Abstract
We are facing a major challenge in bridging the gap between identifying subtypes of asthma to understand causal mechanisms and translating this knowledge into personalized prevention and management strategies. In recent years, “big data” has been sold as a panacea for generating hypotheses and driving new frontiers of health care; the idea that the data must and will speak for themselves is fast becoming a new dogma. One of the dangers of ready accessibility of health care data and computational tools for data analysis is that the process of data mining can become uncoupled from the scientific process of clinical interpretation, understanding the provenance of the data, and external validation. Although advances in computational methods can be valuable for using unexpected structure in data to generate hypotheses, there remains a need for testing hypotheses and interpreting results with scientific rigor. We argue for combining data- and hypothesis-driven methods in a careful synergy, and the importance of carefully characterized birth and patient cohorts with genetic, phenotypic, biological, and molecular data in this process cannot be overemphasized. The main challenge on the road ahead is to harness bigger health care data in ways that produce meaningful clinical interpretation and to translate this into better diagnoses and properly personalized prevention and treatment plans. There is a pressing need for cross-disciplinary research with an integrative approach to data science, whereby basic scientists, clinicians, data analysts, and epidemiologists work together to understand the heterogeneity of asthma.
Highlights
We are facing a major challenge in bridging the gap between identifying subtypes of asthma to understand causal mechanisms and translating this knowledge into personalized prevention and management strategies
Data science must take the path of least inferential resistance, including the use of better ways to incorporate prior knowledge about likely causal mechanisms
We are facing a major challenge to bridge the gap between identifying subtypes of asthma in clinical and general populations to understand causal mechanisms of the discovered subtypes and translating this knowledge into better prevention and management strategies.[78,85]
Summary
Danielle Belgrave, PhD,a John Henderson, MD,b Angela Simpson, MD, PhD,c Iain Buchan, MD, PhD,d. Machine learning is a data-driven approach to identify structure within data to make predictions and identify patterns It is used commonly by computer scientists for problem solving in a variety of fields and is used increasingly to disaggregate complex disease phenotypes in respiratory medicine and allergy.[1,3,5,10,11,12] It must be noted that machine learning as a discipline is fairly new, the mathematic and statistical foundations have been in existence since the beginning of the 20th century.[50,51,52,53] Machine learning as a new discipline is a result of the exponential growth in computational power, which has enabled implementation of the mathematic groundwork that was initiated decades earlier.[54,55]. Machine learning applied to medicine attempts to predict disease states and to get the best estimate of uncertainty analogous to clinical diagnosis Both approaches combined with epidemiology, which carefully tests hypotheses to infer causality, need to be considered along with medical and biological expertise in a holistic understanding of disease
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
