Using Local Grammar for Entity Extraction from Clinical Reports

@article{Ghoulam2015UsingLG,
  title={Using Local Grammar for Entity Extraction from Clinical Reports},
  author={Aicha Ghoulam and Fatiha Barigou and Ghalem Belalem and F. Meziane},
  journal={Int. J. Interact. Multim. Artif. Intell.},
  year={2015},
  volume={3},
  pages={16-24}
}
Information Extraction (IE) is a natural language processing (NLP) task whose aim is to analyze texts written in natural language to extract structured and useful information such as named entities and semantic relations linking these entities. Information extraction is an important task for many applications such as bio-medical literature mining, customer care, community websites, and personal information management. The increasing information available in patient clinical reports is difficult… 

Figures and Tables from this paper

Query Expansion Using Medical Information Extraction for Improving Information Retrieval in French Medical Domain
TLDR
A query expansion method is presented that uses medical entities and their semantic relations in the query context based on an external resource in OWL to evaluate the effectiveness of an information retrieval system to support doctors in accessing easily relevant information.
CLUSTERING OF MEDICAL DOCUMENTS USING SYMPTOM/MEDICATION NAMES
TLDR
The multi-view Non-negative matrix factorization (NMF) is used to cluster clinical documents and the experimental result shows that, as the number of clinical documents increases processing speed decreases to get the result.
Named Entity Recognition in Chinese Electronic Medical Records Based on CRF
TLDR
A medical dictionary is built and the effects of different types of features in Chinese clinical NER tasks based on Condition Random Fields (CRF) algorithm, the most popular algorithm for NER, are investigated, including bag-of-characters, part of speech, dictionary feature, and word clustering features.
Clustering of biomedical documents using ontology-based TF-IGM enriched semantic smoothing model for telemedicine applications
TLDR
The results show that the proposed approach of medical document clustering is highly accurate and thus improves the concepts of clinical practices and telemedicine.
A personal knowledge management metamodel based on semantic analysis and social information
TLDR
The result is the design of a functional architecture that permits integrating the Web 2.0 application and a semantic analysis algorithm from unstructured information by applying machine learning techniques.
Social movie recommender system based on deep autoencoder network using Twitter data
TLDR
A hybrid social recommender system utilizing a deep autoencoder network is introduced and the accuracy and effectiveness of the proposed approach have been improved compared to the other state-of-the-art methods.
Friend recommendation in social networks based on multi-source information fusion
TLDR
This work proposes a scalable FR framework in social networks, where multiple sources have been integrated based on improved D-S evidence theory, and designs a novel BPA evidence function by quantifying the evidence, where each evidence measures the relevance of forming friends among users.
An algorithm for influence maximization in competitive social networks with unwanted users
TLDR
This paper formally defines the problem of influence maximization with limited unwanted users (IML) under the independent cascade model, and proposes a propagation path based strategy to compute the activation probabilities between the node pairs based on the activation probability.
...
...

References

SHOWING 1-10 OF 69 REFERENCES
MedIX: A named entity extraction tool from patient clinical reports
TLDR
A rule-based approach is applied to clinical reports corpus of infectious diseases to extract semantic content in the form of named entities and properties to help the patient data anonymization and the structured database fill in dedicated for future medical applications.
Learning Patterns for Building Resources about Semantic Relations in the Medical Domain
TLDR
A method for extracting automatically semantic relations from texts in the medical domain using linguistic patterns, which refer to three levels of information about words: inflected form, lemma and part-of-speech.
Medication information extraction with linguistic pattern matching and semantic rules
TLDR
Based on the F-measure, the performance achieved was in line with the initial agreement between human annotators (82%), indicating that such a system may greatly facilitate the process of extracting relevant information from medical records by providing a solid basis for a manual review process.
A Hybrid Approach for the Extraction of Semantic Relations from MEDLINE Abstracts
TLDR
This paper focuses on the relations that may occur between diseases and treatments, and proposes an approach relying on two different techniques to extract the target relations: relation patterns based on human expertise and machine learning based on SVM classification.
BioinformaticsUA: Concept Recognition in Clinical Narratives Using a Modular and Highly Efficient Text Processing Framework
TLDR
The approach in this task, which was based on a fully modular architecture for text mining, followed a pure dictionary-based approach, after performing error analysis to refine the authors' dictionaries.
Using a Cellular Automaton to Extract Medical Information from Clinical Reports
TLDR
This research aims to develop a system for extracting information from unstructured text, and proposes the use of a Boolean inference engine, which is based on a cellular automaton, to do extraction.
A Supervised Named-Entity Extraction System for Medical Text
TLDR
A supervised CRF model that based on a rich set of features learns to predict disorder named entities, a named-entity recognition system specialized in the medical domain, and a system that can perform NER on medical text.
A natural language parsing system for encoding admitting diagnoses
TLDR
A natural language parser is developed that converts free-text admitting diagnoses into a coded form and has proven acceptably accurate in the experimental laboratory to warrant a test in the target clinical environment.
RelAgent: Entity Detection and Normalization for Diseases in Clinical Records: a Linguistically Driven Approach
TLDR
The performance of Cocoa/Peaberry, a linguistically motivated system, on extracting disease entities from clinical notes in the training and development sets for Task 7 was refined, and a module to map the extracted entities to the SNOMED subset of UMLS was developed.
...
...