Clinical Report Classification Using Natural Language Processing and Topic Modeling

2012 ◽  
Author(s):  
Efsun Sarioglu ◽  
Hyeong-Ah Choi ◽  
Kabir Yadav
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Clinical Report

An Evaluation of Patient Safety Event Report Categories Using Unsupervised Topic Modeling

2015 ◽  
Vol 54 (04) ◽  
pp. 338-345 ◽  
Author(s):  
A. Fong ◽  
R. Ratwani
Keyword(s):  
Patient Safety ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Free Text ◽  
Event Data ◽  
Event Type ◽  
Modeling Approach ◽  
Safety Event

SummaryObjective: Patient safety event data repositories have the potential to dramatically improve safety if analyzed and leveraged appropriately. These safety event reports often consist of both structured data, such as general event type categories, and unstructured data, such as free text descriptions of the event. Analyzing these data, particularly the rich free text narratives, can be challenging, especially with tens of thousands of reports. To overcome the resource intensive manual review process of the free text descriptions, we demonstrate the effectiveness of using an unsupervised natural language processing approach.Methods: An unsupervised natural language processing technique, called topic modeling, was applied to a large repository of patient safety event data to identify topics, or themes, from the free text descriptions of the data. Entropy measures were used to evaluate and compare these topics to the general event type categories that were originally assigned by the event reporter.Results: Measures of entropy demonstrated that some topics generated from the un-supervised modeling approach aligned with the clinical general event type categories that were originally selected by the individual entering the report. Importantly, several new latent topics emerged that were not originally identified. The new topics provide additional insights into the patient safety event data that would not otherwise easily be detected.Conclusion: The topic modeling approach provides a method to identify topics or themes that may not be immediately apparent and has the potential to allow for automatic reclassification of events that are ambiguously classified by the event reporter.

scholarly journals Forty-two Million Ways to Describe Pain: Topic Modeling of 200,000 PubMed Pain-Related Abstracts Using Natural Language Processing and Deep Learning–Based Text Generation

Pain Medicine ◽  
2020 ◽  
Vol 21 (11) ◽  
pp. 3133-3160
Author(s):  
Patrick J Tighe ◽  
Bharadwaj Sannapaneni ◽  
Roger B Fillingim ◽  
Charlie Doyle ◽  
Michael Kent ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Taxonomic Structure ◽  
Generation Model ◽  
Pain Research ◽  
Embedded Model ◽  
Gated Recurrent Units

Abstract Objective Recent efforts to update the definitions and taxonomic structure of concepts related to pain have revealed opportunities to better quantify topics of existing pain research subject areas. Methods Here, we apply basic natural language processing (NLP) analyses on a corpus of >200,000 abstracts published on PubMed under the medical subject heading (MeSH) of “pain” to quantify the topics, content, and themes on pain-related research dating back to the 1940s. Results The most common stemmed terms included “pain” (601,122 occurrences), “patient” (508,064 occurrences), and “studi-” (208,839 occurrences). Contrarily, terms with the highest term frequency–inverse document frequency included “tmd” (6.21), “qol” (6.01), and “endometriosis” (5.94). Using the vector-embedded model of term definitions available via the “word2vec” technique, the most similar terms to “pain” included “discomfort,” “symptom,” and “pain-related.” For the term “acute,” the most similar terms in the word2vec vector space included “nonspecific,” “vaso-occlusive,” and “subacute”; for the term “chronic,” the most similar terms included “persistent,” “longstanding,” and “long-standing.” Topic modeling via Latent Dirichlet analysis identified peak coherence (0.49) at 40 topics. Network analysis of these topic models identified three topics that were outliers from the core cluster, two of which pertained to women’s health and obstetrics and were closely connected to one another, yet considered distant from the third outlier pertaining to age. A deep learning–based gated recurrent units abstract generation model successfully synthesized several unique abstracts with varying levels of believability, with special attention and some confusion at lower temperatures to the roles of placebo in randomized controlled trials. Conclusions Quantitative NLP models of published abstracts pertaining to pain may point to trends and gaps within pain research communities.

scholarly journals Topic Modeling for Keyword Extraction: using Natural Language Processing methods for keyword extraction in Portal Min@s

2015 ◽  
Vol 23 (3) ◽  
pp. 695 ◽  
Author(s):  
Arnaldo Candido Junior ◽  
Célia Magalhães ◽  
Helena Caseli ◽  
Régis Zangirolami
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Keyword Extraction ◽  
Processing Methods ◽  
Dirichlet Allocation

<p style="margin-bottom: 0cm; line-height: 100%;" align="justify"> </p><p>Este artigo tem o objetivo da avaliar a aplicação de dois métodos automáticos eficientes na extração de palavras-chave, usados pelas comunidades da Linguística de <em>Corpus </em>e do Processamento da Língua Natural para gerar palavras-chave de textos literários: o <em>WordSmith Tools </em>e o <em>Latent Dirichlet Allocation </em>(LDA). As duas ferramentas escolhidas para este trabalho têm suas especificidades e técnicas diferentes de extração, o que nos levou a uma análise orientada para a sua performance. Objetivamos entender, então, como cada método funciona e avaliar sua aplicação em textos literários. Para esse fim, usamos análise humana, com conhecimento do campo dos textos usados. O método LDA foi usado para extrair palavras-chave por meio de sua integração com o <em>Portal Min@s: Corpora de Fala e Escrita</em>, um sistema geral de processamento de <em>corpora</em>, concebido para diferentes pesquisas de Linguística de <em>Corpus</em>. Os resultados do experimento confirmam a eficácia do WordSmith Tools e do LDA na extração de palavras-chave de um <em>corpus </em>literário, além de apontar que é necessária a análise humana das listas em um estágio anterior aos experimentos para complementar a lista gerada automaticamente, cruzando os resultados do WordSmith Tools e do LDA. Também indicam que a intuição linguística do analista humano sobre as listas geradas separadamente pelos dois métodos usados neste estudo foi mais favorável ao uso da lista de palavras-chave do WordSmith Tools.</p>

Examination of fake news from a viral perspective: an interplay of emotions, resonance, and sentiments

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Krishnadas Nanath ◽  
Supriya Kaitheri ◽  
Sonia Malik ◽  
Shahid Mustafa
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Machine Learning Algorithms ◽  
Fake News ◽  
Linguistic Features ◽  
Data Set ◽  
Content Type

Purpose The purpose of this paper is to examine the factors that significantly affect the prediction of fake news from the virality theory perspective. The paper looks at a mix of emotion-driven content, sentimental resonance, topic modeling and linguistic features of news articles to predict the probability of fake news. Design/methodology/approach A data set of over 12,000 articles was chosen to develop a model for fake news detection. Machine learning algorithms and natural language processing techniques were used to handle big data with efficiency. Lexicon-based emotion analysis provided eight kinds of emotions used in the article text. The cluster of topics was extracted using topic modeling (five topics), while sentiment analysis provided the resonance between the title and the text. Linguistic features were added to the coding outcomes to develop a logistic regression predictive model for testing the significant variables. Other machine learning algorithms were also executed and compared. Findings The results revealed that positive emotions in a text lower the probability of news being fake. It was also found that sensational content like illegal activities and crime-related content were associated with fake news. The news title and the text exhibiting similar sentiments were found to be having lower chances of being fake. News titles with more words and content with fewer words were found to impact fake news detection significantly. Practical implications Several systems and social media platforms today are trying to implement fake news detection methods to filter the content. This research provides exciting parameters from a viral theory perspective that could help develop automated fake news detectors. Originality/value While several studies have explored fake news detection, this study uses a new perspective on viral theory. It also introduces new parameters like sentimental resonance that could help predict fake news. This study deals with an extensive data set and uses advanced natural language processing to automate the coding techniques in developing the prediction model.

scholarly journals The Semantics and Collocations Relation in Food Reviews

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Fazel Keshtkar ◽  
Ledong Shi ◽  
Syed Ahmad Chan Bukhari
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Computational Linguistics ◽  
Language Processing ◽  
Topic Modeling ◽  
State Of The Art ◽  
Semantic Relation ◽  
The Other ◽  
Good Place ◽  
The Common

Finding our favorite dishes have became a hard task since restaurants are providing more choices and va- rieties. On the other hand, comments and reviews of restaurants are a good place to look for the answer. The purpose of this study is to use computational linguistics and natural language processing to categorise and find semantic relation in various dishes based on reviewers’ comments and menus description. Our goal is to imple- ment a state-of-the-art computational linguistics meth- ods such as, word embedding model, word2vec, topic modeling, PCA, classification algorithm. For visualiza- tions, t-Distributed Stochastic Neighbor Embedding (t- SNE) was used to explore the relation within dishes and their reviews. We also aim to extract the common pat- terns between different dishes among restaurants and reviews comment, and in reverse, explore the dishes with a semantics relations. A dataset of articles related to restaurant and located dishes within articles used to find comment patterns. Then we applied t-SNE visual- izations to identify the root of each feature of the dishes. As a result, to find a dish our model is able to assist users by several words of description and their inter- est. Our dataset contains 1,000 articles from food re- views agency on a variety of dishes from different cul- tures: American, i.e. ’steak’, hamburger; Chinese, i.e. ’stir fry’, ’dumplings’; Japanese, i.e., ’sushi’.

scholarly journals Natural Language Processing (NLP) in Qualitative Public Health Research: A Proof of Concept Study

2019 ◽  
Vol 18 ◽  
pp. 160940691988702 ◽  
Author(s):  
William Leeson ◽  
Adam Resnick ◽  
Daniel Alexander ◽  
John Rovers
Keyword(s):  
Public Health ◽  
Natural Language Processing ◽  
Natural Language ◽  
Qualitative Analysis ◽  
Computer Science ◽  
Language Processing ◽  
Topic Modeling ◽  
Qualitative Data ◽  
Proof Of Concept ◽  
Open Coding

Qualitative data-analysis methods provide thick, rich descriptions of subjects’ thoughts, feelings, and lived experiences but may be time-consuming, labor-intensive, or prone to bias. Natural language processing (NLP) is a machine learning technique from computer science that uses algorithms to analyze textual data. NLP allows processing of large amounts of data almost instantaneously. As researchers become conversant with NLP, it is becoming more frequently employed outside of computer science and shows promise as a tool to analyze qualitative data in public health. This is a proof of concept paper to evaluate the potential of NLP to analyze qualitative data. Specifically, we ask if NLP can support conventional qualitative analysis, and if so, what its role is. We compared a qualitative method of open coding with two forms of NLP, Topic Modeling, and Word2Vec to analyze transcripts from interviews conducted in rural Belize querying men about their health needs. All three methods returned a series of terms that captured ideas and concepts in subjects’ responses to interview questions. Open coding returned 5–10 words or short phrases for each question. Topic Modeling returned a series of word-probability pairs that quantified how well a word captured the topic of a response. Word2Vec returned a list of words for each interview question ordered by which words were predicted to best capture the meaning of the passage. For most interview questions, all three methods returned conceptually similar results. NLP may be a useful adjunct to qualitative analysis. NLP may be performed after data have undergone open coding as a check on the accuracy of the codes. Alternatively, researchers can perform NLP prior to open coding and use the results to guide their creation of their codebook.

scholarly journals Tracking mutational semantics of SARS-CoV-2 genomes

2021 ◽  
Author(s):  
Rohan Singh ◽  
Sunil Nagpal ◽  
Nishal Kumar Pinna ◽  
Sharmila S Mande
Keyword(s):  
Biological Sciences ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Data Science ◽  
Higher Order ◽  
Dynamic Phenomenon ◽  
Alternative Strategies ◽  
Daunting Task

Genomes have an inherent context dictated by the order in which the nucleotides and higher order genomic elements are arranged in the DNA/RNA. Learning this context is a daunting task, governed by the combinatorial complexity of interactions possible between ordered elements of genomes. Can natural language processing be employed on these orderly, complex and also evolving datatypes (genomic sequences) to reveal the latent patterns or context of genomic elements (e.g Mutations)? Here we present an approach to understand the mutational landscape of Covid-19 by treating the temporally changing (continuously mutating) SARS-CoV-2 genomes as documents. We demonstrate how the analogous interpretation of evolving genomes to temporal literature corpora provides an opportunity to use dynamic topic modeling (DTM) and temporal Word2Vec models to delineate mutation signatures corresponding to different Variants-of-Concerns and tracking the semantic drift of Mutations-of-Concern (MoC). We identified and studied characteristic mutations affiliated to Covid-infection severity and tracked their relationship with MoCs. Our ground work on utility of such temporal NLP models in genomics could supplement ongoing efforts in not only understanding the Covid pandemic but also provide alternative strategies in studying dynamic phenomenon in biological sciences through data science (especially NLP, AI/ML).

scholarly journals Patient Triage by Topic Modeling of Referral Letters: Feasibility Study

10.2196/21252 ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. e21252
Author(s):  
Irena Spasic ◽  
Kate Button
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Topic Modeling ◽  
Topic Model ◽  
Qualitative Evaluation ◽  
Musculoskeletal Conditions ◽  
Latent Topics ◽  
Referral Letters

Background Musculoskeletal conditions are managed within primary care, but patients can be referred to secondary care if a specialist opinion is required. The ever-increasing demand for health care resources emphasizes the need to streamline care pathways with the ultimate aim of ensuring that patients receive timely and optimal care. Information contained in referral letters underpins the referral decision-making process but is yet to be explored systematically for the purposes of treatment prioritization for musculoskeletal conditions. Objective This study aims to explore the feasibility of using natural language processing and machine learning to automate the triage of patients with musculoskeletal conditions by analyzing information from referral letters. Specifically, we aim to determine whether referral letters can be automatically assorted into latent topics that are clinically relevant, that is, considered relevant when prescribing treatments. Here, clinical relevance is assessed by posing 2 research questions. Can latent topics be used to automatically predict treatment? Can clinicians interpret latent topics as cohorts of patients who share common characteristics or experiences such as medical history, demographics, and possible treatments? Methods We used latent Dirichlet allocation to model each referral letter as a finite mixture over an underlying set of topics and model each topic as an infinite mixture over an underlying set of topic probabilities. The topic model was evaluated in the context of automating patient triage. Given a set of treatment outcomes, a binary classifier was trained for each outcome using previously extracted topics as the input features of the machine learning algorithm. In addition, a qualitative evaluation was performed to assess the human interpretability of topics. Results The prediction accuracy of binary classifiers outperformed the stratified random classifier by a large margin, indicating that topic modeling could be used to predict the treatment, thus effectively supporting patient triage. The qualitative evaluation confirmed the high clinical interpretability of the topic model. Conclusions The results established the feasibility of using natural language processing and machine learning to automate triage of patients with knee or hip pain by analyzing information from their referral letters.

Customers' experience of purchasing event tickets: mining online reviews based on topic modeling and sentiment analysis

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Krzysztof Celuch
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Topic Modeling ◽  
Data Science ◽  
Latent Dirichlet Allocation ◽  
Online Reviews ◽  
Third Party ◽  
Content Type

PurposeIn search of creating an extraordinary experience for customers, services have gone beyond the means of a transaction between buyers and sellers. In the event industry, where purchasing tickets online is a common procedure, it remains unclear as to how to enhance the multifaceted experience. This study aims at offering a snapshot into the most valued aspects for consumers and to uncover consumers' feelings toward their experience of purchasing event tickets on third-party ticketing platforms.Design/methodology/approachThis is a cross-disciplinary study that applies knowledge from both data science and services marketing. Under the guise of natural language processing, latent Dirichlet allocation topic modeling and sentiment analysis were used to interpret the embedded meanings based on online reviews.FindingsThe findings conceptualized ten dimensions valued by eventgoers, including technical issues, value of core product and service, word-of-mouth, trustworthiness, professionalism and knowledgeability, customer support, information transparency, additional fee, prior experience and after-sales service. Among these aspects, consumers rated the value of the core product and service to be the most positive experience, whereas the additional fee was considered the least positive one.Originality/valueDrawing from the intersection of natural language processing and the status quo of the event industry, this study offers a better understanding of eventgoers' experiences in the case of purchasing online event tickets. It also provides a hands-on guide for marketers to stage memorable experiences in the era of digitalization.

scholarly journals Doctrinal Implications of Computational Antitrust

10.51868/7 ◽  
2021 ◽  
pp. 117-131
Author(s):  
Felix Chang ◽  
Erin McCabe ◽  
Zhaowei Ren ◽  
Joshua Beckelhimer ◽  
James Lee
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Market Power ◽  
Language Processing ◽  
Topic Modeling ◽  
Access Project ◽  
Key Terms ◽  
Single Set

Utilizing antitrust decisions extracted from the Caselaw Access Project, we aggregate—or embed—layers of topic modeling into a single set of visualizations. Aggregated models can provide new perspectives on how courts tackle thorny doctrinal questions, such as the measure of market power and the balance between antitrust and regulation. Our central contribution is the improvement of natural language processing to provide greater context for key terms. Our secondary contribution is a new suite of tools to assess the weighty policy arguments that currently dominate antitrust.

Sign in / Sign up

Export Citation Format

Share Document