RT期刊文章SR电子T1无人监督的表型聚类确定儿童的临床地位与囊性纤维化摩根富林明欧洲呼吸杂志乔和J FD欧元欧洲呼吸学会SP 2002881 10.1183/13993003.02881 -2020签证官58 2 A1 Filipow,妮可A1戴维斯,格温妮丝A1主要,埃莉诺A1 Sebire,188bet官网地址囊性纤维化(CF)是一种多系统疾病，仅根据肺功能评估疾病严重程度可能不合适。这项研究的目的是开发一种综合的机器学习算法来评估独立于肺功能的儿童的临床状态。方法采用综合前瞻性收集的临床数据库(加拿大多伦多)进行无监督聚类分析。然后通过对目前和未来的肺功能、未来住院的风险和未来口服抗生素治疗的肺加重风险对确定的群集进行比较。采用k近邻(KNN)算法对聚类进行前瞻性分配。这些方法在来自大奥蒙德街医院(Great Ormond Street Hospital, GOSH)的儿科临床CF数据集中得到验证。结果基于530个个体的12 200次接触，优化聚类模型识别出4个(A-D)表型簇。两组患者(A和B)病情轻微，1秒内用力呼气量(FEV1)高，口服抗生素治疗后住院和肺部加重的风险低。与严重疾病一致的两组簇(C和D)也被确定为低FEV1。D组患者接受口服抗生素治疗至住院和肺部恶化的时间最短。 The outcomes were consistent in 3124 encounters from 171 children at GOSH. The KNN cluster allocation error rate was low, at 2.5% (Toronto) and 3.5% (GOSH).Conclusion Machine learning derived phenotypic clusters can predict disease severity independent of lung function and could be used in conjunction with functional measures to predict future disease trajectories in CF patients.Machine learning-derived clusters can be used to define clinical status in children with cystic fibrosis https://bit.ly/3nudlPG