The problem with most existing healthcare services is that patient records are scattered between different archives, both computerized and paper-based, and spread out at various physical locations.
Not only is the information widely dispersed, but it is:
- Expressed in different vocabularies and terminology
- Expressed in different formats and languages
- Retrieved using different access methods
- Retrieved through different delivery vehicles
Mining the medical information is critical for research in many new domains including genomic-based diagnosis, drug discovery and personalized drugs, and clinical trials. This becomes increasingly difficult as the records become more dispersed.
In addition, the low-granularity security model approach endorses locking sensitive information, such as psychiatric evaluation or various serological findings, from certain care providers. When information is shared based on a 'need-to-know' basis, security issues become increasingly complex.
IMR is a middleware that can integrate and correlate medical records from diverse sources. Using innovative technology, the data is first annotated to create XML documents that are human readable, as well as machine processable. Next, the XML documents are fully indexed (structure and free text) using an indexing system specialized for XML documents. The middleware API then provides a unified and secured access to electronic health records (EHRs) that are compiled from those documents. Currently, the format of the XML documents is based on the HL7 Clinical Document Architecture (CDA) standard.