replying to D. Giacobbe Nature Machine Intelligence https://doi.org/10.1038/s42256-020-0207-0 (2020)
The article1 by Giacobbe is very interesting and relevant. They suggest a new research direction regarding the hypothesis that severe bacterial superinfections are a major cause of death in patients with COVID-19. We would be open to exploring this hypothesis with the proposed machine learning approaches2, provided that new data becomes available. The new data would need to confirm the existence of bacterial superinfections and quantify the type and severity of the infection. We could then test the impact of bacterial superinfections on COVID-19 mortality and determine how this additional information could improve predictions of patient outcomes. We also agree that ongoing collaboration and discussion between clinicians and machine learning modellers would drive advances in this field.
Giacobbe, D. Clinical interpretation of an interpretable prognostic model for patients with COVID-19. Nat. Mach. Intell. https://doi.org/10.1038/s42256-020-0207-0 (2020)
Yan, L., Zhang, H. & Goncalves, J. et al. An interpretable mortality prediction model for COVID-19 patients. Nat. Mach. Intell. 2, 283–288 (2020).
The authors declare no competing interests.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Yuan, Y., Goncalves, J., Xiao, Y. et al. Reply to: Clinical interpretation of an interpretable prognostic model for patients with COVID-19. Nat Mach Intell (2020). https://doi.org/10.1038/s42256-020-0206-1