For any health profession to succeed in value-based care, there is a critical need to analyze real-time health care data and outcomes among different populations. Where health care once may have lacked real-world data to measure the effectiveness of an intervention, for example, now we simply have too much data to identify a signal in the noise — the pattern in a vast sea of data that can help improve patient outcomes.

Traditional data analytics tools, such as the dashboards in your electronic health records program, can visualize basic trends in the data collected on your patients, benchmark outcomes, and track provider performance based on specific data points. But what they can't do is offer a wholistic view of a patient's health and identify that individual's health risk based on a multitude of factors that interact and change over time.

Enter artificial intelligence, or AI. By analyzing large data sets from electronic health records, claims databases from private payers and the Centers for Medicare and Medicaid Services, randomized controlled trials, wearable devices, and even clinical data registries, health services researchers are just beginning to scratch the surface of AI's promise to advance both practice and research.