The diagnostic potential of proteomics and machine learning in Lyme neuroborreliosis

Abstract

Abstract Lyme neuroborreliosis (LNB), a nervous system infection caused by tick-borne spirochetes of the Borrelia burgdorferi sensu lato complex, is among the most frequent bacterial infections of the nervous system in Europe. Early diagnosis and continuous monitoring remain challenging due to limited sensitivity and specificity of current methods and requires invasive lumbar punctures, underscoring the need for improved, less invasive diagnostic tools. Here, we apply mass spectrometry-based proteomics to analyse 308 cerebrospinal fluid (CSF) samples and 207 plasma samples from patients with LNB, viral meningitis, controls and other manifestations of Lyme borreliosis. Diagnostic panels of regulated proteins are identified and evaluated through machine learning-assisted proteome analyses. In CSF, the classifier distinguishes LNB from viral meningitis and controls with AUCs of 0.92 and 0.90, respectively. In plasma, LNB is distinguished from controls with an AUC of 0.80. Our findings suggest a potential diagnostic role for machine learning-assisted proteomics in adults with LNB.