Information Extraction from Data Visualizations

Regulatory agencies publish several documents that outline the approval process of drugs. These contain valuable information on a drug’s safety, efficacy, etc. along with the feedback of reviewers from the agencies. Current technologies apply machine learning techniques to extract and categorize the unstructured text found in these documents. However, it does not accurately capture information from data visualizations such as tables, graphs, charts, etc. The data present in these elements are important for drug development teams to decide what clinical trial designs to use, which safety and efficacy data to gather for approval, etc. If solved, this can lead to quicker and more accurate decision-making by regulatory professionals, and in turn, result in faster drug approval and lowered drug development cost.

Faculty Supervisor:

Kieran Campbell

Student:

Partner:

Biotech Square Inc.

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Toronto

Program: