Corpus ID: 17630172

Clinical Question Answering using Key-Value Memory Networks and Knowledge Graph

@inproceedings{Hasan2016ClinicalQA,
  title={Clinical Question Answering using Key-Value Memory Networks and Knowledge Graph},
  author={Sadid A. Hasan and Siyuan Zhao and Vivek Datla and Joey Liu and Kathy Lee and Ashequl Qadir and Aaditya Prakash and Oladimeji Farri},
  booktitle={TREC},
  year={2016}
}
We describe our clinical question answering system implemented for the Text Retrieval Conference (TREC 2016) Clinical Decision Support (CDS) track. We submitted five runs using a combination of knowledge-driven (based on a curated knowledge graph) and deep learning-based (using key-value memory networks) approaches to retrieve relevant biomedical articles for answering generic clinical questions (diagnoses, treatment, and test) for each clinical scenario provided in three forms: notes… Expand
Condensed Memory Networks for Clinical Diagnostic Inferencing
Diagnosis of a clinical condition is a challenging task, which often requires significant medical investigation. Previous work related to diagnostic inferencing problems mostly consider multivariateExpand
Knowledge Abstraction Matching for Medical Question Answering
TLDR
A novel Knowledge Abstraction Matching method for the medical QA problem that consists of frequent segment $N$-gram mining, medical knowledge abstraction, medical segment matching and answer re-retrieval and can generate more quality answers for MelodyQA with a significant improvement of question coverage under acceptable accuracy. Expand
Automated clinical diagnosis: The role of content in various sections of a clinical document
TLDR
Evaluation on MIMIC-III dataset demonstrates that the content of “history of present illness” and “past medical history” sections can play a greater role for clinical diagnosis inference than other sections and all sections combined. Expand
Retrieving documents based on gene name variations: MedIER at TREC 2017 Precision Medicine Track
TLDR
This work focused on the genetic variations mentioned in the query and explored ways to modify the search query and the retrieval ranking using this information, and explored filtering retrieved results based on demographic information matching for clinical trials. Expand
Improving Clinical Diagnosis Inference through Integration of Structured and Unstructured Knowledge
TLDR
A novel approach to the task of automatically inferring the most probable diagnosis from a given clinical narrative by building a concept graph from both structured and unstructured knowledge sources and ranking the diagnosis concepts using the enhanced word embedding vectors learned from integrated sources. Expand
Clinical Natural Language Processing with Deep Learning
TLDR
This tutorial chapter will present an overview of how deep learning techniques can be applied to solve NLP tasks in general, followed by a literature survey of existing deep learning algorithms applied to clinical NLP problems. Expand
LANGUAGE MODELS FOR UNSUPERVISED ACQUISITION OF MEDICAL KNOWLEDGE FROM NATURAL LANGUAGE TEXTS : APPLICATION FOR DIAGNOSIS PREDICTION
  • 2019
Following recent success of neural language models in various downstream language understanding tasks, including common sense reasoning, we investigate possible utility of such models in domainExpand
Dual Control Memory Augmented Neural Networks for Treatment Recommendations
TLDR
The task is formulated as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications, built on the premise that an effective treatment plan may have long-term dependencies from previous medical history. Expand
Data Science for Healthcare
  • S. Consoli
  • Computer Science
  • Springer International Publishing
  • 2019

References

SHOWING 1-10 OF 24 REFERENCES
Using Neural Embeddings for Diagnostic Inferencing in Clinical Question Answering
TLDR
It is concluded that diagnostic inferencing may be the most important determinant of the accuracy of the clinical question answering systems, and that the use of neural embeddings and advanced deep learning techniques could help improve the quality of such systems in order to effectively support decision-making in patient care. Expand
A Hybrid Approach to Clinical Question Answering
TLDR
Evaluation results showed that the clinical question answering system developed and submitted for the Text Retrieval Conference (TREC 2014) Clinical Decision Support (CDS) track achieved the best scores in two of eight dual-judged topics: #5 and 27, and performed relatively better compared to the median scores for topics. Expand
Condensed Memory Networks for Clinical Diagnostic Inferencing
Diagnosis of a clinical condition is a challenging task, which often requires significant medical investigation. Previous work related to diagnostic inferencing problems mostly consider multivariateExpand
Key-Value Memory Networks for Directly Reading Documents
TLDR
This work introduces a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation. Expand
Memory Networks
TLDR
This work describes a new class of learning models called memory networks, which reason with inference components combined with a long-term memory component; they learn how to use these jointly. Expand
End-To-End Memory Networks
TLDR
A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. Expand
The effect of sampling strategy on inferred measures
TLDR
Examination of the effect on collection quality of different sampling strategies within the inferred measures framework finds strategies that include a top-10 pool create better collections than those that do not, as well as allow Precision(10) scores to be directly computed. Expand
Biomedical ontologies in action: role in knowledge management, data integration and decision support.
  • O. Bodenreider
  • Computer Science, Medicine
  • Yearbook of medical informatics
  • 2008
TLDR
Ontologies play an important role in biomedical research through a variety of applications, and are used primarily as a source of vocabulary for standardization and integration purposes, but many applications also use them as a sources of computable knowledge. Expand
Adapting Clinical Ontologies in Real-World Environments
TLDR
The desideratum of semantic interoperability has been intensively discussed in medical informatics circles in recent years and the use of the term 'ontology' has been steadily increasing more recently. Expand
A simple and efficient sampling method for estimating AP and NDCG
We consider the problem of large scale retrieval evaluation. Recently two methods based on random sampling were proposed as a solution to the extensive effort required to judge tens of thousands ofExpand
...
1
2
3
...