Abstract: Aspects discussed herein relate to employing deep learning to automate mapping and transformation of a source data set to a target data schema. A system may utilize deep learning algorithms to determine a mapping from the source schema to the target schema through identifying the source schema and creating a correspondence between source fields and target fields, and a corresponding data transformation. Artificial neural networks, configured as schema-level and instance-level classifiers, may generate a set of predictions based on the fields of the source data set and fields of the target data schema. These predictions may be combined with other predictions based on other criteria (such as similarity between the fields) to generate a complete prediction of a schema mapping. Similarly, deep learning techniques may be employed to determine an appropriate data transformation to transform source data content to an appropriate format for corresponding fields of the target schema.

Abstract: Presented herein are systems and methods for merging and manipulating data from different sources of clinical trial data. Clinical trial data is collected using multiple different ‘forms’ and can be from either a single clinical trial or from multiple clinical trials. In certain embodiments, the systems and methods described herein are provided in the form of an intuitive graphical user interface (GUI) that enables a user to merge and manipulate data from two or more source tables of clinical trial data associated with one or more clinical studies to produce a custom merged table, without having to rely upon complex computer code.

Abstract: Aspects discussed herein relate to employing deep learning to automate mapping and transformation of a source data set to a target data schema. A system may utilize deep learning algorithms to determine a mapping from the source schema to the target schema through identifying the source schema and creating a correspondence between source fields and target fields, and a corresponding data transformation. Artificial neural networks, configured as schema-level and instance-level classifiers, may generate a set of predictions based on the fields of the source data set and fields of the target data schema. These predictions may be combined with other predictions based on other criteria (such as similarity between the fields) to generate a complete prediction of a schema mapping. Similarly, deep learning techniques may be employed to determine an appropriate data transformation to transform source data content to an appropriate format for corresponding fields of the target schema.

Abstract: Presented herein are systems and methods for merging and manipulating data from different sources of clinical trial data. Clinical trial data is collected using multiple different ‘forms’ and can be from either a single clinical trial or from multiple clinical trials. In certain embodiments, the systems and methods described herein are provided in the form of an intuitive graphical user interface (GUI) that enables a user to merge and manipulate data from two or more source tables of clinical trial data associated with one or more clinical studies to produce a custom merged table, without having to rely upon complex computer code.

Abstract: Presented herein are systems, methods, and architectures related to a scalable and platform-agnostic framework that leverages multiple pluggable connectors to retrieve clinical trial data from different data sources (e.g. corresponding to different systems used to collect and manage data collected over the course of a clinical trial). The clinical connector technology described herein transforms the retrieved data to one or more standardized representations using one or more pre-defined data models. By providing clinical trial data to the client applications of stakeholders in one or more standardized formats (e.g. represented according to a standardize pre-defined data model), irrespective of the source of the clinical trial data, the systems, methods, and architectures described herein obviate the need for stakeholders to modify their workflow depending on the particular source.

Abstract: Presented herein are systems and methods to automatically and periodically retrieve clinical trial data from an EDC source, process the data to transform it from its initial representation as retrieved from the EDC source into table-based format, and store the resultant transformed data in an intermediate data storage layer for access by stakeholders. Accordingly, instead of accessing source data, such as EDC ODM-XML data directly from an EDC source, a stakeholder may retrieve clinical trial data from the transformed data stored in the data storage layer. The systems and methods provide transformed data that better serves the needs of stakeholders during a clinical trial.