A platform for data discovery to enhance the reuse of clinical neuroscience/neuroimaging data.
Replication, mega analysis, and meta-analysis are critical to the advancement of neuroimaging research. However, these are costly and time-consuming processes, and the subjects and data are usually not similar across studies, making actual replication or meta- analysis challenging. The question is how to harness already-collected data for replication purposes efficiently and rigorously. Progress in this goal depends not only on advanced experimental and computational techniques, but on the timely availability and discoverability of the most useful datasets. Much of the present efforts on reproducibility science assumes that appropriate datasets are available. While many different neuroimaging databases exist, they have different languages, formats, and usually do not communicate with each other. Moreover, neuroimaging data are collected in hundreds of laboratories each year, forming the “long tail of science” data. Much of this data is described in journal publications but remains underutilized. A critical gap therefore exists in getting enough data of the right kind to the scientist.
NeuroBridge is a platform for data discovery to enhance the reuse of clinical neuroscience/neuroimaging data. We develop the NeuroBridge ontology, and combine machine learning with ontology-based search of both neuroimaging repositories (e.g. XNAT databases) and open-access full text journals (such as PubMed Central). The ontology leverages existing and novel ontological terms to include study types, neuroimaging description, and terms for specific clinical domains such as psychosis and addiction. We leverage technologies such as data mediation, natural language processing, text mining, machine learning, ontology look-up service (OLS), and similarity searches.