At the 2013 Health Information Management Systems Society (HIMSS) meeting in New Orleans on March 3 I’ll provide guidance to the Physician IT Seminar on how to convert Meaningful Use advances in electronic health records and health information exchange into real learning opportunities to improve care and health.  The Institute of Medicine’s vision for a Learning Health System is “by 2020, 90% of clinical decisions will be supported by accurate, timely, and up-to-date clinical information and will reflect the best available evidence.”  How do the Meaningful Use rules carry us closer to this goal?

I’ve diagrammed critical elements for a learning health system, below.  At its base, and most critically, the electronic health record (EHR) captures information.  This may be entered by clinicians, or received from either patients or other health care providers.  This use of the EHR to “learn about the patient” is fundamental to all other improvements in care.

Various objectives in Stage 1 and 2 Meaningful Use require data capture.  They also require that EHRs be able to exchange information with other clinicians and to some extent with patients.  Meaningful Use objectives also require public health reporting, quality reporting, and decision support, each setting the stage for still more sophisticated learning.

Today, naturally, many providers are obsessed with the implementation of the Meaningful Use objectives and the receipt of incentive payments.  But it is never too soon to consider how these EHR objectives can be pressed into the service of “accurate, timely, and up-to-date clinical information and… the best available evidence.” It is already happening.   For example, in late 2012 a mysterious surge in fungal meningitis cases was detected in Tennessee, and was rapidly traced to certain lots of injection steroids produced by the New England Compounding Center.  Little was known about how to treat the predominant fungus,  Exserohilum rostratum.  Investigators used electronic health record reviews to rapidly identify exposed patients, and to track the success of treatment.   A rapid decline in case mortality among infected persons resulted within just two weeks.  That is truly a learning health system in action.*

Information alone does not bring about learning.  Learning requires a “central nervous system” to process incoming information in light of other knowledge.   Public health agencies, like local and state health departments, the Centers for Disease Control and Prevention (CDC), and the Food and Drug Administration (FDA) are examples of such “central nervous systems.”  But a good brain is useless without being attached to sensory and motor organs.   The Exserohilum rostratum outbreak helps show the Meaningful-Use-certified EHR is beginning to serve a valuable sensory function.   Equipped with decision support tools, it is destined to be a powerful motor organ as well.

*Thanks to the American Medical Informatics Association Public Health Informatics Workgroup for a great webcast on informatics use and needs associated with this outbreak.