no code implementations • EMNLP (SpLU) 2020 • Surabhi Datta, Kirk Roberts
Radiology reports contain important clinical information about patients which are often tied through spatial expressions.
no code implementations • LREC 2022 • Surabhi Datta, Hio Cheng Lam, Atieh Pajouhi, Sunitha Mogalla, Kirk Roberts
This is one of the first attempts focusing on CDCR in the clinical domain and holds potential in benefiting physicians and clinical research through long-term tracking of radiology findings.
coreference-resolution Cross Document Coreference Resolution
no code implementations • 19 May 2023 • Surabhi Datta, Tasneem Kaochar, Hio Cheng Lam, Nelly Nwosu, Luca Giancardo, Alice Z. Chuang, Robert M. Feldman, Kirk Roberts
This is the first work to represent and extract a wide variety of clinical information in ophthalmology.
no code implementations • 10 Oct 2020 • Surabhi Datta, Shekhar Khanpara, Roy F. Riascos, Kirk Roberts
Classifying fine-grained ischemic stroke phenotypes relies on identifying important clinical information.
no code implementations • 10 Sep 2020 • Surabhi Datta, Jordan Godfrey-Stovall, Kirk Roberts
Further, no study to date has attempted to leverage RadLex for standardization.
no code implementations • LREC 2020 • Surabhi Datta, Morgan Ulinski, Jordan Godfrey-Stovall, Shekhar Khanpara, Roy F. Riascos-Castaneda, Kirk Roberts
The framework is adopted from the existing SpatialNet representation in the general domain with the aim to generate more accurate representations of spatial language used by radiologists.
no code implementations • 13 Aug 2019 • Surabhi Datta, Yuqi Si, Laritza Rodriguez, Sonya E Shooshan, Dina Demner-Fushman, Kirk Roberts
We define a representation framework for extracting spatial information from radiology reports (Rad-SpRL).
no code implementations • 2 Apr 2019 • Surabhi Datta, Elmer V Bernstam, Kirk Roberts
Conclusion: The list of common frames described in this paper identifies important cancer-related information extracted by existing NLP techniques and serves as a useful resource for future researchers requiring cancer information extracted from EHR notes.