慢阻肺月报202304
文摘
科学
2023-04-23 20:34
上海
![]()
Chest. 2023 Apr 1; PMID: 37011709
Valaciclovir for Epstein-Barr virus suppression in moderate-to-severe COPD (EViSCO): A randomised, double-blind, placebo-controlled trial.Dermot A Linden, Hong Guo-Parke, Michael C McKelvey, et al![]()
American Journal of Respiratory and Critical Care Medicine. 2023 Apr 11; PMID: 37040482Exacerbation Risk and Mortality in COPD GOLD Group A and B Patients with and without Exacerbation History.Lowie E G W Vanfleteren, Anne Lindberg, Caddie Zhou, et al![]()
American Journal of Respiratory and Critical Care Medicine. 2023 Apr 18; PMID: 37071848Eosinophils Sub-Types in Asthmatic and COPD Patients.Carlos Cabrera López, Alejandra Sánchez Santos, Angelina Lemes Castellano, et alEuropean Respiratory Journal. 2023 Mar 29; PMID: 36990472![]()
同样是气道嗜酸性粒细胞，在哮喘和慢阻肺患者中的质可能不同，并因此表现出对治疗（ICS、针对嗜酸性粒细胞的生物制剂）反应的差异。Preterm birth and asthma and COPD in adulthood: a nationwide register study from two Nordic countries.Anna Pulakka, Kari Risnes, Johanna Metsälä, et al![]()
Thorax. 2023 Apr 3; PMID: 37012070Estimating individual treatment effects on COPD exacerbations by causal machine learning on randomised controlled trials.Kenneth Verstraete, Iwein Gyselinck, Helene Huts, et al![]()
该研究引入了一种数据分析方法，即ITE模型，其中将RCT受试者按照预测的ITE排序，从而筛选出从治疗中受益、无反应或有危害的个体（下图）。![]()
看起来是回应了重视个体特征在治疗选择中的作用，文末作者总结道，这种模型有助于临床上慢阻肺的个体治疗决策。只是，看上去是使用了眼花缭乱的机器学习建模，但根本上输出取决于输入，比如SUMMIT研究如果没有丰富的EOS数据，建的模型也就不会有EOS。所以人和现阶段的人工智能的区别中一个关键点或许是，人脑能够通过归纳和演绎，有根据的联想，突破现存框架，福至心灵，突发奇想，来一招天外飞仙...
