Data-augmented machine learning redefines the effective concentration of eculizumab in complement blood disorders

Eculizumab, a humanized monoclonal antibody targeting the complement lytic pathway protein C5, has demonstrated high efficacy in the treatment of paroxysmal nocturnal hemoglobinuria, atypical hemolytic uremic syndrome, generalized myasthenia gravis, and neuromyelitis optica spectrum disorder. However, recent reports have highlighted patients who exhibit a lack of treatment response, necessitating an increase in the recommended dose or a reduction in the dosing interval. In this study, we employed machine-learning predictive models to identify the optimal blood concentration of eculizumab to inhibit the complement lytic pathway. Additionally, we examined the impact of data augmentation through the generation of artificial data on the predictive performance of these models. In conclusion, our machine learning model predicts that the target blood concentration of eculizumab should be increased to a minimum of 152-162 μg mL–1 (up from 50-100 μg mL–1) to achieve a more complete inhibition of the complement system’s lytic pathway.