BioMIMS - SOA Platform for Research of Rare Hereditary Diseases

Introduction: BioMIMS is an award-winning* platform that realizes our vision for how information technologies can support the research of rare hereditary diseases. A disease is considered rare when it affects only a small percentage of the population, most rare diseases are genetic. Researching rare hereditary diseases imposes several significant challenges for dedicated informatics tools. Collaboration is a critical element in the research process, and partnerships among research centers are essential to ensure advances in understanding and treating these diseases. Because a single research center usually lacks sufficient data for conducting meaningful research, data must be shared among partners. Consequently, the first challenge of the underlying platform is to merge information gathered from dispersed hospitals, research centers, clinics, labs and other facilities. Additionally, various data types such as clinical, genomic, imaging data, and pedigrees, must be combined to create a comprehensive disease view. Obtaining and visualizing all the available data is the first step toward gaining insights through analytics. Research questions cannot always be known in advance and tend to change over time; therefore, an effective platform should be able to integrate various data mining and analytic algorithms. Platform Architecture: We designed BioMIMS based on Service Oriented Architecture (SOA) principles. The BioMIMS architecture is composed of a rich set of fine-grained services decoupled by a central bus. The bus orchestrates the existing services according to predefined workflows, following the Message Oriented Middleware (MOM) concept. Message queues provide temporary storage when the destination service is busy or not connected. All the messages running through the bus and handled by the different services are based on approved industry standards. Medical images are uploaded to and retrieved from the appropriate system service in DICOM v3.0 format, while clinical and family history data are uploaded and retrieved according to HL7 v2.x and HL7 v3 Family History standards. Patients may have different patient identifiers in different systems. To ensure the correct identification of patients and their data in a standard manner, BioMIMS supports IHE Patient Identifier Cross-Reference (PIX) and Patient Demographic Query (PDQ) transactions. To enable interoperability at the cross-hospital and regional levels, metadata are extracted from the stored information according to IHE Cross-enterprise Document Sharing (XDS/XDS-I) Profiles. A SOA approach, based on standard interfaces has numerous benefits, namely: a) a flexible architecture that allows easy integration of new services, creation of new workflows by reusing existing ones, and easy integration with existing applications, b) inherent scalability, c) speedy custom application development that reduces total IT costs. Platform Validation: BioMIMS was validated by researchers of the Rizzoli Orthopaedic Institute (IOR). IOR researchers uploaded and investigated data for two different orthopedic diseases -- Multiple Osteochondromas (MO) and Osteogenesis Imperfecta (OI) The researchers confirmed several presumed insights for the available data using BioMIMS. Moreover, a few interesting points arose during the validation process, helping to determine goals for future studies.