阻塞性睡眠呼吸暂停：分类聚类分析及可视化。

Obstructive sleep apnea: A categorical cluster analysis and visualization.

机构信息

MEDCIDS-FMUP - Community Medicine, Information and Decision Sciences, Faculty of Medicine of the University of Porto, Porto, Portugal; CINTESIS - Center for Health Technology and Services Research, Porto, Portugal.

出版信息

Pulmonology. 2023 May-Jun;29(3):207-213. doi: 10.1016/j.pulmoe.2021.10.003. Epub 2021 Nov 17.

DOI:10.1016/j.pulmoe.2021.10.003

PMID:34801436

Abstract

INTRODUCTION AND OBJECTIVES

Obstructive sleep apnea (OSA) is a prevalent sleep condition which is very heterogeneous although not formally characterized as such, resulting in missed or delayed diagnosis. Cluster analysis has been used in different clinical domains, particularly within sleep disorders. We aim to understand OSA heterogeneity and provide a variety of cluster visualizations to communicate the information clearly and efficiently.

MATERIALS AND METHODS

We applied an extension of k-means to be used in categorical variables: k-modes, to identify OSA patients' groups, based on demographic, physical examination, clinical history, and comorbidities characterization variables (n = 40) obtained from a derivation and validation cohorts (211 and 53, respectively) from the northern region of Portugal. Missing values were imputed with k-nearest neighbours (k-NN) and a chi-square test was held for feature selection.

RESULTS

Thirteen variables were inserted in phenotypes, resulting in the following three clusters: Cluster 1, middle-aged males reporting witnessed apneas and high alcohol consumption before sleep; Cluster 2, middle-aged women with increased neck circumference (NC), non-repairing sleep and morning headaches; and Cluster 3, obese elderly males with increased NC, witnessed apneas and alcohol consumption. Patients from the validation cohort assigned to different clusters showed similar proportions when compared with the derivation cohort, for mild (C1: 56 vs 75%, P = 0.230; C2: 61 vs 75%, P = 0.128; C3: 45 vs 48%, P = 0.831), moderate (C1: 24 vs 25%; C2: 20 vs 25%; C3: 25 vs 19%) and severe (C1: 20 vs 0%; C2: 18 vs 0%; C3: 29 vs 33%) levels. Therefore, the allocation supported the validation of the obtained clusters.

CONCLUSIONS

Our findings suggest different OSA patients' groups, creating the need to rethink these patients' stereotypical baseline characteristics.

摘要

介绍和目的

阻塞性睡眠呼吸暂停（OSA）是一种普遍存在的睡眠状况，尽管尚未正式确定其特征，但由于诊断的遗漏或延迟，这种状况具有很大的异质性。聚类分析已在不同的临床领域中使用，特别是在睡眠障碍中。我们旨在了解 OSA 的异质性，并提供多种聚类可视化效果，以清晰高效地传达信息。

材料和方法

我们应用了一种扩展的 k-均值算法，即 k-模式，用于根据人口统计学、体格检查、临床病史和合并症特征变量（分别从葡萄牙北部的一个推导队列和验证队列中获得 n=40 和 n=53），识别 OSA 患者的分组。缺失值使用最近邻（k-NN）进行插补，并进行卡方检验进行特征选择。

结果

有 13 个变量被纳入表型，结果分为以下三个聚类：聚类 1，中年男性报告有目击性呼吸暂停和睡前大量饮酒；聚类 2，中年女性颈部周长（NC）增加，睡眠无法修复且有晨起头痛；聚类 3，肥胖老年男性 NC 增加，有目击性呼吸暂停和饮酒。与推导队列相比，验证队列中分配到不同聚类的患者具有相似的比例，对于轻度（C1：56%对 75%，P=0.230；C2：61%对 75%，P=0.128；C3：45%对 48%，P=0.831）、中度（C1：24%对 25%；C2：20%对 25%；C3：25%对 19%）和重度（C1：20%对 0%；C2：18%对 0%；C3：29%对 33%）水平。因此，该分配支持获得的聚类的验证。