Hemocytometric Parameters Associated with Bacterial and Viral Etiology in COPD Exacerbations: An Exploratory Analysis

Exacerbations of Chronic Obstructive Pulmonary Disease (ECOPD) are often triggered by bacterial and viral infections, yet current diagnostic methods are time-consuming and biomarkers (e.g. C-reactive protein (CRP)) show limited accuracy in differentiating between these triggers. Hemocytometric parameters derived from routine blood analysis may provide a rapid, accessible alternative. This study evaluated whether machine learning applied to routine hemocytometric parameters can accurately distinguish between bacterial and viral etiology in ECOPD.We performed a post hoc, exploratory analysis on 64 patients hospitalized for an ECOPD. Bacterial and viral pathogens were detected using sputum culture and/or polymerase chain reaction on nasopharyngeal swab samples. After preprocessing 53 hemocytometric parameters, Random Forest models were developed using selected hemocytometry features for bacterial (n = 12) and viral (n = 6) presence. Model performance was assessed using repeated stratified train-test splits with out-of-sample predictions.Hemocytometry-based models showed good performance for classification of bacterial presence (AUC 0.783; 95% CI 0.713–0.853), with accuracy, sensitivity, and specificity of 72%, 73%, and 70%, respectively, outperforming CRP (AUC 0.585, p < 0.001). For classification of viral presence, the model achieved an AUC of 0.717 (95% CI 0.636–0.798), with accuracy, sensitivity, and specificity of 72%, 59%, and 80%, respectively.In this exploratory analysis, hemocytometry-based machine learning models show promising performance for classifying the presence of bacterial and viral infections in ECOPD, outperforming CRP. The worldwide, routine availability of hemocytometry underscores the relevance of our findings as a practical tool for identifying bacterial and viral causes and supports potential for rapid clinical implementation. However, they require validation in larger cohorts.Clinical trial registration NCT04961060.