Family history information extraction via deep joint learning

Abstract

BackgroundFamily history (FH) information, including family members, side of family of family members (i.e., maternal or paternal), living status of family members, observations (diseases) of family members, etc., is very important in the decision-making process of disorder diagnosis and treatment. However FH information cannot be used directly by computers as it is always embedded in unstructured text in electronic health records (EHRs). In order to extract FH information form clinical text, there is a need of natural language processing (NLP). In the BioCreative/OHNLP2018 challenge, there is a task regarding FH extraction (i.e., task1), including two subtasks: (1) entity identification, identifying family members and their observations (diseases) mentioned in clinical text; (2) family history extraction, extracting side of family of family members, living status of family members, and observations of family members. For this task, we propose a system based on deep joint learning methods to extract FH information. Our system achieves the highest F1- scores of 0.8901 on subtask1 and 0.6359 on subtask2, respectively.

Extracting Family History of Patients From Clinical Narratives: Exploring an End-to-End Solution With Deep Learning Models

“…We approached the 2 tasks as classification problems. Previous studies [ 35 , 42 ] approached the 2 tasks using rule-based methods; here, we applied deep learning–based classification methods as machine learning–based methods have shown a better generalizability.…”

“…The 2018 BioCreative/OHNLP Challenge [ 33 , 34 ] is the first shared task focusing on FH extraction. During that challenge, Shi et al [ 35 ] explored a joint deep learning approach and achieved the best performance among all participated teams. In 2019, the National NLP Clinical Challenge (n2c2) organized shared tasks to solicit advanced NLP methods for extracting FH information from clinical text.…”

Family History Information Extraction With Neural Attention and an Enhanced Relation-Side Scheme: Algorithm Development and Validation (Preprint)

“…We used the network architecture developed by Dai [10] as a baseline. The network architecture is very similar to the entity recognition part of the network developed by Shi et al [11], with the major difference being that the latter further extended the network with an additional BiLSTM to create a joint learning model. Both were top-ranked systems in the BioCreative/OHNLP challenge.…”

“…Several research projects have previously worked on the FHI extraction task. Shi et al [11] developed a neural network model based on BiLSTM networks for joint learning of FHIs and the relations among them. Zhan et al [21] fine-tuned the bidirectional encoder representations from transformers [22] by including an additional Biaffine classifier adapted from the dependency parsing to extract FHIs.…”

“…In addition to the challenge of optimizing both submodules separately, there are at least two other known limitations of applying postprocessing rules. One is the inability to determine cases like indirect relatives as pointed out by Dai [10] and Shi et al [11], and the other is the general ability to classify FHIs represented in different writing styles. Unfortunately, although the aforementioned relation-side scheme is expected to facilitate the development of a single end-to-end model to conquer the task of FHI extraction, the experiment results by Dai [10] revealed issues of insufficient and imbalanced training instances.…”