An algorithm for the classification of mRNA patters in eosinophilic esophagitis: integration of machine learning

Publication date: Available online 19 December 2017
Source:Journal of Allergy and Clinical Immunology
Author(s): Benjamin F. Sallis, Lena Erkert, Sherezade Moñino-Romero, Utkucan Acar, Rina Wu, Liza Konnikova, Willem S. Lexmond, Matthew J. Hamilton, W. Augustine Dunn, Zsolt Szepfalusi, Jon A. Vanderhoof, Scott B. Snapper, Jerrold R. Turner, Jeffrey D. Goldsmith, Lisa A. Spencer, Samuel Nurko, Edda Fiebiger
BackgroundDiagnostic evaluation of eosinophilic esophagitis (EoE) remains difficult, particularly the assessment of the patient's allergic status.ObjectiveEstablish an automated medical algorithm to assist in the evaluation of EoE.MethodsMachine learning techniques were used to establish a diagnostic probability score for EoE (pEoE) 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.ResultsIn the primary analysis, a three-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 94.4%, specificity 92.9%, AUC 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≥37.5 for a patient subpopulation with increased esophageal allergic inflammation.ConclusionThe 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 towards the development of decision trees to define EoE subpopulations and, consequently, will facilitate individualized therapy.

Graphical abstract

http://ift.tt/2BqBi7m