Abstract:
The absence of a diagnostic for long COVID (LC) or post-acute sequelae of COVID-19 (PASC) has profound implications for research and potential therapeutics. Further, symptom-based identification of patients with long-term COVID-19 lacks the specificity to serve as a diagnostic because of the overlap of symptoms with other chronic inflammatory conditions like chronic Lymedisease (CLD), myalgic encephalomyelitis-chronic fatigue syndrome (ME-CFS), and others. Here, we report a machine-learning approach to long COVID diagnosis using cytokine hubs that are also capable of differentiating long COVID from chronic Lyme.
We constructed three tree-based classifiers: decision tree, random forest, and gradient-boosting machine (GBM) and compared their diagnostic capabilities. A 223 patient dataset was partitioned into training (178 patients) and evaluation (45 patients) sets. The GBM model was selected based on performance (89% Sensitivity and 96% Specificity for LC) with no evidence of overfitting.
We tested the GBM on a random dataset of 124 individuals (106 PASC and 18 Lyme), resulting in high sensitivity (97%) and specificity 90% for LC). A Lyme Index composed of two features ((TNF-alpha +IL-4)/(IFN-gamma + IL-2) and (TNF-alpha *IL-4)/(IFN-gamma + IL-2 + CCL3) was constructed as a confirmatory algorithm to discriminate between LC and CLD.
Source: Bruce Patterson, Jose Guevara-Coto, Javier Mora et al. Long COVID Diagnostic with Differentiation from Chronic Lyme Disease using Machine Learning and Cytokine Hubs, 18 January 2024, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-3873244/v1] https://www.researchsquare.com/article/rs-3873244/v1 (Full text)