Azad Dehghan

Azad Dehghan

This report describes a minimalistic set of methods engineered to anchor clinical events onto a temporal space. Specifically, we describe methods to extract clinical events (e.g., Problems, Treatments and Tests), temporal expressions (i.e., time, date, duration, and frequency), and temporal links (e.g., Before, After, Overlap) between events and temporal entities. These methods are developed and validated using high quality datasets.

Azad Dehghan

The problem of named entity recognition in the medical/clinical domain has gained increasing attention do to its vital role in a wide range of clinical decision support applications. The identification of complete and correct term span is vital for further knowledge synthesis (e.g., coding/mapping concepts thesauruses and classification standards). This paper investigates boundary adjustment by sequence labeling representations models and post-processing techniques in the problem of clinical named entity recognition (recognition of clinical events). Using current state-of-the-art sequence labeling algorithm (conditional random fields), we show experimentally that sequence labeling representation and post-processing can be significantly helpful in strict boundary identification of clinical events.