My Kieu Ha1,2,3, Esther Bartholomeus4,5,6, Luc Van Os7, Julie Dandelooy8, Julie Leysen8,9, Olivier Aerts8,9, Vasiliki Siozopoulou10, Eline De Smet11, Jan Gielen11,12, Khadija Guerti13, Michel De Maeseneer14, Nele Herregods15, Bouchra Lechkar16, Ruth Wittoek17,18, Elke Geens18, Laura Claes19, Mahmoud Zaqout20,21, Wendy Dewals20, Annelies Lemay22, David Tuerlinckx23,24, David Weynants25, Koen Vanlede26, Gerlant van Berlaer27, Marc Raes28, Helene Verhelst29, Tine Boiy30, Pierre Van Damme4,31, Anna C Jansen19, Marije Meuwissen5, Vito Sabato16,32, Guy Van Camp6, Arvid Suls4, Jutte Van der Werff Ten Bosch33, Joke Dehoorne34, Rik Joos18,30,32,34, Kris Laukens4,35,36, Pieter Meysman4,35,36, Benson Ogunjimi37,38,39,40,41,42. 1. Center for Health Economics Research and Modelling Infectious Diseases (CHERMID), Vaccine and Infectious Disease Institute, University of Antwerp, Wilrijk, Belgium. my.ha@uantwerpen.be. 2. Antwerp Unit for Data Analysis and Computation in Immunology and Sequencing (AUDACIS), University of Antwerp, Antwerp, Belgium. my.ha@uantwerpen.be. 3. Antwerp Center for Translational Immunology and Virology (ACTIV), Vaccine and Infectious Disease Institute, University of Antwerp, Wilrijk, Belgium. my.ha@uantwerpen.be. 4. Antwerp Unit for Data Analysis and Computation in Immunology and Sequencing (AUDACIS), University of Antwerp, Antwerp, Belgium. 5. Antwerp Center for Translational Immunology and Virology (ACTIV), Vaccine and Infectious Disease Institute, University of Antwerp, Wilrijk, Belgium. 6. Center of Medical Genetics, University of Antwerp, Antwerp University Hospital, Edegem, Belgium. 7. Ophthalmology Department, Antwerp University Hospital, Edegem, Belgium. 8. Dermatology Department, Antwerp University Hospital, Edegem, Belgium. 9. Department of Translational Research in Immunology and Inflammation, University of Antwerp, Wilrijk, Belgium. 10. Pathology Department, Antwerp University Hospital, Edegem, Belgium. 11. Radiology Department, Antwerp University Hospital, Edegem, Belgium. 12. Department of Molecular - Morphology - Microscopy, University of Antwerp, Wilrijk, Belgium. 13. Clinical Biology Department, Antwerp University Hospital, Edegem, Belgium. 14. Radiology Department, Brussels University Hospital, Jette, Belgium. 15. Radiology Department, Ghent University Hospital, Ghent, Belgium. 16. Department of Immunology, Allergology, and Rheumatology, Antwerp University Hospital, Edegem, Belgium. 17. Rheumatology Department, Ghent University Hospital, Ghent, Belgium. 18. Rheumatology Department, Antwerp Hospital Network, Antwerp, Belgium. 19. Pediatric Neurology Unit, Antwerp University Hospital, Edegem, Belgium. 20. Pediatric Cardiology Department, Antwerp University Hospital, Edegem, Belgium. 21. Pediatric Cardiology Department, Antwerp Hospital Network, Antwerp, Belgium. 22. Department of Pediatrics, Turnhout General Hospital, Turnhout, Belgium. 23. Department of Pediatrics, Catholic University of Louvain, Louvain-la-Neuve, Belgium. 24. Department of Pediatrics, Namur University Hospital Center, Site Dinant, Dinant, Belgium. 25. Department of Pediatrics, Namur University Hospital Center, Site Sainte-Elisabeth, Namur, Belgium. 26. Department of Pediatrics, Nikolaas General Hospital, Sint-Niklaas, Belgium. 27. Department of Emergency Medicine/Pediatric Care, Brussels University Hospital, Jette, Belgium. 28. Department of Pediatrics, Jessa Hospital, Hasselt, Belgium. 29. Department of Pediatric Neurology, Ghent University Hospital, Ghent, Belgium. 30. Department of Pediatric Rheumatology, Antwerp University Hospital, Edegem, Belgium. 31. Center for the Evaluation of Vaccine, Vaccine and Infectious Disease Institute, University of Antwerp, Wilrijk, Belgium. 32. Antwerp Center for Pediatric Rheumatology and Autoinflammatory Diseases, Antwerp, Belgium. 33. Pediatric Immunology Department, Brussels University Hospital, Jette, Belgium. 34. Department of Pediatric Rheumatology, Ghent University Hospital, Ghent, Belgium. 35. ADREM Data Lab, Department of Mathematics and Computer Science, University of Antwerp, Antwerp, Belgium. 36. Biomedical Informatics Research Network Antwerp, University of Antwerp, Antwerp, Belgium. 37. Center for Health Economics Research and Modelling Infectious Diseases (CHERMID), Vaccine and Infectious Disease Institute, University of Antwerp, Wilrijk, Belgium. benson.ogunjimi@uantwerpen.be. 38. Antwerp Unit for Data Analysis and Computation in Immunology and Sequencing (AUDACIS), University of Antwerp, Antwerp, Belgium. benson.ogunjimi@uantwerpen.be. 39. Rheumatology Department, Antwerp Hospital Network, Antwerp, Belgium. benson.ogunjimi@uantwerpen.be. 40. Department of Pediatric Rheumatology, Antwerp University Hospital, Edegem, Belgium. benson.ogunjimi@uantwerpen.be. 41. Antwerp Center for Pediatric Rheumatology and Autoinflammatory Diseases, Antwerp, Belgium. benson.ogunjimi@uantwerpen.be. 42. Department of Pediatric Rheumatology, Brussels University Hospital, Jette, Belgium. benson.ogunjimi@uantwerpen.be.
Abstract
BACKGROUND: Transcriptome profiling of blood cells is an efficient tool to study the gene expression signatures of rheumatic diseases. This study aims to improve the early diagnosis of pediatric rheumatic diseases by investigating patients' blood gene expression and applying machine learning on the transcriptome data to develop predictive models. METHODS: RNA sequencing was performed on whole blood collected from children with rheumatic diseases. Random Forest classification models were developed based on the transcriptome data of 48 rheumatic patients, 46 children with viral infection, and 35 controls to classify different disease groups. The performance of these classifiers was evaluated by leave-one-out cross-validation. Analyses of differentially expressed genes (DEG), gene ontology (GO), and interferon-stimulated gene (ISG) score were also conducted. RESULTS: Our first classifier could differentiate pediatric rheumatic patients from controls and infection cases with high area-under-the-curve (AUC) values (AUC = 0.8 ± 0.1 and 0.7 ± 0.1, respectively). Three other classifiers could distinguish chronic recurrent multifocal osteomyelitis (CRMO), juvenile idiopathic arthritis (JIA), and interferonopathies (IFN) from control and infection cases with AUC ≥ 0.8. DEG and GO analyses reveal that the pathophysiology of CRMO, IFN, and JIA involves innate immune responses including myeloid leukocyte and granulocyte activation, neutrophil activation and degranulation. IFN is specifically mediated by antibacterial and antifungal defense responses, CRMO by cellular response to cytokine, and JIA by cellular response to chemical stimulus. IFN patients particularly had the highest mean ISG score among all disease groups. CONCLUSION: Our data show that blood transcriptomics combined with machine learning is a promising diagnostic tool for pediatric rheumatic diseases and may assist physicians in making data-driven and patient-specific decisions in clinical practice.
BACKGROUND: Transcriptome profiling of blood cells is an efficient tool to study the gene expression signatures of rheumatic diseases. This study aims to improve the early diagnosis of pediatric rheumatic diseases by investigating patients' blood gene expression and applying machine learning on the transcriptome data to develop predictive models. METHODS: RNA sequencing was performed on whole blood collected from children with rheumatic diseases. Random Forest classification models were developed based on the transcriptome data of 48 rheumatic patients, 46 children with viral infection, and 35 controls to classify different disease groups. The performance of these classifiers was evaluated by leave-one-out cross-validation. Analyses of differentially expressed genes (DEG), gene ontology (GO), and interferon-stimulated gene (ISG) score were also conducted. RESULTS: Our first classifier could differentiate pediatric rheumatic patients from controls and infection cases with high area-under-the-curve (AUC) values (AUC = 0.8 ± 0.1 and 0.7 ± 0.1, respectively). Three other classifiers could distinguish chronic recurrent multifocal osteomyelitis (CRMO), juvenile idiopathic arthritis (JIA), and interferonopathies (IFN) from control and infection cases with AUC ≥ 0.8. DEG and GO analyses reveal that the pathophysiology of CRMO, IFN, and JIA involves innate immune responses including myeloid leukocyte and granulocyte activation, neutrophil activation and degranulation. IFN is specifically mediated by antibacterial and antifungal defense responses, CRMO by cellular response to cytokine, and JIA by cellular response to chemical stimulus. IFN patients particularly had the highest mean ISG score among all disease groups. CONCLUSION: Our data show that blood transcriptomics combined with machine learning is a promising diagnostic tool for pediatric rheumatic diseases and may assist physicians in making data-driven and patient-specific decisions in clinical practice.
Authors: Manuel Rojas; Paula Restrepo-Jiménez; Diana M Monsalve; Yovana Pacheco; Yeny Acosta-Ampudia; Carolina Ramírez-Santana; Patrick S C Leung; Aftab A Ansari; M Eric Gershwin; Juan-Manuel Anaya Journal: J Autoimmun Date: 2018-10-26 Impact factor: 7.094
Authors: Thomas A Griffin; Michael G Barnes; Norman T Ilowite; Judyann C Olson; David D Sherry; Beth S Gottlieb; Bruce J Aronow; Paul Pavlidis; Claas H Hinze; Sherry Thornton; Susan D Thompson; Alexei A Grom; Robert A Colbert; David N Glass Journal: Arthritis Rheum Date: 2009-07
Authors: Dana E Orange; Phaedra Agius; Edward F DiCarlo; Nicolas Robine; Heather Geiger; Jackie Szymonifka; Michael McNamara; Ryan Cummings; Kathleen M Andersen; Serene Mirza; Mark Figgie; Lionel B Ivashkiv; Alessandra B Pernis; Caroline S Jiang; Mayu O Frank; Robert B Darnell; Nithya Lingampali; William H Robinson; Ellen Gravallese; Vivian P Bykerk; Susan M Goodman; Laura T Donlin Journal: Arthritis Rheumatol Date: 2018-04-02 Impact factor: 10.995
Authors: Daniel B Horton; Frank I Scott; Kevin Haynes; Mary E Putt; Carlos D Rose; James D Lewis; Brian L Strom Journal: Pediatrics Date: 2015-07-20 Impact factor: 7.124
Authors: Grant S Schulert; Alex V Pickering; Thuy Do; Sanjeev Dhakal; Ndate Fall; Daniel Schnell; Mario Medvedovic; Nathan Salomonis; Sherry Thornton; Alexei A Grom Journal: Ann Rheum Dis Date: 2020-12-04 Impact factor: 19.103
Authors: Alessandra Tesser; Luciana Martins de Carvalho; Paula Sandrin-Garcia; Alessia Pin; Serena Pastore; Andrea Taddio; Luciana Rodrigues Roberti; Rosane Gomes de Paula Queiroz; Virginia Paes Leme Ferriani; Sergio Crovella; Alberto Tommasini Journal: Arthritis Res Ther Date: 2020-04-25 Impact factor: 5.156