Applying decision tree algorithms to early differential diagnosis between different clinical forms of acute Lyme borreliosis and tick-borne encephalitis

Abstract

Background: Tick-borne encephalitis and Lyme borreliosis are the most common natural focal infections in Russia often arising as a mixed infection, which is often clinically difficult to distinguish from a monoinfection at the onset of the disease that is a result of delayed laboratory verification of the diagnosis and it requires further searching for fundamentally new approaches to the issue of early differential diagnosis of tick-borne infections.Aims: is to develop decision tree algorithms for early differential diagnosis between the mono- and mixed forms of acute Lyme borreliosis and tick-borne encephalitis with prevailing febrile syndrome in clinical picture based on clinical and laboratory data.Materials and methods: We retrospectively analyzed 55 clinical and laboratory parameters obtained from 291 hospitalized tick-borne infections patients with or without erythema migrans at the site of ixodid tick bites in the first week of the disease, who were included in the single-center study from 2010 to 2023. In 211 patients without erythema, the analysis was carried out between three classes depending on the diagnosis: the mixed infection of non-erythematous Lyme borreliosis and tick-borne encephalitis, the mono-infection of non-erythematous Lyme borreliosis or the monoinfection of tick-borne encephalitis. The other two classes, which included 80 patients with erythema, had the mixed infection of acute erythematous Lyme borreliosis and tick-borne encephalitis or erythematous Lyme borreliosis monoinfection. Python programming language was applied to develop two decision tree models. Feature importance was assessed for all predictors. Each patient class was randomly divided into training (70%) and testing (30%) datasets. Accuracy evaluation of the models was based on ROC analysis.Results: The decision tree algorithm for early differential diagnosis among the tick-borne infection patients without erythema migrans included the following most important predictors: maximal fever rise, chills, neutrophil-to-monocyte ratio, ESR, absolute number of reactive lymphocytes and immature granulocytes, and percentage of eosinophils. The model for differential diagnosis between the patients with erythema migrans included the following predictors: maximal fever rise, the absolute number of reactive lymphocytes and immature granulocytes, and the percentage of basophils. Both decision tree models showed excellent predictive values based on sensitivity, specificity, precision, accuracy, and F1 scores, as well as areas under the ROC curve, which were higher than 0.90.Conclusions: Based on clinical and laboratory parameters, two decision tree models with high sensitivity have been developed, which can be easily applied in clinical practice for early differential diagnosis of the tick-borne infections with prevailing fever syndrome.