Two key “learning” applications of big health care data that hold the promise of improving patient care are the generation of new knowledge about the effectiveness of treatments and the prediction of outcomes. Both these functions exceed the bounds of most computer applications currently used in health care, which tend to offer physicians such tools as context-sensitive warning messages, reminders, suggestions for economical prescribing, and results of mandated quality-improvement activities.
Physicians currently struggle to apply new medical knowledge to their own patients, since most evidence regarding the effectiveness of medical innovations has been generated by studies involving patients who differ from their own and who were treated in highly controlled research environments. But many data that are routinely collected in a health care system can be used to evaluate medical products and interventions and directly influence patient care in the very systems that generated the data.Given that clinical trials are conducted in an environment that usually doesn't reflect the "real world," clinicians often use that as an excuse to deviate from guideline recommendations. It's actually not an excuse. When you have a patient who has certain comorbid conditions or other factors, you need to make a clinical judgement about how you will treat that individual, and that may require you to deviate from clinical practice guidelines.
Currently, it is very costly and cumbersome to conduct "real-world" research studies. But, as we collect more data about the "effectiveness of treatments and the prediction of outcomes," clinicians will be more empowered than ever before to make better clinical decisions. It won't be an era of "cookbook medicine" that's entirely driven by static algorithms and flowcharts. Instead, treatment decisions will be customized and tailored for each individual based on unique factors, genomic profiles, patient preferences, socioeconomic factors, and much more.