The advent of large expansive datasets has generated substantial interest as a means of developing and implementing unique algorithms that facilitate more precise and personalized interventions. This methodology has permeated the realm of sleep medicine and in the care of patients with sleep disorders. One of the large repositories of information consists of adherence and physiological datasets across long periods of time as derived from patients undergoing positive airway pressure (PAP) treatment for sleep‐disordered breathing. Here, we evaluate the extant and yet scarce findings derived from big data in both adults and children receiving PAP for obstructive sleep apnea and suggest future directions towards more expansive utilization of such valuable approaches to improve therapeutic decisions and outcomes.