OBJECTIVE: The objective of this scoping review is to identify and describe the literature on the use of geospatial data in pediatric asthma research. INTRODUCTION: Asthma is one of the most common pediatric chronic diseases in the United States, disproportionately affecting low-income patients. Asthma exacerbations may be triggered by local environmental factors, such as air pollution or exposure to indoor allergens. Geographic information systems are increasingly recognized as tools that use geospatial data to enhance understanding of the link between environmental exposure, social determinants of health, and clinical outcomes. Geospatial data in pediatric asthma may help inform risk factors for asthma severity, and guide targeted clinical and social interventions. INCLUSION CRITERIA: This review will consider studies that utilize geospatial data in the evaluation of pediatric patients with asthma, ages 2 to 18 years, in the United States. Mixed samples of adults and children will also be considered. Geospatial data will include any external non-clinical geographic-based data source that uses a patients environment or context. METHODS: The following databases will be searched: PubMed, Embase, Cochrane CENTRAL, CINAHL, ERIC, Web of Science, and IEEE. Gray literature will be searched in DBLP, the US Environmental Protection Agency, Google Scholar, Google search, and a hand search of recent abstracts from relevant conferences. Articles published in English, Spanish, and French from 2010 to the present will be included. Study screening and selection will be performed independently by 2 reviewers. Data extraction will be performed by a trained research team member following pilot testing.

Background

Stratification of patients with post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) would allow precision clinical management strategies. However, long COVID is incompletely understood and characterised by a wide range of manifestations that are difficult to analyse computationally. Additionally, the generalisability of machine learning classification of COVID-19 clinical outcomes has rarely been tested.

Methods

We present a method for computationally modelling PASC phenotype data based on electronic healthcare records (EHRs) and for assessing pairwise phenotypic similarity between patients using semantic similarity. Our approach defines a nonlinear similarity function that maps from a feature space of phenotypic abnormalities to a matrix of pairwise patient similarity that can be clustered using unsupervised machine learning.

Findings

We found six clusters of PASC patients, each with distinct profiles of phenotypic abnormalities, including clusters with distinct pulmonary, neuropsychiatric, and cardiovascular abnormalities, and a cluster associated with broad, severe manifestations and increased mortality. There was significant association of cluster membership with a range of pre-existing conditions and measures of severity during acute COVID-19. We assigned new patients from other healthcare centres to clusters by maximum semantic similarity to the original patients, and showed that the clusters were generalisable across different hospital systems. The increased mortality rate originally identified in one cluster was consistently observed in patients assigned to that cluster in other hospital systems.

Interpretation

Semantic phenotypic clustering provides a foundation for assigning patients to stratified subgroups for natural history or therapy studies on PASC.

Funding

NIH (TR002306/OT2HL161847-01/OD011883/HG010860), U.S.D.O.E. (DE-AC02-05CH11231), Donald A. Roux Family Fund at Jackson Laboratory, Marsico Family at CU Anschutz.