Learning to Infer Entities, Properties and their Relations from Clinical Conversations

@article{Du2019LearningTI,
  title={Learning to Infer Entities, Properties and their Relations from Clinical Conversations},
  author={Nan Du and Mingqiu Wang and Linh Tran and Gang Li and Izhak Shafran},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.11536}
}
Recently we proposed the Span Attribute Tagging (SAT) Model to infer clinical entities (e.g., symptoms) and their properties (e.g., duration). It tackles the challenge of large label space and limited training data using a hierarchical two-stage approach that identifies the span of interest in a tagging step and assigns labels to the span in a classification step. We extend the SAT model to jointly infer not only entities and their properties but also relations between them. Most relation… 

Figures and Tables from this paper

Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
TLDR
A Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues and addresses the realworld challenges that the disease- symptom correlations of each disease may vary or evolve along with more diagnostic cases.
Weakly Supervised Medication Regimen Extraction from Medical Conversations
TLDR
This paper describes a unique dataset of annotated doctor-patient conversations and presents a weakly supervised model architecture that can perform span extraction using noisy classification data, and utilizes an attention bottleneck inside a classification model to perform the extraction.
Extracting Appointment Spans from Medical Conversations
TLDR
A novel task of extracting appointment spans from medical conversations is introduced and it is proposed to leverage weak supervision approaches, namely incomplete supervision, inaccurate supervision, and a hybrid supervision approach and evaluate both generic and domain-specific, ELMo, and BERT embeddings using sequence tagging models.
The Medical Scribe: Corpus Development and Model Performance Analyses
TLDR
An annotation scheme to extract relevant clinical concepts from a corpus of clinical encounters was developed and used to train a state-of-the-art tagging model, which is more useful than the F-scores reflect.
Generating Medical Reports from Patient-Doctor Conversations Using Sequence-to-Sequence Models
TLDR
Significantly large wins over a strong oracle baseline indicate that sequence-to-sequence modeling is a promising approach for automatic generation of medical reports, in the presence of data at scale.
Natural Language Processing for Automated Annotation of Medication Mentions in Primary Care Visit Conversations
Objectives: The objective of this study is to build and evaluate a natural language processing approach to identify medication mentions in primary care visit conversations between patients and
Natural language processing for automated annotation of medication mentions in primary care visit conversations
Abstract Objectives The objective of this study is to build and evaluate a natural language processing approach to identify medication mentions in primary care visit conversations between patients
Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer
TLDR
A Multi-granularity Transformer (MGT) model is proposed to enhance the dialogue context understanding from multi-granular features, and incorporates word-level information by adapting a Lattice-based encoder with the proposed relative position encoding method.
Relation Classification for Bleeding Events From Electronic Health Records Using Deep Learning Systems: An Empirical Study
TLDR
This comprehensive study explored and compared different DL systems to classify relations between bleeding events and other medical concepts and found that BERT-based models outperformed other DL models for identifying the relations of bleeding-related entities.
MKA: A Scalable Medical Knowledge-Assisted Mechanism for Generative Models on Medical Conversation Tasks
TLDR
A scalable medical knowledge-assisted mechanism aimed at assisting general neural generative models to achieve better performance on the medical conversation task and achieves state-of-the-art performance.
...
1
2
...

References

SHOWING 1-10 OF 58 REFERENCES
Extracting Symptoms and their Status from Clinical Conversations
TLDR
Novel models tailored for a new application, that of extracting the symptoms mentioned in clinical conversations along with their status, are described, using a new hierarchical span-attribute tagging (SA-T) model and a variant of sequence-to-sequence model which decodes the symptoms and their status from a few speaker turns within a sliding window over the conversation.
Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction
TLDR
A model which simultaneously predicts relationships between all mention pairs in a document and a new dataset an order of magnitude larger than existing human-annotated biological information extraction datasets and more accurate than distantly supervised alternatives is proposed.
Neural Relation Extraction Within and Across Sentence Boundaries
TLDR
iDepNN models the shortest and augmented dependency paths via recurrent and recursive neural networks to extract relationships within (intra-) and across (inter-) sentence boundaries and is more robust to false positives in relationships spanning sentences.
Investigating LSTMs for Joint Extraction of Opinion Entities and Relations
TLDR
It is found that standard LSTMs are not competitive with a state-of-the-art CRF+ILP joint inference approach to opinion entities extraction, performing below even the standalone sequencetagging CRF.
2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text
TLDR
The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for Clinical Records presented three tasks, which showed that machine learning approaches could be augmented with rule-based systems to determine concepts, assertions, and relations.
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
TLDR
A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
TLDR
An extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel is proposed, and a novel pruning strategy is applied to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold.
Annotation of a Large Clinical Entity Corpus
TLDR
The annotation guidelines, annotation process and the approaches in creating a CER (clinical entity recognition) corpus of 5,160 clinical documents from forty different clinical specialities are described in detail.
Neural Knowledge Acquisition via Mutual Attention Between Knowledge Graph and Text
TLDR
A general joint representation learning framework for knowledge acquisition on two tasks, knowledge graph completion and relation extraction from text, where models trained under this joint framework are significantly improved in comparison with other baselines.
A Hierarchical Framework for Relation Extraction with Reinforcement Learning
TLDR
This paper presents a novel paradigm to deal with relation extraction by regarding the related entities as the arguments of a relation and applies a hierarchical reinforcement learning (HRL) framework in this paradigm to enhance the interaction between entity mentions and relation types.
...
1
2
3
4
5
...