In a drive for standardization, the proposed U.S. Core Data for Interoperability1, mandated by the 2015 21st Century Cure Act2, calls for the identification and refinement of a basic set of clinical data to be required for all electronic health records. The American Medical Informatics Association, however, recommends that healthcare researchers and providers concentrate on sharing data as quickly as possible, deferring the creation of standards until sometime in the future.3 “This is a false choice and a distraction,” said James D’Arezzo, CEO of Condusiv Technologies.
D’Arezzo, whose company is the world leader in I/O reduction and SQL database performance, adds, “What the healthcare industry really needs to focus on is enabling its heavily overburdened IT infrastructure to do the job it’s being asked to do.”
The industry’s preoccupation with interoperability and standardization, notes D’Arezzo, is perfectly understandable. Turf wars over proprietary interfaces and protocols are having a major impact on healthcare IT budgets.4 Non-compatible electronic health records contribute significantly to the fact that computerized record keeping consumes more than 50 percent of the average physician’s workday, which now stretches to more than 11 hours.6 Healthcare organizations struggling to process this tsunami of data are frustrated by the number and variety of analytics tools they are forced to use.6
Supporting all this activity, however—unnoticed and, says D’Arezzo, dangerously neglected—is the basic computational machinery itself. Data analytics requires a computer system to access multiple and often far-flung databases, pulling information together through millions of individual input-output (I/O) operations. The system’s analytic capability is dependent on the efficiency of those operations, which in turn is dependent on the efficiency of the computer’s operating environment.
According to experts, the most widely used operating system, Microsoft Windows, is in many ways the least efficient. In any storage environment, from multi-cloud to a PC hard drive, Windows penalizes optimum performance because of server inefficiencies in the handoff of data to storage. This is a problem that, untreated, worsens with time. The average Windows-based system pays a 30 percent to 40 percent penalty in overall throughput capability because of I/O degradation.7