Identification of Asthma Subtypes Using Clustering Methodologies

Abstract

Asthma is a heterogeneous disease comprising a number of subtypes which may be caused by different pathophysiologic mechanisms (sometimes referred to as endotypes) but may share similar observed characteristics (phenotypes). The use of unsupervised clustering in adult and paediatric populations has identified subtypes of asthma based on observable characteristics such as symptoms, lung function, atopy, eosinophilia, obesity, and age of onset. Here we describe different clustering methods and demonstrate their contributions to our understanding of the spectrum of asthma syndrome. Precise identification of asthma subtypes and their pathophysiological mechanisms may lead to stratification of patients, thus enabling more precise therapeutic and prevention approaches.

Features of asthma which provide meaningful insights for understanding the disease heterogeneity

“…One limitation of the clustering methodologies (including our analyses) is that for the selection of variables, the investigators rely on the data which is available. The majority of previous studies used similar data sources (eg detailed questionnaire responses, sensitization, and lung function), but the variable choice for input into the model has varied . We relied on a detailed clinical assessment carried out in our study.…”

“…Data‐driven methods have been used in both case/patient and birth cohort studies, and are invaluable tools for discovering complex patterns and structures in data sets. However, there has been little consistency in the results between different studies and no unified methodology, leading to a degree of scepticism in the clinical community about the value of these techniques …”

“…However, the clusters which emerged in the HC based on all available variables remained unstable, suggesting that it may not be useful to input all variables into the clustering algorithm, as the overloaded model may not be fully informative. Increasing the number of input variables increases the odds of the variables no longer being dissimilar (a feature important in differentiating clusters) . This introduces high degrees of collinearity among the variables, making it more difficult for the model to identify unique features, and some domains may be over‐represented.…”

“…In most previous studies which used such approaches, the selection of variables used for subtype discovery was either pre‐determined by clinical advice, or by the use of statistical data reduction techniques such as principal component analysis (PCA) . Although valuable information has been gained, and there was some (but not complete) resemblance between the results, most studies reported different disease clusters; several recent reviews have summarized these findings . These inconsistencies may be explained by the inherent heterogeneity among different populations, the differences in clustering techniques used, the lack of consistency in selecting variables, their encodings and transformations, or the use of excessive numbers of variables which may result in subtype “signals” being drowned in the noise …”

The heterogeneity of viral bronchiolitis: A lack of universal consensus definitions

“…It has recently become appreciated that traditional asthma definitions encompass a collection of endotypes with overlapping clinical characteristics. Different asthma subtypes have been suggested, subdivided on multiple characteristics including temporal symptom patterns, age at onset, triggers, severity of exacerbations, medication responsiveness, presence of atopy, and/or patterns of lung inflammation, although a unifying set of classifications has yet to be defined. Furthermore, different endotypes of acute asthma exacerbations have also been suggested, based on whether the pathophysiology is primarily driven by mast cells (anaphylactic), eosinophils (type 1 exacerbation), or neutrophils (type 2 exacerbation) …”