BackgroundMyalgic encephalomyelitis (ME) is a complex and debilitating disease that often initially presents with flu-like symptoms, accompanied by incapacitating fatigue. Currently, there are no objective biomarkers or laboratory tests that can be used to unequivocally diagnosis ME; therefore, a diagnosis is made when a patient meets series of a costly and subjective inclusion and exclusion criteria. The purpose of the present study was to evaluate the utility of four clinical parameters in diagnosing ME.MethodsIn the present study, we utilized logistic regression and classification and regression tree analysis to conduct a retrospective investigation of four clinical laboratory in 140 ME cases and 140 healthy controls.ResultsCorrelations between the covariates ranged between [− 0.26, 0.61]. The best model included the serum levels of the soluble form of CD14 (sCD14), serum levels of prostaglandin E2 (PGE2), and serum levels of interleukin 8, with coefficients 0.002, 0.249, and 0.005, respectively, and p-values of 3 × 10−7, 1 × 10−5, and 3 × 10−3, respectively.ConclusionsOur findings show that these parameters may help physicians in their diagnosis of ME and may additionally shed light on the pathophysiology of this disease.Electronic supplementary materialThe online version of this article (10.1186/s12967-018-1696-z) contains supplementary material, which is available to authorized users.