Machine Learning with Alpha Toxin Phenotype to Predict Clinical Outcome in Patients with Bloodstream Infection.

bloodstream (SAB) infection remains a leading cause of sepsis-related mortality. Yet, current treatment does not account for variable virulence traits that mediate host dysregulated immune response, such as SA α-toxin (Hla)-mediated thrombocytopenia. Here, we applied machine learning (ML) to bacterial growth images combined with platelet count data to predict patient outcomes. We profiled Hla phenotypes of SA isolates collected from patients with bacteremia by taking smartphone images of beta-hemolytic growth on sheep blood agar (SBA). Electronic medical records were reviewed to extract relevant laboratory and clinical data. A convolutional neural network was applied to process the plate image data for input along with day 1 patient platelet count to generate ML-based models that predict thrombocytopenia on day 4 and mortality. A total of 229 patients infected with SA strains exhibiting varying zone sizes of beta-hemolysis on SBA were included. A total of 539 images of bacterial growth on SBA were generated as inputs for model development. One-third of patients developed thrombocytopenia at onset, with an overall mortality rate of 18.8%. The models developed from the ML algorithm showed strong performance (AUC 0.92) for predicting thrombocytopenia on day 4 of infection and modest performance (AUC 0.711) for mortality. Our findings support further development and validation of a proof-of-concept ML application in digital microbiology, with a measure of bacterial virulence factor production that carries prognostic significance and can help guide treatment selection.