants, 1991-1999. Pediatrics 2002;110:143-151. doi: 10.1542/peds.110.1.143
  13. Jobe, A. H.: The new bronchopulmonary dysplasia. Current opinion in pediatrics, 2011, 23(2), 167 doi: 10.1097/MOP.0b013e3283423e6b
  14. Jones, H. L.: Jacknife estimation of functions of stratum means. Biometrika, 1974, 61(2), 343-348 doi: 10.1093/biomet/61.2.343
  15. Kim YD, Kim EA, Kim KS, Pi SY, Kang W. Scoring method for early prediction of neonatal chronic lung disease using modified respiratory parameters. J Korean Med Sci 2005;20:397-401. doi: 10.3346/jkms.2005.20.3.397
  16. Kuenzel L. Predicting and undestanding bronchopulmonary dysplasia in permature infants. Stanford Undergraduate Research Journal
  17. Laughon, Matthew M., et al. "Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants." American journal of respiratory and critical care medicine 183.12 (2011): 1715. doi: 10.1164/rccm.201101-0055OC
  18. Marshall DD, Kotelchuck M, Young TE, Bose CL, Kruyer L, O'Shea TM. Risk factors for chronic lung disease in the surfactant era: a North Carolina population-based study of very low birth weight infants. North Carolina Neonatologists Association. Pediatrics 1999; 104:1345-1350. doi: 10.1542/peds.104.6.1345
  19. Noack G, Mortensson W, Robertson B, Nilsson R. Correlations between radiological and cytological findings in early development of bron- chopulmonary dysplasia. Eur J Pediatr 1993;152:1024-1029. doi: 10.1007/BF01957230
  20. Ochab Marcin and Wiesław Wajs. Bronchopulmonary Dysplasia Prediction Using Support Vector Machine and Logit Regression. Information Technologies in Biomedicine, Volume 4. Springer International Publishing, 2014. 365-374. doi: 10.1007/978-3-319-06596-0_34
  21. Oh W, Poindexter BB, Perritt R, Lemons JA, Bauer CR, Ehrenkranz RA, Stoll BJ, Poole K, Wright LL; Neonatal Research Network. Association between fluid intake and weight loss during the first ten days of life and risk of bronchopulmonary dysplasia in extremely low birth weight infants. J Pediatr 2005;147:786-790. doi: 10.1016/j.jpeds.2005.06.039
  22. Rojas MA, Gonzalez A, Bancalari E, Claure N, Poole C, Silva-Neto G. Changing trends in the epidemiology and pathogenesis of neonatal chronic lung disease. J Pediatr 1995;126:605-610. doi: 10.1016/S0022-3476(95)70362-4
  23. Romagnoli C, Zecca E, Tortorolo L, Vento G, Tortorolo G. A scoring system to predict the evolution of respiratory distress syndrome into chronic lung disease in preterm infants. Intensive Care Med 1998;24: 476-480. doi: 10.1007/s001340050599
  24. Ryan SW, Nycyk J, Shaw BN. Prediction of chronic neonatal lung disease on day 4 of life. Eur J Pediatr 1996;155:668-671. doi: 10.1007/BF01957150
  25. Sosenko, I. R., Bancalari, E.: New Developments in the Pathogenesis and Prevention of Bronchopulmonary Dysplasia. The Newborn Lung: Neonatology Questions and Controversies: Expert Consult-Online and Print, 2012, 217
  26. Stoch, P.: Prediction of BronchoPulmonary Dysplasia in preterm neonates using statistical and artificial neural network tools. (Thesis or Dissertation style) Ph.D. dissertation, AGH University of Science and Technology, Kraków, 2007 (in Polish), pp. 60-72
  27. Stoll BJ, Hansen NI, Bell EF, Shankaran S, Laptook AR, Walsh MC, Hale EC, Newman NS, Schibler K, Carlo WA, et al.; Eunice Kennedy Shriver National Institute of Child Health and Human Development Neonatal Research Network. Neonatal outcomes of extremely preterm infants from the NICHD Neonatal Research Network. Pediatrics 2010;126:443-456. doi: 10.1542/peds.2009-2959
  28. Subhedar NV, Hamdan AH, Ryan SW, Shaw NJ. Pulmonary artery pressure: early predictor of chronic lung disease in preterm infants. Arch Dis Child Fetal Neonatal Ed 1998;78:F20-F24. doi:10.1136/fn.78.1.F20
  29. Tapia, J.L., Agost, D., Alegria, A., Standen, J., Escobar, M., Grandi, C., et al.: Bronchopulmonary dysplasia: incidence, risk factors and resource utilization in a population of South American very low birth weight infants. Journal de Pediatria (Rio J). 2006, 82(1), 15-20 doi: 10.1590/S0021-75572006000100005
  30. Toce SS, Farrell PM, Leavitt LA, Samuels DP, Edwards DK. Clinical and roentgenographic scoring systems for assessing bronchopulmo- nary dysplasia. Am J Dis Child 1984;138:581- 585. doi:10.1001/archpedi.1984.02140440065017
  31. Walsh, M. et al. Summary proceedings from the bronchopulmonary dysplasia group. Pediatrics 117(3), S52-56 (2006) doi: 10.1542/peds.2005-0620I
  32. Yuksel B, Greenough A, Karani J. Prediction of chronic lung disease from the chest radiograph appearance at seven days of age. Acta Paediatr 1993;82:944-947. doi: 10.1111/j.1651-2227.1993.tb12605.x
Cited by
Share on Facebook Share on Twitter Share on Google+ Share on Pinterest Share on LinkedIn Wyślij znajomemu