Perkinelmer Informatics, Inc.

Chad Millen

Abhinav Tiwari

Samuel Campbell

Stephen Menyhart

Abdul Al-Haimi

Harold Miller-Koren

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.

Methods and systems for automating clinical data mapping and transformation

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.

Growing community of inventors

Guelph, Canada

Chad Millen