A diagnostic classifier for gene expression-based identification of early Lyme disease

BackgroundLyme disease is a tick-borne illness that causes an estimated 476,000 infections annually in the United States. New diagnostic tests are urgently needed, as existing antibody-based assays lack sufficient sensitivity and specificity.MethodsHere we perform transcriptome profiling by RNA sequencing (RNA-Seq), targeted RNA-Seq, and/or machine learning-based classification of 263 peripheral blood mononuclear cell samples from 218 subjects, including 94 early Lyme disease patients, 48 uninfected control subjects, and 57 patients with other infections (influenza, bacteremia, or tuberculosis). Differentially expressed genes among the 25,278 in the reference database are selected based on & GE;1.5-fold change, & LE;0.05 p value, and & LE;0.001 false-discovery rate cutoffs. After gene selection using a k-nearest neighbor algorithm, the comparative performance of ten different classifier models is evaluated using machine learning.ResultsWe identify a 31-gene Lyme disease classifier (LDC) panel that can discriminate between early Lyme patients and controls, with 23 genes (74.2%) that have previously been described in association with clinical investigations of Lyme disease patients or in vitro cell culture and rodent studies of Borrelia burgdorferi infection. Evaluation of the LDC using an independent test set of samples from 63 subjects yields an overall sensitivity of 90.0%, specificity of 100%, and accuracy of 95.2%. The LDC test is positive in 85.7% of seronegative patients and found to persist for & GE;3 weeks in 9 of 12 (75%) patients.ConclusionsThese results highlight the potential clinical utility of a gene expression classifier for diagnosis of early Lyme disease, including in patients negative by conventional serologic testing. Servellita et al. develop a machine learning-based classifier to diagnose Lyme disease using gene expression data. The classifier achieves high sensitivity for early infections, even prior to positivity on antibody testing. Plain language summaryLyme disease is a bacterial infection spread by ticks and there are nearly half a million cases a year in the United States. However, the disease is difficult to diagnose and existing laboratory tests have limited accuracy. Here, we develop a new genetic test, described as a Lyme disease classifier (LDC), for diagnosing early Lyme disease from blood samples by assessing the patient's response to the infection. We find that the LDC can identify early Lyme disease patients (those presenting with symptoms within weeks of a tick bite) accurately, even before standard laboratory tests turn positive. In the future, the LDC may be clinically useful as a test for Lyme disease to diagnose patients earlier in the course of their illness, thus guiding more timely and effective treatment for the infection.