An algorithm for the classification of mRNA patterns in eosinophilic esophagitis: Integration of machine learning - 05/04/18
Abstract |
Background |
Diagnostic evaluation of eosinophilic esophagitis (EoE) remains difficult, particularly the assessment of the patient's allergic status.
Objective |
This study sought to establish an automated medical algorithm to assist in the evaluation of EoE.
Methods |
Machine learning techniques were used to establish a diagnostic probability score for EoE, p(EoE), based on esophageal mRNA transcript patterns from biopsies of patients with EoE, gastroesophageal reflux disease and controls. Dimensionality reduction in the training set established weighted factors, which were confirmed by immunohistochemistry. Following weighted factor analysis, p(EoE) was determined by random forest classification. Accuracy was tested in an external test set, and predictive power was assessed with equivocal patients. Esophageal IgE production was quantified with epsilon germ line (IGHE) transcripts and correlated with serum IgE and the Th2-type mRNA profile to establish an IGHE score for tissue allergy.
Results |
In the primary analysis, a 3-class statistical model generated a p(EoE) score based on common characteristics of the inflammatory EoE profile. A p(EoE) ≥ 25 successfully identified EoE with high accuracy (sensitivity: 90.9%, specificity: 93.2%, area under the curve: 0.985) and improved diagnosis of equivocal cases by 84.6%. The p(EoE) changed in response to therapy. A secondary analysis loop in EoE patients defined an IGHE score of ≥37.5 for a patient subpopulation with increased esophageal allergic inflammation.
Conclusions |
The development of intelligent data analysis from a machine learning perspective provides exciting opportunities to improve diagnostic precision and improve patient care in EoE. The p(EoE) and the IGHE score are steps toward the development of decision trees to define EoE subpopulations and, consequently, will facilitate individualized therapy.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Key words : Allergy diagnosis, eosinophils, eosinophilic esophagitis, chronic allergic inflammation, IgE, machine learning, medical algorithm
Abbreviations used : CCL, EGID, EoE, GERD, HIF1A, IGHE, p(EoE), ROC
Plan
| E.F. is supported by a Bridge Grant from the Research Council of Boston Children's Hospital, an Emerging Investigator Award from Food Allergy Research & Education, a Senior Research Award from the Crohn's and Colitis Foundation, and an unrestricted gift from the Mead Johnson Nutrition Company. S.M.-R. was supported by the Fonds zur Förderung der wissenschaftlichen Forschung grant DK W1248. W.A.D. is supported by a grant from The Helmsley Charitable Trust through the Very Early Onset Inflammatory Bowel Disease Consortium. M.J.H. is supported by National Institutes of Health (NIH) grant NIHDK094971. J.R.T. is supported by NIH grants R01DK61931, R01DK68271, and R24DK099803 as well as a Senior Research Award from the Crohn's and Colitis Foundation. L.A.S. is supported by NIH grant R01AI121186. This work was further supported by an NIH grant of the Harvard Digestive Diseases Center (P30DK034854, Cores B and C). |
|
| Disclosure of potential conflict of interest: W. S. Lexmond has received grant funding from Ter Meulen Fund, Royal Netherlands Academy of Sciences and the Banning-de Jong Fund; fees from Kiniksa Pharmaceuticals for consultation; and his institution has received grant funds from Mead Johnson Company. Matthew J. Hamilton's institution has grants pending with GlaxoSmithKline; and he has received consultancy fees from Pfizer, Takeda, and Protal Instruments. J. D. Goldsmith has received consulting fees from Roche Diagnostics and Takeda Pharmaceuticals; travel support from the College of American Pathologists and the Crohn's and Colitis Foundation; and fees for expert testimony. The rest of the authors declare that they have no relevant conflicts of interest. |
Vol 141 - N° 4
P. 1354 - avril 2018 Retour au numéro
Article précédent
- Allergen specificity of early peanut consumption and effect on development of allergic disease in the Learning Early About Peanut Allergy study cohort
- George du Toit, Peter H. Sayre, Graham Roberts, Kaitie Lawson, Michelle L. Sever, Henry T. Bahnson, Helen R. Fisher, Mary Feeney, Suzana Radulovic, Monica Basting, Marshall Plaut, Gideon Lack
- Step-up empiric elimination diet for pediatric and adult eosinophilic esophagitis: The 2-4-6 study
- Javier Molina-Infante, Ángel Arias, Javier Alcedo, Ruth Garcia-Romero, Sergio Casabona-Frances, Alicia Prieto-Garcia, Ines Modolell, Pedro L. Gonzalez-Cordero, Isabel Perez-Martinez, Jose Luis Martin-Lorente, Carlos Guarner-Argente, Maria L. Masiques, Victor Vila-Miravet, Roger Garcia-Puig, Edoardo Savarino, Carlos Teruel Sanchez-Vegazo, Cecilio Santander, Alfredo J. Lucendo
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?