Eye-SpatialNet: Spatial Information Extraction from Ophthalmology Notes
This work addresses the need for detailed spatial data extraction in ophthalmology to support applications like disease progression and screening, but it is incremental as it extends an existing schema to a new domain.
The authors tackled the problem of extracting spatial information from ophthalmology notes by creating an annotated corpus and using a BERT-based question answering approach, achieving F1 scores of up to 89.31 for spatial triggers.
We introduce an annotated corpus of 600 ophthalmology notes labeled with detailed spatial and contextual information of ophthalmic entities. We extend our previously proposed frame semantics-based spatial representation schema, Rad-SpatialNet, to represent spatial language in ophthalmology text, resulting in the Eye-SpatialNet schema. The spatially-grounded entities are findings, procedures, and drugs. To accurately capture all spatial details, we add some domain-specific elements in Eye-SpatialNet. The annotated corpus contains 1715 spatial triggers, 7308 findings, 2424 anatomies, and 9914 descriptors. To automatically extract the spatial information, we employ a two-turn question answering approach based on the transformer language model BERT. The results are promising, with F1 scores of 89.31, 74.86, and 88.47 for spatial triggers, Figure, and Ground frame elements, respectively. This is the first work to represent and extract a wide variety of clinical information in ophthalmology. Extracting detailed information can benefit ophthalmology applications and research targeted toward disease progression and screening.