Comparison of Word Embeddings for Extraction from Medical Records

Dudchenko, Aleksei; Kopanitsa, Georgy

doi:10.3390/ijerph16224360

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They presented the performance evaluations of employing three sentence embedding models on DUC 2002 dataset for ATS and show that deep learning methods display exceptional output [22]. Dudchenko and Kopanitsa compared the performance of various artificial neural network models for extracting text from Russian medical text documents with the help of word embeddings [23]. They compared multi-layer perceptron (MLP), convolutional neural networks (CNN) and long short-term memory networks (LSTMs); MLP and CNN presented similar performance with the embedding models.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

D’Silva

Sharma

2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Automatic text summarization has gained immense popularity in research. Previously, several methods have been explored for obtaining effective text summarization outcomes. However, most of the work pertains to the most popular languages spoken in the world. Through this paper, we explore the area of extractive automatic text summarization using deep learning approach and apply it to Konkani language, which is a low-resource language as there are limited resources, such as data, tools, speakers and/or experts in Konkani. In the proposed technique, Facebook’s fastText <br /> pre-trained word embeddings are used to get a vector representation for sentences. Thereafter, deep multi-layer perceptron technique is employed, as a supervised binary classification task for auto-generating summaries using the feature vectors. Using pre-trained fastText word embeddings eliminated the requirement of a large training set and reduced training time. The system generated summaries were evaluated against the ‘gold-standard’ human generated summaries with recall-oriented understudy for gisting evaluation (ROUGE) toolkit. The results thus obtained showed that performance of the proposed system matched closely to the performance of the human annotators in generating summaries.</span>

show abstract

Section: Related Workmentioning

confidence: 99%

“…MLP network has a relatively simpler structure but yet obtains respectable results. The simpler structure has a direct impact on the time and space complexity of a system [23], [28]. The optimizer used in this experiment was Adam [32] and the loss function used was binary_crossentropy.…”

Section: Multi-layer Perceptron Networkmentioning

confidence: 99%

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

D’Silva

Sharma

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…can then be used as inputs to a classifier [20,21]. There is no publicly available text corpus related to pediatric abuse case analysis, therefore two embeddings were selected for this study: the publicly available GloVE embedding (WE-GLOVE, Global Vectors for word representation) utilizing 100 dimensional representations of words trained on the entirety of Wikipedia [22], and an in-house embedding based on the MIMIC-III database (WE-MIMIC, Medical Information Mart for Intensive Care) trained on the notes in the MIMIC-III database, a set of adult ICU records from Beth-Israel-Deaconess Medical Center [23].…”

Section: Plos Onementioning

confidence: 99%

A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records

et al. 2021

View full text Add to dashboard Cite

Child physical abuse is a leading cause of traumatic injury and death in children. In 2017, child abuse was responsible for 1688 fatalities in the United States, of 3.5 million children referred to Child Protection Services and 674,000 substantiated victims. While large referral hospitals maintain teams trained in Child Abuse Pediatrics, smaller community hospitals often do not have such dedicated resources to evaluate patients for potential abuse. Moreover, identification of abuse has a low margin of error, as false positive identifications lead to unwarranted separations, while false negatives allow dangerous situations to continue. This context makes the consistent detection of and response to abuse difficult, particularly given subtle signs in young, non-verbal patients. Here, we describe the development of artificial intelligence algorithms that use unstructured free-text in the electronic medical record—including notes from physicians, nurses, and social workers—to identify children who are suspected victims of physical abuse. Importantly, only the notes from time of first encounter (e.g.: birth, routine visit, sickness) to the last record before child protection team involvement were used. This allowed us to develop an algorithm using only information available prior to referral to the specialized child protection team. The study was performed in a multi-center referral pediatric hospital on patients screened for abuse within five different locations between 2015 and 2019. Of 1123 patients, 867 records were available after data cleaning and processing, and 55% were abuse-positive as determined by a multi-disciplinary team of clinical professionals. These electronic medical records were encoded with three natural language processing (NLP) algorithms—Bag of Words (BOW), Word Embeddings (WE), and Rules-Based (RB)—and used to train multiple neural network architectures. The BOW and WE encodings utilize the full free-text, while RB selects crucial phrases as identified by physicians. The best architecture was selected by average classification accuracy for the best performing model from each train-test split of a cross-validation experiment. Natural language processing coupled with neural networks detected cases of likely child abuse using only information available to clinicians prior to child protection team referral with average accuracy of 0.90±0.02 and average area under the receiver operator characteristic curve (ROC-AUC) 0.93±0.02 for the best performing Bag of Words models. The best performing rules-based models achieved average accuracy of 0.77±0.04 and average ROC-AUC 0.81±0.05, while a Word Embeddings strategy was severely limited by lack of representative embeddings. Importantly, the best performing model had a false positive rate of 8%, as compared to rates of 20% or higher in previously reported studies. This artificial intelligence approach can help screen patients for whom an abuse concern exists and streamline the identification of patients who may benefit from referral to a child protection team. Furthermore, this approach could be applied to develop computer-aided-diagnosis platforms for the challenging and often intractable problem of reliably identifying pediatric patients suffering from physical abuse.

show abstract

“…Advanced textual analysis, akin to platforms like Voyant Tools but customized for this study, uses natural language processing (NLP) to dissect academic content meticulously [ 452 , 453 , 454 , 455 , 456 , 457 , 458 , 459 , 460 , 461 , 462 , 463 , 464 ]. This aligns with the core themes of microstructural characterization, electrical dynamics, and mechanical complexities in nanocomposites.…”

Section: Introductionmentioning

confidence: 99%

A 30-Year Review on Nanocomposites: Comprehensive Bibliometric Insights into Microstructural, Electrical, and Mechanical Properties Assisted by Artificial Intelligence

Gomes Souza,

Bhansali,

Pal

et al. 2024

Materials

View full text Add to dashboard Cite

From 1990 to 2024, this study presents a groundbreaking bibliometric and sentiment analysis of nanocomposite literature, distinguishing itself from existing reviews through its unique computational methodology. Developed by our research group, this novel approach systematically investigates the evolution of nanocomposites, focusing on microstructural characterization, electrical properties, and mechanical behaviors. By deploying advanced Boolean search strategies within the Scopus database, we achieve a meticulous extraction and in-depth exploration of thematic content, a methodological advancement in the field. Our analysis uniquely identifies critical trends and insights concerning nanocomposite microstructure, electrical attributes, and mechanical performance. The paper goes beyond traditional textual analytics and bibliometric evaluation, offering new interpretations of data and highlighting significant collaborative efforts and influential studies within the nanocomposite domain. Our findings uncover the evolution of research language, thematic shifts, and global contributions, providing a distinct and comprehensive view of the dynamic evolution of nanocomposite research. A critical component of this study is the “State-of-the-Art and Gaps Extracted from Results and Discussions” section, which delves into the latest advancements in nanocomposite research. This section details various nanocomposite types and their properties and introduces novel interpretations of their applications, especially in nanocomposite films. By tracing historical progress and identifying emerging trends, this analysis emphasizes the significance of collaboration and influential studies in molding the field. Moreover, the “Literature Review Guided by Artificial Intelligence” section showcases an innovative AI-guided approach to nanocomposite research, a first in this domain. Focusing on articles from 2023, selected based on citation frequency, this method offers a new perspective on the interplay between nanocomposites and their electrical properties. It highlights the composition, structure, and functionality of various systems, integrating recent findings for a comprehensive overview of current knowledge. The sentiment analysis, with an average score of 0.638771, reflects a positive trend in academic discourse and an increasing recognition of the potential of nanocomposites. Our bibliometric analysis, another methodological novelty, maps the intellectual domain, emphasizing pivotal research themes and the influence of crosslinking time on nanocomposite attributes. While acknowledging its limitations, this study exemplifies the indispensable role of our innovative computational tools in synthesizing and understanding the extensive body of nanocomposite literature. This work not only elucidates prevailing trends but also contributes a unique perspective and novel insights, enhancing our understanding of the nanocomposite research field.

show abstract

Comparison of Word Embeddings for Extraction from Medical Records

Cited by 7 publications

References 14 publications

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records

A 30-Year Review on Nanocomposites: Comprehensive Bibliometric Insights into Microstructural, Electrical, and Mechanical Properties Assisted by Artificial Intelligence

Contact Info

Product

Resources

About