As a child develops from preconception to adolescence, genetic, cultural, nutritional, infectious, and environmental factors all influence his or her health. These factors shape the future of children, susceptibilities to adult diseases, and individual child health outcomes. As a result of evolution, phenotypic characteristics are selected during the development of the fetus, infancy, childhood, and adolescence to cope with predictable and unpredictable exposures/stresses.

Although child health has improved globally over the past 30 years, continued improvement requires access to data that fully represent the complexity of these interactions and to new analytic methods. Big Data and innovative data science methods provide an armamentarium to integrate multiple data dimensions for the description of best clinical, predictive, and preventive practices, for decreasing racial disparities in child health outcomes, for including patient and family input in medical assessments, and for describing individual disease risk, mechanisms, and therapies. 

Studies have suggested the feasibility of applying Big Data and data science to child health questions and its potential to predict and mitigate disease risk over decades of life. However, acknowledging this will demand funding prioritization from the NIH and other agencies, an unprecedented collaboration among institutions, investigators, and patients/families, consolidation of existing data networks, and child health-specific innovation.

Vesoulis ZA, Husain AN, Cole FS. Improving child health through Big Data and data science. Pediatr Res. 2022. https://doi.org/10.1038/s41390-022-02264-9