Predicting breast cancer recurrence using Natural Language Processing on imaging reports
Institution: Barts Cancer Institute, Queen Mary University of London
Corresponding Researcher: Maryam Abdollahyan
Publication Link(s): NA
Data Link(s): NA
Keyword(s): imaging reports, Natural Language Processing, recurrence
Summary
Despite recent advances in early detection and treatment of breast cancer (BC), a large percentage of patients still go on to experience recurrence. This figure is expected to rise in the upcoming years due to disruptions in screening programmes related to the COVID‐19 pandemic. We explore the use of Natural Language Processing (NLP) techniques to extract insights from electronic health records (EHRs), specifically imaging text reports, that combined with data from other sources (e.g., biorepositories and sequencing initiatives) could help stratify patients into groups such as those likely to be at risk of disease progression, respond to treatment or experience side effects.
