Hewlett Packard Enterprise, USA.
Hewlett Packard Enterprise, USA.
Med Hypotheses. 2021 Jan;146:110395. doi: 10.1016/j.mehy.2020.110395. Epub 2020 Nov 28.
We present the hypothesis to the scientific community actively designing clinical trials and recommending public health guidelines to control the pandemic that - "Tetanus vaccination may be contributing to reduced severity of the COVID-19 infection" - and urge further research to validate or invalidate the effectiveness of the tetanus toxoid vaccine against COVID-19. This hypothesis was revealed by an explainable artificial intelligence system unleashed on open public biomedical datasets. As a foundation for scientific rigor, we describe the data and the artificial intelligence system, document the provenance and methodology used to derive the hypothesis and also gather potentially relevant data/evidence from recent studies. We conclude that while correlations may not be reason for causation, correlations from multiple sources is more than a serendipitous coincidence that is worthy of further and deeper investigation.
我们向积极设计临床试验和推荐公共卫生指南以控制大流行的科学界提出假设,即“破伤风疫苗可能有助于减轻 COVID-19 感染的严重程度”,并敦促进一步研究以验证或否定破伤风类毒素疫苗对 COVID-19 的有效性。这一假设是由一个可解释的人工智能系统在公开的公共生物医学数据集上揭示的。作为科学严谨性的基础,我们描述了数据和人工智能系统,记录了得出假设所使用的出处和方法,并从最近的研究中收集了潜在相关的数据/证据。我们的结论是,虽然相关关系不一定是因果关系的原因,但来自多个来源的相关关系不仅仅是一个偶然的巧合,值得进一步深入调查。