Noëmi Rebecca Meier1,2, Thomas M Sutter3, Marc Jacobsen4, Tom H M Ottenhoff5, Julia E Vogt3, Nicole Ritz1,2,6,7. 1. Mycobacterial Research Laboratory, University of Basel Children's Hospital, Basel, Switzerland. 2. Faculty of Medicine, University of Basel, Basel, Switzerland. 3. Department of Computer Science, Medical Data Science, Eidgenössische Technische Hochschule (ETH) Zurich, Zurich, Switzerland. 4. Department of General Pediatrics, Neonatology and Pediatric Cardiology, University Children's Hospital, Heinreich Heine University, Düsseldorf, Germany. 5. Department of Infectious Diseases, Leiden University Medical Center, Leiden, Netherlands. 6. Pediatric Infectious Diseases and Vaccinology Unit, University of Basel Children's Hospital, Basel, Switzerland. 7. Department of Pediatrics, Royal Children's Hospital Melbourne, University of Melbourne, Parkville, VIC, Australia.
Abstract
Rationale: Tuberculosis diagnosis in children remains challenging. Microbiological confirmation of tuberculosis disease is often lacking, and standard immunodiagnostic including the tuberculin skin test and interferon-γ release assay for tuberculosis infection has limited sensitivity. Recent research suggests that inclusion of novel Mycobacterium tuberculosis antigens has the potential to improve standard immunodiagnostic tests for tuberculosis. Objective: To identify optimal antigen-cytokine combinations using novel Mycobacterium tuberculosis antigens and cytokine read-outs by machine learning algorithms to improve immunodiagnostic assays for tuberculosis. Methods: A total of 80 children undergoing investigation of tuberculosis were included (15 confirmed tuberculosis disease, five unconfirmed tuberculosis disease, 28 tuberculosis infection and 32 unlikely tuberculosis). Whole blood was stimulated with 10 novel Mycobacterium tuberculosis antigens and a fusion protein of early secretory antigenic target (ESAT)-6 and culture filtrate protein (CFP) 10. Cytokines were measured using xMAP multiplex assays. Machine learning algorithms defined a discriminative classifier with performance measured using area under the receiver operating characteristics. Measurements and main results: We found the following four antigen-cytokine pairs had a higher weight in the discriminative classifier compared to the standard ESAT-6/CFP-10-induced interferon-γ: Rv2346/47c- and Rv3614/15c-induced interferon-gamma inducible protein-10; Rv2031c-induced granulocyte-macrophage colony-stimulating factor and ESAT-6/CFP-10-induced tumor necrosis factor-α. A combination of the 10 best antigen-cytokine pairs resulted in area under the curve of 0.92 ± 0.04. Conclusion: We exploited the use of machine learning algorithms as a key tool to evaluate large immunological datasets. This identified several antigen-cytokine pairs with the potential to improve immunodiagnostic tests for tuberculosis in children.
Rationale: Tuberculosis diagnosis in children remains challenging. Microbiological confirmation of tuberculosis disease is often lacking, and standard immunodiagnostic including the tuberculin skin test and interferon-γ release assay for tuberculosis infection has limited sensitivity. Recent research suggests that inclusion of novel Mycobacterium tuberculosis antigens has the potential to improve standard immunodiagnostic tests for tuberculosis. Objective: To identify optimal antigen-cytokine combinations using novel Mycobacterium tuberculosis antigens and cytokine read-outs by machine learning algorithms to improve immunodiagnostic assays for tuberculosis. Methods: A total of 80 children undergoing investigation of tuberculosis were included (15 confirmed tuberculosis disease, five unconfirmed tuberculosis disease, 28 tuberculosis infection and 32 unlikely tuberculosis). Whole blood was stimulated with 10 novel Mycobacterium tuberculosis antigens and a fusion protein of early secretory antigenic target (ESAT)-6 and culture filtrate protein (CFP) 10. Cytokines were measured using xMAP multiplex assays. Machine learning algorithms defined a discriminative classifier with performance measured using area under the receiver operating characteristics. Measurements and main results: We found the following four antigen-cytokine pairs had a higher weight in the discriminative classifier compared to the standard ESAT-6/CFP-10-induced interferon-γ: Rv2346/47c- and Rv3614/15c-induced interferon-gamma inducible protein-10; Rv2031c-induced granulocyte-macrophage colony-stimulating factor and ESAT-6/CFP-10-induced tumor necrosis factor-α. A combination of the 10 best antigen-cytokine pairs resulted in area under the curve of 0.92 ± 0.04. Conclusion: We exploited the use of machine learning algorithms as a key tool to evaluate large immunological datasets. This identified several antigen-cytokine pairs with the potential to improve immunodiagnostic tests for tuberculosis in children.
Authors: Susanna Commandeur; Krista E van Meijgaarden; May Young Lin; Kees L M C Franken; Annemieke H Friggen; Jan Wouter Drijfhout; Fredrik Oftung; Gro Ellen Korsvold; Annemieke Geluk; Tom H M Ottenhoff Journal: Clin Vaccine Immunol Date: 2011-01-19
Authors: Susanna Commandeur; Krista E van Meijgaarden; Corine Prins; Alexander V Pichugin; Karin Dijkman; Susan J F van den Eeden; Annemieke H Friggen; Kees L M C Franken; Gregory Dolganov; Igor Kramnik; Gary K Schoolnik; Fredrik Oftung; Gro Ellen Korsvold; Annemieke Geluk; Tom H M Ottenhoff Journal: J Immunol Date: 2013-01-14 Impact factor: 5.422
Authors: Young Yil Bahk; Suk Am Kim; Ji-Soo Kim; Hyung-Jin Euh; Gil-Han Bai; Sang-Nae Cho; Yu Sam Kim Journal: Proteomics Date: 2004-11 Impact factor: 3.984
Authors: I Latorre; J Díaz; I Mialdea; M Serra-Vidal; N Altet; C Prat; N Díez; A Escribano; I Casas; C Rodrigo; V Ausina; M Ruhwald; J Domínguez Journal: J Infect Date: 2014-06-27 Impact factor: 6.072
Authors: Mᵃdel Mar Serra-Vidal; Irene Latorre; Kees L C M Franken; Jéssica Díaz; Maria Luiza de Souza-Galvão; Irma Casas; José Maldonado; Cèlia Milà; Jordi Solsona; M Ángeles Jimenez-Fuentes; Neus Altet; Alícia Lacoma; Juan Ruiz-Manzano; Vicente Ausina; Cristina Prat; Tom H M Ottenhoff; José Domínguez Journal: Front Microbiol Date: 2014-10-08 Impact factor: 5.640
Authors: Noemi Rebecca Meier; Manuel Battegay; Tom H M Ottenhoff; Hansjakob Furrer; Johannes Nemeth; Nicole Ritz Journal: Front Immunol Date: 2021-03-12 Impact factor: 7.561