• <Plus d'infos sur intel.fr

Electronic Medical Records System Benchmark: White Paper

Veuillez nous excuser, ce PDF peut uniquement être téléchargé

Executive Summary
Database performance is a critical component to massive transactional processing systems, such as Electronic Medical Records (EMR) management applications. Traditionally, costly IT solutions have been required to support scalability of today’s large relational database deployments using object-oriented programming technologies.

This benchmark, hosted by HP and supported by InterSystems, Intel, and VMware, reveals the high scalability and performance of InterSystems Caché running on quad-core Intel® Xeon® processors X5570, in both a native configuration and a virtualized configuration. The combination of Caché and the Intel Xeon processor blade-based server achieved performance and scalability results not seen in these configurations before.

Database Performance Challenges in EMR
Database performance for EMR management is a growing concern for hospital IT personnel and EMR application developers. As large hospitals and hospital groups migrate their patient information to EMR, the database must adequately scale and support a massive number of database accesses to allow administration personnel to add, update, and retrieve patient information thousands of times per day, in some installations.

Historically, to achieve necessary performance, deployments relied on in-memory database implementations, which require massive amounts of costly memory. In addition to high deployment costs, the inherent reliability risk with these types of solutions for businesscritical applications is their inability to persist data. Today’s implementations typically use persistent, relational databases.

As persistent, relational databases supporting modern objectoriented applications scale to handle larger volumes of data, their performance often degrades. This is usually because of the inherent mismatch between object-oriented development technologies and the two-dimensional, rows-and-columns data structures used on disk. The processing overhead required to “map” between the complex data types used by today’s sophisticated software applications and a relational database tends to restrict throughput.

Read the full Electronic Medical Records System Benchmark White Paper.