Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

English version

Autoři: Antonio Rivero-Juárez ^aff001; David Guijo-Rubio ^aff002; Francisco Tellez ^aff003; Rosario Palacios ^aff004; Dolores Merino ^aff005; Juan Macías ^aff006; Juan Carlos Fernández ^aff002; Pedro Antonio Gutiérrez ^aff002; Antonio Rivero ^aff001; César Hervás-Martínez ^aff002
Působiště autorů: Unidad de Enfermedades Infecciosas, Hospital Universitario Reina Sofía de Córdoba, Instituto Maimónides de Investigación Biomédica de Córdoba, Universidad de Córdoba, Córdoba, España ^aff001; Departamento de Informática y Análisis Numérico, Universidad de Córdoba, Córdoba, España ^aff002; Unidad de Enfermedades Infecciosas, Hospital Universitario de Puerto Real, Cádiz, España ^aff003; Unidad de Enfermedades Infecciosas, Hospital Juan Ramón Jiménez e Infanta Elena de Huelva, Huelva, España ^aff004; Unidad de Enfermedades Infecciosas, Hospital Universitario Virgen de la Victoria, Complejo Hospitalario Provincial de Málaga, Málaga, España ^aff005; Unidad de Enfermedades Infecciosas, Hospital Universitario de Valme, Instituto de Biomedicina de Sevilla, Sevilla, España ^aff006
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: https://doi.org/10.1371/journal.pone.0227188

Souhrn

Several European countries have established criteria for prioritising initiation of treatment in patients infected with the hepatitis C virus (HCV) by grouping patients according to clinical characteristics. Based on neural network techniques, our objective was to identify those factors for HIV/HCV co-infected patients (to which clinicians have given careful consideration before treatment uptake) that have not being included among the prioritisation criteria. This study was based on the Spanish HERACLES cohort (NCT02511496) (April-September 2015, 2940 patients) and involved application of different neural network models with different basis functions (product-unit, sigmoid unit and radial basis function neural networks) for automatic classification of patients for treatment. An evolutionary algorithm was used to determine the architecture and estimate the coefficients of the model. This machine learning methodology found that radial basis neural networks provided a very simple model in terms of the number of patient characteristics to be considered by the classifier (in this case, six), returning a good overall classification accuracy of 0.767 and a minimum sensitivity (for the classification of the minority class, untreated patients) of 0.550. Finally, the area under the ROC curve was 0.802, which proved to be exceptional. The parsimony of the model makes it especially attractive, using just eight connections. The independent variable “recent PWID” is compulsory due to its importance. The simplicity of the model means that it is possible to analyse the relationship between patient characteristics and the probability of belonging to the treated group.

Klíčová slova:

Artificial neural networks – Drug abuse – Evolutionary algorithms – Hepatitis C virus – HIV – Liver fibrosis – Mental health therapies – Neural networks

Zdroje

1. WHO. Global hepatitis report. World Health Organization; 2017.

2. Wiessing L, Ferri M, Grady B, Kantzanou M, Sperle I, Cullen KJ, et al. Hepatitis C virus infection epidemiology among people who inject drugs in Europe: a systematic review of data for scaling up treatment and prevention. PloS one. 2014;9(7):e103345. doi: 10.1371/journal.pone.0103345 25068274

3. Macias J, Berenguer J, Japón MA, Girón JA, Rivero A, López-Cortés LF, et al. Fast fibrosis progression between repeated liver biopsies in patients coinfected with human immunodeficiency virus/hepatitis C virus. Hepatology. 2009;50(4):1056–1063. doi: 10.1002/hep.23136 19670415

4. Pineda JA, García-García JA, Aguilar-Guisado M, Ríos-Villegas MJ, Ruiz-Morales J, Rivero A, et al. Clinical progression of hepatitis C virus–related chronic liver disease in human immunodeficiency virus–infected patients undergoing highly active antiretroviral therapy. Hepatology. 2007;46(3):622–630. doi: 10.1002/hep.21757 17659577

5. AASLD. HCV Guidance: Recommendations for Testing, Managing, and Treating Hepatitis C. American Association for the Study of Liver Disease (AASLD); 2018.

6. Omland LH, Christensen PB, Krarup H, Jepsen P, Weis N, Sørensen HT, et al. Mortality among patients with cleared hepatitis C virus infection compared to the general population: a Danish nationwide cohort study. PLoS One. 2011;6(7):e22476. doi: 10.1371/journal.pone.0022476 21789259

7. Truong TN, Laureillard D, Lacombe K, Thi HD, Hanh PPT, Xuan LTT, et al. High proportion of HIV-HCV Coinfected patients with advanced liver fibrosis requiring hepatitis C treatment in Haiphong, northern Vietnam (ANRS 12262). PloS one. 2016;11(5):e0153744. doi: 10.1371/journal.pone.0153744

8. Bishop CM, et al. Neural networks for pattern recognition. Oxford university press; 1995.

9. Wang D, Larder B, Revell A, Montaner J, Harrigan R, De Wolf F, et al. A comparison of three computational modelling methods for the prediction of virological response to combination HIV therapy. Artificial Intelligence in Medicine. 2009;47(1):63–74. doi: 10.1016/j.artmed.2009.05.002 19524413

10. Resino S, Seoane JA, Bellón JM, Dorado J, Martin-Sanchez F, Álvarez E, et al. An artificial neural network improves the non-invasive diagnosis of significant fibrosis in HIV/HCV coinfected patients. Journal of Infection. 2011;62(1):77–86. doi: 10.1016/j.jinf.2010.11.003 21073895

11. Lamers SL, Salemi M, McGrath MS, Fogel GB. Prediction of R5, X4, and R5X4 HIV-1 coreceptor usage with evolved neural networks. IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB). 2008;5(2):291–300. doi: 10.1109/TCBB.2007.1074

12. Pradhan M, Sahu RK. Multilayer perceptron network in HIV/AIDS application. International Journal of Computer Applications in Engineering Sciences. 2011;1(1):41–48.

13. Bisaso KR, Anguzu GT, Karungi SA, Kiragga A, Castelnuovo B. A survey of machine learning applications in HIV clinical research and care. Computers in biology and medicine. 2017;91:366–371. doi: 10.1016/j.compbiomed.2017.11.001 29127902

14. Johansson EM, Dowla FU, Goodman DM. Backpropagation learning for multilayer feed-forward neural networks using the conjugate gradient method. International Journal of Neural Systems. 1991;2(04):291–301. doi: 10.1142/S0129065791000261

15. Durbin R, Rumelhart DE. Product units: A computationally powerful and biologically plausible extension to backpropagation networks. Neural computation. 1989;1(1):133–142. doi: 10.1162/neco.1989.1.1.133

16. Billings SA, Wei HL, Balikhin MA. Generalized multiscale radial basis function networks. Neural Networks. 2007;20(10):1081–1094. doi: 10.1016/j.neunet.2007.09.017 17993257

17. Fei Y, Hu J, Gao K, Tu J, Wang W, Li Wq. Risk Prediction for Portal Vein Thrombosis in Acute Pancreatitis Using Radial Basis Function. Annals of vascular surgery. 2018;47:78–84. doi: 10.1016/j.avsg.2017.09.004 28943487

18. Kim Y, Na YH, Xing L, Lee R, Park S. Automatic deformable surface registration for medical applications by radial basis function-based robust point-matching. Computers in biology and medicine. 2016;77:173–181. doi: 10.1016/j.compbiomed.2016.07.013 27567399

19. Griffiths GW, Schiesser W, et al. Analysis of cornea curvature using radial basis functions–Part I: Methodology. Computers in biology and medicine. 2016;77:274–284. doi: 10.1016/j.compbiomed.2016.08.011 27614697

20. Shaikhina T, Khovanova NA. Handling limited datasets with neural networks in medical applications: A small-data approach. Artificial Intelligence in Medicine. 2017;75:51–63. doi: 10.1016/j.artmed.2016.12.003 28363456

21. Dey P, Lamba A, Kumari S, Marwaha N. Application of an artificial neural network in the prognosis of chronic myeloid leukemia. Analytical and quantitative cytology and histology. 2011;33(6):335–339. 22590811

22. Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. Journal of Applied Biomedicine. 2013;11(2):47–58. doi: 10.2478/v10136-012-0031-x

23. Duch W, Jankowski N. Transfer functions: hidden possibilities for better neural networks. In: ESANN. Citeseer; 2001. p. 81–94.

24. Ismail A, Jeng DS, Zhang L. An optimised product-unit neural network with a novel PSO–BP hybrid training algorithm: Applications to load–deformation analysis of axially loaded piles. Engineering applications of artificial intelligence. 2013;26(10):2305–2314. doi: 10.1016/j.engappai.2013.04.007

25. Vukicevic AM, Stojadinovic M, Radovic M, Djordjevic M, Cirkovic BA, Pejovic T, et al. Automated development of artificial neural networks for clinical purposes: Application for predicting the outcome of choledocholithiasis surgery. Computers in biology and medicine. 2016;75:80–89. doi: 10.1016/j.compbiomed.2016.05.016 27261565

26. Cruz-Ramirez M, Hervas-Martinez C, Fernandez JC, Briceno J, De La Mata M. Predicting patient survival after liver transplantation using evolutionary multi-objective artificial neural networks. Artificial Intelligence in Medicine. 2013;58(1):37–49. doi: 10.1016/j.artmed.2013.02.004 23489761

27. Dorado-Moreno M, Pérez-Ortiz M, Gutiérrez PA, Ciria R, Briceño J, Hervás-Martínez C. Dynamically weighted evolutionary ordinal neural network for solving an imbalanced liver transplantation problem. Artificial Intelligence in Medicine. 2017;77:1–11. doi: 10.1016/j.artmed.2017.02.004 28545607

28. Martínez-Estudillo FJ, Hervás-Martínez C, Gutiérrez PA, Martínez-Estudillo AC. Evolutionary product-unit neural networks classifiers. Neurocomputing. 2008;72(1-3):548–561. doi: 10.1016/j.neucom.2007.11.019

29. Lippmann RP. Pattern classification using neural networks. IEEE communications magazine. 1989;27(11):47–50. doi: 10.1109/35.41401

30. Schmitt M. On the complexity of computing and learning with multiplicative neural networks. Neural Computation. 2002;14(2):241–301. doi: 10.1162/08997660252741121 11802913

31. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural networks. 1989;2(5):359–366. doi: 10.1016/0893-6080(89)90020-8

32. Angeline PJ, Saunders GM, Pollack JB. An evolutionary algorithm that constructs recurrent neural networks. IEEE transactions on Neural Networks. 1994;5(1):54–65. doi: 10.1109/72.265960 18267779

33. Martínez-Estudillo A, Martínez-Estudillo F, Hervás-Martínez C, García-Pedrajas N. Evolutionary product unit based neural networks for regression. Neural Networks. 2006;19(4):477–486. doi: 10.1016/j.neunet.2005.11.001 16481148

34. Yao X. Evolving artificial neural networks. Proceedings of the IEEE. 1999;87(9):1423–1447. doi: 10.1109/5.784219

35. Ding S, Li H, Su C, Yu J, Jin F. Evolutionary artificial neural networks: a review. Artificial Intelligence Review. 2013;39(3):251–260. doi: 10.1007/s10462-011-9270-6

36. Yao X, Liu Y. A new evolutionary system for evolving artificial neural networks. IEEE transactions on neural networks. 1997;8(3):694–713. doi: 10.1109/72.572107 18255671

37. Odri SV, Petrovacki DP, Krstonosic GA. Evolutional development of a multilevel neural network. Neural Networks. 1993;6(4):583–595. doi: 10.1016/S0893-6080(05)80061-9

38. Bebis G, Georgiopoulos M, Kasparis T. Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization. Neurocomputing. 1997;17(3-4):167–194. doi: 10.1016/S0925-2312(97)00050-7

39. Cantú-Paz E, Kamath C. An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). 2005;35(5):915–927. doi: 10.1109/TSMCB.2005.847740

40. Fernández JC, Martínez FJ, Hervás C, Gutiérrez PA. Sensitivity versus accuracy in multiclass problems using memetic pareto evolutionary neural networks. IEEE Transactions on Neural Networks. 2010;21(5):750–770. doi: 10.1109/TNN.2010.2041468

41. Fawcett T. An introduction to ROC analysis. Pattern recognition letters. 2006;27(8):861–874. doi: 10.1016/j.patrec.2005.10.010

42. Hervás C, Gutierrez PA, Silva M, Serrano JM. Combining classification and regression approaches for the quantification of highly overlapping capillary electrophoresis peaks by using evolutionary sigmoidal and product unit neural networks. Journal of Chemometrics: A Journal of the Chemometrics Society. 2007;21(12):567–577. doi: 10.1002/cem.1082

43. Cortes C, Vapnik V. Support-vector networks. Machine learning. 1995;20(3):273–297. doi: 10.1023/A:1022627411411

44. Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2016;374(2065):20150202. doi: 10.1098/rsta.2015.0202

45. Levene H. Robust tests for equality of variances. Contributions to probability and statistics Essays in honor of Harold Hotelling. 1961; p. 279–292.

46. Tukey JW. Comparing individual means in the analysis of variance. Biometrics. 1949; p. 99–114. doi: 10.2307/3001913 18151955

47. Peters PJ, Pontones P, Hoover KW, Patel MR, Galang RR, Shields J, et al. HIV infection linked to injection use of oxymorphone in Indiana, 2014–2015. New England Journal of Medicine. 2016;375(3):229–239. doi: 10.1056/NEJMoa1515195 27468059

48. Campo DS, Khudyakov Y. Intelligent Network DisRuption Analysis (INDRA): A targeted strategy for efficient interruption of hepatitis C transmissions. Infection, Genetics and Evolution. 2018;. doi: 10.1016/j.meegid.2018.05.028 29860098

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

Souhrn

Klíčová slova:

Zdroje

PLOS One

INSIGHTS from European Respiratory Congress

Současné pohledy na riziko v parodontologii

Svět praktické medicíny 3/2024 (znalostní test z časopisu)

Kardiologické projevy hypereozinofilií

Střevní příprava před kolonoskopií