Machine Learning Logistic Regression Model for Early Decision Making in Referral of Children with Cervical Lymphadenopathy Suspected of Lymphoma

Abstract

While cervical lymphadenopathy is common in children, a decision model for detecting high-grade lymphoma is lacking. Previously reported individual lymphoma-predicting factors and multivariate models were not sufficiently discriminative for clinical application. To develop a diagnostic scoring tool, we collected data from all children with cervical lymphadenopathy referred to our national pediatric oncology center within 30 months (n = 182). Thirty-nine putative lymphoma-predictive factors were investigated. The outcome groups were classical Hodgkin lymphoma (cHL), nodular lymphocyte-predominant Hodgkin lymphoma (NLPHL), non-Hodgkin lymphoma (NHL), other malignancies, and a benign group. We integrated the best univariate predicting factors into a multivariate, machine learning model. Logistic regression allocated each variable a weighing factor. The model was tested in a different patient cohort (n = 60). We report a 12-factor diagnostic model with a sensitivity of 95% (95% CI 89–98%) and a specificity of 88% (95% CI 77–94%) for detecting cHL and NHL. Our 12-factor diagnostic scoring model is highly sensitive and specific in detecting high-grade lymphomas in children with cervical lymphadenopathy. It may enable fast referral to a pediatric oncologist in patients with high-grade lymphoma and may reduce the number of referrals and unnecessary invasive procedures in children with benign lymphadenopathy.