Abstract
Preschool wheezing and childhood asthma create a heavy disease burden which is only exacerbated by the complexity of the conditions. Preschool wheezing exhibits both “curricular” and “aetiological” heterogeneity: that is, heterogeneity across patients both in the time-course of its development and in its underpinning pathological mechanisms. Since these are not fully understood, but clinical presentations across patients may nonetheless be similar, current diagnostic labels are imprecise—not mapping cleanly onto underlying disease mechanisms—and prognoses uncertain. These uncertainties also make a identifying new targets for therapeutic intervention difficult. In the past few decades, carefully designed birth cohort studies have collected “big data” on a large scale, incorporating not only a wealth of longitudinal clinical data, but also detailed information from modalities as varied as imaging, multiomics, and blood biomarkers. The profusion of big data has seen the proliferation of what we term “modern data approaches” (MDAs)—grouping together machine learning, artificial intelligence, and data science—to make sense and make use of this data. In this review, we survey applications of MDAs (with an emphasis on machine learning) in childhood wheeze and asthma, highlighting the extent of their successes in providing tools for prognosis, unpicking the curricular heterogeneity of these conditions, clarifying the limitations of current diagnostic criteria, and indicating directions of research for uncovering the etiology of the diseases underlying these conditions. Specifically, we focus on the trajectories of childhood wheeze phenotypes. Further, we provide an explainer of the nature and potential use of MDAs and emphasize the scope of what we can hope to achieve with them.
 |
| Comparison of internal homogeneity of wheezing phenotypes derived using the novel method based on spells and the Partition Around Medoids-PAM clustering (panel A) and binary LCA approaches (panel B); |
Key Message
The overall evidence to date suggests that: (1) Machine learning approaches have better performance over regression-based models for the prediction of childhood asthma, but the clinical utility of such models is limited by the use of the aggregated outcome of “asthma diagnosis”; (2) There are distinct pathophysiological clusters of preschool wheeze which are underpinned by unique genetic architectures but which are not associated with diagnoses used in clinical practice; (3) All clusters/phenotypes of preschool wheezing are associated with impaired lung function in early adulthood; (4) In cohorts with long-term follow-up, using large and imputed data sets, we can apply modern data analysis techniques to clearly differentiate early childhood wheezers whose symptoms resolve from those with different wheezing patterns which persist to adulthood; (5) This provides an opportunity to capitalize on extant longitudinal data sets and novel analytical methodologies to address the key questions of predicting the long-term outcomes of preschool wheezing and understanding the mechanisms associated with persistence.
No comments:
Post a Comment