Advances in medical decision support systems for diagnosis of acute graft-versus-host disease: molecular and computational intelligence joint approaches

Abstract

Acute graft-versus-host disease (aGVHD) is a serious systemic complication of allogeneic hematopoietic stem cell transplantation (HSCT) causing considerable morbidity and mortality. Acute GVHD occurs when alloreactive donor-derived T cells recognize host-recipient antigens as foreign. These trigger a complex multiphase process that ultimately results in apoptotic injury in target organs. The early events leading to GVHD seem to occur very soon, presumably within hours from the graft infusion. Therefore, when the first signs of aGVHD clinically manifest, the disease has been ongoing for several days at the cellular level, and the inflammatory cytokine cascade is fully activated. So, it comes as no surprise that progress in treatment based on clinical diagnosis of aGVHD has been limited in the past 30 years. It is likely that a pre-emptive strategy using systemic high-dose corticosteroids as early as possible could improve the outcome of aGVHD. Due to the deleterious effects of such treatment particularly in terms of infection risk posed by systemic steroid administration in a population that is already immune-suppressed, it is critical to identify biomarker signatures for approaching this very complex task. Some research groups have begun addressing this issue through molecular and proteomic analyses, combining these approaches with computational intelligence techniques, with the specific aim of facilitating the identification of diagnostic biomarkers in aGVHD. In this review, we focus on the aGVHD scenario and on the more recent state-of-the-art. We also attempt to give an overview of the classical and novel techniques proposed as medical decision support system for the diagnosis of GVHD.

Keywords

computational intelligence / gene selection / GVHD / machine learning / personalized modelling / wrapper

References

[1] Ayuk F, Diyachenko G, Zabelina T, Panse J, Wolschke C, Eiermann T, Binder T, Fehse B, Erttmann R, Kabisch H, Bacher U, Kröger N, Zander A R (2008). Anti-thymocyte globulin overcomes the negative impact of HLA mismatching in transplantation from unrelated donors. Exp Hematol, 36(8): 1047–1054

[2] Bacigalupo A, Lamparelli T, Milone G, Sormani M P, Ciceri F, Peccatori J, Locasciulli A, Majolino I, Di Bartolomeo P, Mazza F, Sacchi N, Pollicheni S, Pinto V, Van Lint M T, the Gruppo Italiano Trapianto Midollo Osseo (GITMO) (2010). Pre-emptive treatment of acute GVHD: a randomized multicenter trial of rabbit anti-thymocyte globulin, given on day+7 after alternative donor transplants. Bone Marrow Transplant, 45(2): 385–391

[3] Beilhack A, Schulz S, Baker J, Beilhack G F, Wieland C B, Herman E I, Baker E M, Cao Y A, Contag C H, Negrin R S (2005). In vivo analyses of early events in acute graft-versus-host disease reveal sequential infiltration of T-cell subsets. Blood, 106(3): 1113–1122

[4] Brodoefel H, Bethge W, Vogel M, Fenchel M, Faul C, Wehrmann M, Claussen C, Horger M (2010). Early and late-onset acute GVHD following hematopoietic cell transplantation: CT features of gastrointestinal involvement with clinical and pathological correlation. Eur J Radiol, 73(3): 594–600

[5] Buzzeo M P, Yang J, Casella G, Reddy V (2008). A preliminary gene expression profile of acute graft-versus-host disease. Cell Transplant, 17(5): 489–494

[6] Chaussabel D, Pascual V, Banchereau J (2010). Assessing the human immune system through blood transcriptomics. BMC Biol, 8(1): 84–98

[7] Ferrara J L (2008). Advances in the clinical management of GVHD. Best Pract Res Clin Haematol, 21(4): 677–682

[8] Ferrara J L, Levine J E, Reddy P, Holler E (2009). Graft-versus-host disease. Lancet, 373(9674): 1550–1561

[9] Ferrara J L, Reddy P (2006). Pathophysiology of graft-versus-host disease. Semin Hematol, 43(1): 3–10

[10] Fiasché M (2010). Implementations of Evolving Integrated Multimodel Systems, Algorithms and Applications in Biomedical Field. DissertationTip. DIMET, University “Mediterranea” of Reggio Calabria

[11] Fiasché M, Cuzzola M, Fedele R, Iacopino P, Morabito F C (2010a). Machine Learning and Personalized Modelling based Gene Selection for acute GvHD Gene Expression Data Analysis. In: Artificial Neural Networks — proceedings of ICANN 2010 Part I, LNCS6352

[12] Fiasché M, Cuzzola M, Iacopino P, Kasabov N, Morabito F C (2010b). Personalized Modelling based Gene Selection for acute GvHD Gene Expression Data Analysis: a Computational Framework Proposed. Australian Journal of Intellignet Information Processing Systems, 12(4): Machine Iearning Applications (Part II)

[13] Fiasché M, Verma A, Cuzzola M, Iacopino P, Kasabov N, Morabito F C (2009). Discovering Diagnostic Gene Targets and Early Diagnosis of Acute GVHD Using Methods of Computational Intelligence over Gene Expression Data. In: Artificial Neural Networks — ICANN 2009. Part II, LNCS 5769/2009, Berlin: Springer Heidelberg, pp. 10–19

[14] Firoz B F, Lee S J, Nghiem P, Qureshi A A (2006). Role of skin biopsy to confirm suspected acute graft-vs-host disease: results of decision analysis. Arch Dermatol, 142(2): 175–182

[15] Foley J E, Mariotti J, Ryan K, Eckhaus M, Fowler D H (2008). Th2 cell therapy of established acute graft-versus-host disease requires IL-4 and IL-10 and is abrogated by IL-2 or host-type antigen-presenting cells. Biol Blood Marrow Transplant, 14(9): 959–972

[16] Fujimura J, Takeda K, Kaduka Y, Saito M, Akiba H, Yagita H, Yamashiro Y, Shimizu T, Okumura K (2010). Contribution of B7RP-1/ICOS co-stimulation to lethal acute GVHD. Pediatr Transplant, 14(4): 540–548

[17] Guyon I, Elisseeff A (2003). An introduction to variable and feature selection. J Mach Learn Res, 3(7-8): 1157–1182

[18] Harik G R, Lobo F G, Goldberg D E (1999). The compact genetic algorithm. IEEE Trans Evol Comput, 3(4): 287–297

[19] Ho V T, Cutler C (2008). Current and novel therapies in acute GVHD. Best Pract Res Clin Haematol, 21(2): 223–237

[20] Hu Y, Song Q, Kasabov N (2009). Personalized modelling based gene selection for microarray data analysis. In: Köppen M, Kasabov N, Coghill G (eds.). ICONIP 2008, Part I. LNCS. Springer, Heidelberg, vol. 5506, pp. 1221–1228

[21] Jacobsohn D A, Vogelsang G B (2007). Acute graft versus host disease. Orphanet J Rare Dis, 2(1): 35–44

[22] Lord J D, Hackman R C, Gooley T A, Wood B L, Moklebust A C, Hockenbery D M, Steinbach G, Ziegler S F, McDonald G B (2011). Blood and gastric FOXP3⁺ T cells are not decreased in human gastric graft versus host disease. Biol Blood Marrow Transplant, 17(4): 486–496

[23] Kasabov N (2007a). Evolving Connectionist Systems: The Knowledge Engineering Approach, 2nd ed. Springer, London

[24] Kasabov N (2007b). Global, local and personalized modelling and profile discovery in bioinformatics: An integrated approach. Pattern Recognit Lett, 28(6): 673–685

[25] Kasabov N (2010). To spike or not to spike: A probabilistic spiking neural model. Neural Networks, 23(1): 16–19

[26] Kato K, Cui S, Kuick R, Mineishi S, Hexner E, Ferrara J L M, Emerson S G, Zhang Y (2010). Identification of stem cell transcriptional programs normally expressed in embryonic and neural stem cells in alloreactive CD8⁺ T cells mediating graft-versus-host disease. Biol Blood Marrow Transplant, 16(6): 751–771

[27] Langley P (1994). Selection of relevant features in machine learning, In: Proceedings of AAAI Fall Symposium on Relevance, 140–144

[28] Magenau J M, Qin X, Tawara I, Rogers C E, Kitko C, Schlough M, Bickley D, Braun T M, Jang P S, Lowler K P, Jones D M, Choi S W, Reddy P, Mineishi S, Levine J E, Ferrara J L, Paczesny S (2010). Frequency of CD4⁺CD25(hi)FOXP3⁺ regulatory T cells has diagnostic and prognostic value as a biomarker for acute graft-versus-host-disease. Biol Blood Marrow Transplant, 16(7): 907–914

[29] Miura Y, Thoburn C J, Bright E C, Phelps M L, Shin T, Matsui E C, Matsui W H, Arai S, Fuchs E J, Vogelsang G B, Jones R J, Hess A D (2004). Association of Foxp3 regulatory gene expression with graft-versus-host disease. Blood, 104(7): 2187–2193

[30] Mohty M, Gaugler B, Faucher C, Sainty D, Lafage-Pochitaloff M, Vey N, Bouabdallah R, Arnoulet C, Gastaut JA, Viret F, Wolfers J, Maraninchi D, Blaise D, Olive D (2002). Recovery of lymphocyte and dendritic cell subsets following reduced intensity allogeneic bone marrow transplantation. Hematology, 7(3): 157–64

[31] Paczesny S, Braun T M, Levine J E, Hogan J, Crawford J, Coffing B, Olsen S, Choi S W, Wang H, Faca V, Pitteri S, Zhang Q, Chin A, Kitko C, Mineishi S, Yanik G, Peres E, Hanauer D, Wang Y, Reddy P, Hanash S, Ferrara J L M (2010a). Elafin is a biomarker of graft-versus-host disease of the skin. Sci Transl Med, 2(13): ra2

[32] Paczesny S, Hanauer D, Sun Y, Reddy P (2010b). New perspectives on the biology of acute GVHD. Bone Marrow Transplant, 45(1): 1–11

[33] Paczesny S, Krijanovski O I, Braun T M, Choi S W, Clouthier S G, Kuick R, Misek D E, Cooke K R, Kitko C L, Weyand A, Bickley D, Jones D, Whitfield J, Reddy P, Levine J E, Hanash S M, Ferrara J L M (2009a). A biomarker panel for acute graft-versus-host disease. Blood, 113(2): 273–278

[34] Paczesny S, Levine J E, Braun T M, Ferrara J L M (2009b). Plasma biomarkers in graft-versus-host disease: a new era? Biol Blood Marrow Transplant, 15(Suppl): 33–38

[35] Payne D K, Sullivan M D, Massie M J (1996). Women’s psychological reactions to breast cancer. Semin Oncol, 23(Suppl 2): 89–97

[36] Piper K P, Horlock C, Curnow S J, Arrazi J, Nicholls S, Mahendra P, Craddock C, Moss P A H (2007). CXCL10-CXCR3 interactions play an important role in the pathogenesis of acute graft-versus-host disease in the skin following allogeneic stem-cell transplantation. Blood, 110(12): 3827–3832

[37] Platt J (1998). Fast training of support vector machines using sequential minimal optimization. Advances in Kernel Methods–Support Vector Learning.MIT Press

[38] Schub N, Günther A, Schrauder A, Claviez Aβ, Ehlert C,βGramatzki M,βRepp R (2011). Therapy of steroid-refractory acute GVHD with CD52 antibody alemtuzumab is effective. Bone Marrow Tranplant, 46: 143–147

[39] Socié G (2009). Graft-versus-host disease: proteomics comes of age. Blood, 113(2): 271–272

[40] Socié G, Blazar B R (2009). Acute graft-versus-host disease: from the bench to the bedside. Blood, 114(20): 4327–4336

[41] Song Q, Kasabov N (2006). TWNFI — Transductive weighted neuro-fuzzy inference system and applications for personalized modelling. Neural Netw, 19(10): 159–596

[42] van Bekkum D W, Vries De M J (1967). Radiation Chimaeras, London: Logos Press

[43] Varadi G, Or R, Slavin S, Nagler A (1996). In vivo CAMPATH-1 monoclonal antibodies: a novel mode of therapy for acute graft-versus-host disease. Am J Hematol, 52(3): 236–237

[44] Verma A, Fiasché M, Cuzzola M, Iacopino P, Morabito F C, Kasabov N (2009). Ontology Based Personalized Modelling for Type 2 Diabetes Risk Analysis: An Integrated Approach. In: Leung C S, Lee M, Chan J H (Eds.): ICONIP 2009, Part II, LNCS 5864, Springer, Heidelberg, pp. 360–366

[45] Weissinger E M, Schiffer E, Hertenstein B, Ferrara J L, Holler E, Stadler M, Kolb H J, Zander A, Zürbig P, Kellmann M, Ganser A (2007). Proteomic patterns predict acute graft-versus-host disease after allogeneic hematopoietic stem cell transplantation. Blood, 109(12): 5511–5519

[46] Wolf D, Wolf A M, Fong D, Rumpold H, Strasak A, Clausen J, Nachbaur D (2007). Regulatory T-cells in the graft and the risk of acute graft-versus-host disease after allogeneic stem cell transplantation. Transplantation, 83(8): 1107–1113

[47] Yu X Z, Liang Y, Nurieva R I, Guo F, Anasetti C, Dong C (2006). Opposing effects of ICOS on graft-versus-host disease mediated by CD4 and CD8 T cells. J Immunol, 176(12): 7394–7401

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg