 |
Page History
...
Technical Description: the discovery of analytical steps utilizes inference over semantic annotations of input and output parameters. The researcher selects the metadata types that will be input to the pipeline and those that will be output from the pipeline. The inference engine performs discovery steps, chaining inputs to outputs in an expanding set until all options are exhausted or the resulting type matches. Furthermore, when specific analytical steps are queries for, full-text and concept-based metadata searches are performed in conjunction with output/input matching to provide the bet possible results. Workflows are saved as a set of steps or as a set of constrains upon which workflows are dynamically generated to meet scientific goals.
Support patient to trial matching through the use of computable eligibility criteria
Domain Description: a metadata specialist works with the principle investigator of a trial to define the eligibility criteria for a study in enough detail so that eligibility can be computed from patient data. The metadata specialist defines each eligibility question as a common data element (CDE) with a description, an mathematical operator, and a data operand (what the data gets compared to). For example, the principle investigator tells the metadata specialist that all patients must be at least 21 years old. The metadata specialist defines a CDE annotated with the concept "age", the operator "greater-than or equal", and the operand "21". These steps are performed for each of the 32 eligibility criteria. The principle investigator now works with a clinical informaticist to perform a search using these computable eligibility criteria on patient data at the cancer center to see if anyone is eligible. Furthermore, prospective patients themselves can type their data into the trial matching system to compute elgibility for all known trials to determine if there are any trials for their cancer.
Technical Description: the metadata specialist defines CDEs with operator and operand annotations. These are stored in the local metadata repository, which is used by the trial matching software. When computing eligibility, data for semantically equivalent data element are computed against the eligbility metadata to determine eligibility. "Fuzzy" eligibility can be computed when data is missing or does not match.
- Support the addition of data elements to an existing information model and automatically capture and publish the information about the extensions.
- When defining new datasets for caIntegrator's data-warehouse for biomedical data collection and analysis, automatically record these new datatypes in a well-defined and federated manner so that data can be shared.
Wiki Markup \[may replace or merge with 5\]Discover and orchestrate services to achieve LS research goals; e.g. start with a hypothesis, identify relevant services that provides the necessary analysis and data, create the worklow/pipeline, report findings. Workflow related requirements:
...
