High generation of reactive oxygen species from neutrophils in patients with severe COVID-19.

Neutrophilia and an elevated neutrophil:lymphocyte ratio are both characteristic features of severe COVID-19 infection. However, functional neutrophil responses have been poorly investigated in this setting. We utilised a novel PMA-based stimulation assay to determine neutrophil-derived reactive oxygen species (ROS) generation in patients with severe COVID-19 infection, non-COVID related sepsis and healthy study participants. ROS production was markedly elevated in COVID-19 patients with median values ninefold higher than in healthy controls and was particularly high in patients on mechanical ventilation. ROS generation correlated strongly with neutrophil count and elevated levels were also seen in patients with non-COVID related sepsis. Relative values, adjusted for neutrophil count, were high in both groups but extreme low or high values were seen in two patients who died shortly after testing, potentially indicating a predictive value for neutrophil function. Our results show that the high levels of neutrophils observed in patients with COVID-19 and sepsis exhibit functional capacity for ROS generation. This may contribute to the clinical features of acute disease and represents a potential novel target for therapeutic intervention.

Ensemble learning for poor prognosis predictions: A case study on SARS-CoV-2.

OBJECTIVE: Risk prediction models are widely used to inform evidence-based clinical decision making. However, few models developed from single cohorts can perform consistently well at population level where diverse prognoses exist (such as the SARS-CoV-2 [severe acute respiratory syndrome coronavirus 2] pandemic). This study aims at tackling this challenge by synergizing prediction models from the literature using ensemble learning. MATERIALS AND METHODS: In this study, we selected and reimplemented 7 prediction models for COVID-19 (coronavirus disease 2019) that were derived from diverse cohorts and used different implementation techniques. A novel ensemble learning framework was proposed to synergize them for realizing personalized predictions for individual patients. Four diverse international cohorts (2 from the United Kingdom and 2 from China; N = 5394) were used to validate all 8 models on discrimination, calibration, and clinical usefulness. RESULTS: Results showed that individual prediction models could perform well on some cohorts while poorly on others. Conversely, the ensemble model achieved the best performances consistently on all metrics quantifying discrimination, calibration, and clinical usefulness. Performance disparities were observed in cohorts from the 2 countries: all models achieved better performances on the China cohorts. DISCUSSION: When individual models were learned from complementary cohorts, the synergized model had the potential to achieve better performances than any individual model. Results indicate that blood parameters and physiological measurements might have better predictive powers when collected early, which remains to be confirmed by further studies. CONCLUSIONS: Combining a diverse set of individual prediction models, the ensemble method can synergize a robust and well-performing model by choosing the most competent ones for individual patients.