Article
Computer Science, Artificial Intelligence
Ioannis Almalis, Eleftherios Kouloumpris, Ioannis Vlahavas
Summary: This paper introduces a deep learning solution for sentiment analysis that performs well on previously unseen tweet data. Additionally, the study provides a novel research on predicting specific economic sectors affected by news articles.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yi Han, Mohsen Moghaddam
Summary: Identifying user needs is crucial for successful user-centered design, however, many design firms lack tools for monitoring external platforms and implementing digital methods. Cutting-edge sentiment analysis methods based on deep learning have shown promising results, but they require expert-labeled data and predefined attributes, which limit their impact on designers' insights.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Ricardo Martins, Jose Joao Almeida, Pedro Henriques, Paulo Novais
Summary: Writing style can identify authors, and the prevalence of fake news in social media has made author identification more crucial. This paper introduces a method to improve authorship identification by analyzing emotional profiles in social media messages.
Article
Computer Science, Artificial Intelligence
Jacqueline Kazmaier, Jan H. van Vuuren
Summary: This paper examines the use of ensemble models in sentiment classification, introducing several techniques for constructing heterogeneous ensembles and evaluating their performance. The results demonstrate significant performance improvements of several ensemble configurations compared to the best individual model across different data sets, identifying clear trends that may be valuable to other researchers in the field. Additionally, a novel ensemble selection approach is proposed to address storage and retraining challenges commonly associated with similar methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Alexandru-Costin Baroiu, Stefan Trausan-Matu
Summary: This paper proposes an approach for the automatic detection of sarcasm context in order to develop models that can correctly identify the contexts in which sarcasm may occur or is appropriate. Multiple models are trained and benchmarked using the MUStARD dataset, and an attention-based long short-term memory architecture proves to be the best performer with an F1 score of 60.1. Future research directions include developing a conversational agent that can identify and respond to sarcasm.
Article
Computer Science, Information Systems
Mustafa Khanbhai, Leigh Warren, Joshua Symons, Kelsey Flott, Stephanie Harrison-White, Dave Manton, Ara Darzi, Erik Mayer
Summary: This study demonstrates the use of natural language processing (NLP) to extract meaningful information from patient experience surveys. By analyzing free-text comments, the study identifies issues related to transitions of care, such as discharge and appointment processes. These findings can be used to guide interventions aimed at improving transitional care processes.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Salud Maria Jimenez-Zafra, Noa P. Cruz-Diaz, Maite Taboada, Maria Teresa Martin-Valdivia
Summary: Accurate negation identification is crucial in sentiment analysis, and recent developments have provided methods for accurate detection in languages other than English. This paper focuses on implementing a Spanish system for negation cue detection and applying it to sentiment analysis, demonstrating improvements in accuracy for Spanish sentiment analysis tasks.
NATURAL LANGUAGE ENGINEERING
(2021)
Article
Mathematics
Bledar Fazlija, Pedro Harder
Summary: This paper extracts financial market sentiment information from news articles using natural language processing methods and predicts the price direction of the stock market index. The results show that sentiment scores based on news content are particularly useful for stock price direction prediction.
Article
Public, Environmental & Occupational Health
Jihyun Park, Abhishek Jindal, Patty Kuo, Michael Tanana, Jennifer Elston Lafata, Ming Tai-Seale, David C. Atkins, Zac E. Imel, Padhraic Smyth
Summary: The study used machine learning models to predict emotions of patients and physicians in primary care visits, and the results indicated that the recurrent neural network model showed a high level of agreement with human ratings in emotion evaluation.
PATIENT EDUCATION AND COUNSELING
(2021)
Article
Computer Science, Artificial Intelligence
Sergio Consoli, Luca Barbaglia, Sebastiano Manzan
Summary: Extracting sentiment from news text, social media, and blogs has gained interest in the economics and finance fields. This paper proposes a novel methodology for Fine-Grained Aspect-based Sentiment (FiGAS) analysis, which aims to identify sentiment associated with specific topics in each sentence and assign real-valued polarity scores. The approach outperforms other lexicon-based sentiment analysis methods and provides a sentiment score closer to human annotators.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Basavaraj N. Hiremath, Malini M. Patil
Summary: This article introduces the process of sentiment analysis, which categorizes patient reviews using natural language processing techniques. By analyzing patient reviews, an aspect-based sentiment analysis method is proposed to improve clinical decision-making. The results of the study show that the SVM algorithm performs the best in terms of accuracy.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Health Care Sciences & Services
Zhaohua Lu, Jin-Ah Sim, Jade X. Wang, Christopher B. Forrest, Kevin R. Krull, Deokumar Srivastava, Melissa M. Hudson, Leslie L. Robison, Justin N. Baker, I-Chan Huang
Summary: This study aimed to test the validity of natural language processing and machine learning algorithms in identifying different attributes of pain interference and fatigue symptoms experienced by child and adolescent survivors of cancer. The results showed that the BERT method outperformed other methods in accuracy.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Krzysztof Fiok, Waldemar Karwowski, Edgar Gutierrez, Maciej Wilamowski
Summary: The research in sentiment analysis has been thriving with the advancement of machine learning and deep learning. By comparing with SemEval, the study evaluates performance of popular natural language processing methods and explores how new unsupervised ML techniques can enhance predictive performance of models.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Physics, Condensed Matter
Lei Zhang, Mu He
Summary: In this manuscript, the authors utilized natural language processing (NLP) technique to predict the existence of solar cell types and identify material candidates based on textual data from literature. The study demonstrates the viability of using textual data for data-driven materials prediction and highlights NLP as a powerful tool for reliable prediction of solar cell materials.
JOURNAL OF PHYSICS-CONDENSED MATTER
(2022)
Article
Computer Science, Information Systems
Tatsuho Nagatomo, Takefumi Hiraki, Hiroki Ishizuka, Norihisa Miki
Summary: In this study, a new approach to tactile research using natural language processing of archival word corpus is proposed. By extracting and analyzing touch-related words and sentences, researchers aim to understand how humans perceive surfaces. The study successfully mapped onomatopoeias with adjectives and identified new tactile dimensions through principal component analysis.
Article
Genetics & Heredity
Jean Pierre Bayley, Birke Bausch, Jeroen C. Jansen, Erik F. Hensen, Karin van der Tuin, Eleonora P. M. Corssmit, Peter Devilee, Hartmut P. H. Neumann
Summary: This study investigates the genotype-phenotype associations of SDHB gene variants and finds that truncating variants are associated with a higher risk of developing both PPGL and malignancy compared to missense variants. These findings further support the previously established associations between truncating variants and PPGL, and suggest that the two variant types differ in their impact on complex II function.
JOURNAL OF MEDICAL GENETICS
(2023)
Article
Otorhinolaryngology
Olaf M. Neve, Jeroen C. Jansen, Radboud W. Koot, Mischa de Ridder, Peter Paul G. van Benthem, Anne M. Stiggelbout, Erik F. Hensen
Summary: This study assessed the long-term quality of life (QoL) of patients with vestibular schwannoma in relation to treatment modality and decisional regret. The results showed that the long-term QoL was comparable for patients under active surveillance and those who received active treatment, and it remained stable over time. This suggests that, on average, preservation of QoL of patients with vestibular schwannoma is feasible when adequately managed.
OTOLARYNGOLOGY-HEAD AND NECK SURGERY
(2023)
Article
Clinical Neurology
Maarten C. Kleijwegt, Radboud W. Koot, Andel G. L. van der Mey, Erik F. Hensen, Martijn J. A. Malessy
Summary: This study retrospectively analyzed the advantages and disadvantages of combining the translabyrinthine and classic retrosigmoid approaches. The results showed that the combined approach can safely remove large meningiomas and schwannomas in selected cases. This technique provides sufficient exposure.
JOURNAL OF NEUROLOGICAL SURGERY PART B-SKULL BASE
(2023)
Article
Medicine, General & Internal
David J. McLernon, Daniele Giardiello, Ben Van Calster, Laure Wynants, Nan van Geloven, Maarten van Smeden, Terry Therneau, Ewout W. Steyerberg, STRATOS Initiative
Summary: Risk prediction models need validation to assess their performance. This article focuses on evaluating predictions and improving clinical decision making using survival models based on Cox proportional hazards regression. The authors present a case study on breast cancer patients, where a Cox regression model is developed and validated for prediction of recurrence or death.
ANNALS OF INTERNAL MEDICINE
(2023)
Article
Critical Care Medicine
Anne A. H. de Hond, Ilse M. J. Kant, Mattia Fornasa, Giovanni Cina, Paul W. G. Elbers, Patrick J. J. Thoral, M. Sesmu Arbous, Ewout W. W. Steyerberg
Summary: This study aimed to assess the performance of a decision support tool based on a machine learning model in predicting readmission or death within 7 days after ICU discharge. Through independent validation and retraining on multiple datasets, it was found that the model performed well in new settings and can be considered as an effective clinical tool.
CRITICAL CARE MEDICINE
(2023)
Article
Gastroenterology & Hepatology
Carlijn A. M. Roumans, Ruben D. van der Bogt, Daan Nieboer, Ewout W. Steyerberg, Dimitris Rizopoulos, Iris Lansdorp-Vogelaar, Katharina Biermann, Marco J. Bruno, Manon C. W. Spaander
Summary: In this multicenter prospective cohort study, it was found that half of Barrett's esophagus (BE) surveillance endoscopies do not adhere to guideline recommendations. However, there was no clear association between nonadherence and endoscopic curability of esophageal adenocarcinoma (EAC) or mortality, indicating the need for optimization of BE surveillance guidelines to minimize the burden of endoscopies.
DISEASES OF THE ESOPHAGUS
(2023)
Article
Cardiac & Cardiovascular Systems
Steele C. Butcher, Benjamin Essayagh, Ewout W. Steyerberg, Giovanni Benfari, Clemence Antoine, Francesco Grigioni, Thierry Le Tourneau, Jean-Christian Roussel, Aniek van Wijngaarden, Nina Ajmone Marsan, Christophe Tribouilloy, Dan Rusinaru, Aviram Hochstadt, Yan Topilsky, Hector Michelena, Victoria Delgado, Jeroen J. Bax, Maurice Enriquez-Sarano
Summary: This study examined the impact of secondary outcome determinants on post-operative survival in patients with degenerative mitral regurgitation (DMR) and found that the number of these determinants was independently associated with increased mortality after surgery, providing better outcome discrimination than traditional indications for surgery.
EUROPEAN HEART JOURNAL
(2023)
Review
Health Care Sciences & Services
Mohammed T. Hudda, Lucinda Archer, Maarten van Smeden, Karel G. M. Moons, Gary S. Collins, Ewout W. Steyerberg, Charlotte Wahlich, Johannes B. Reitsma, Richard D. Riley, Ben Van Calster, Laure Wynants
Summary: The study aims to assess the improvement in reporting completeness of COVID-19 prediction models after peer review. The findings suggest that the reporting quality of preprints is poor and did not improve significantly after peer review, indicating that peer review had minimal effect on the completeness of reporting during the COVID-19 pandemic.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Otorhinolaryngology
Kimberley S. S. Koetsier, Heiko Locher, Radboud W. W. Koot, Andel G. L. van Der Mey, Peter-Paul G. van Benthem, Jeroen C. C. Jansen, Erik F. F. Hensen
Summary: This study evaluates the natural course of hearing loss prior to treatment in patients with progressive tumors and an indication for active intervention. The majority of patients (58%) with radiologically confirmed progressive vestibular schwannomas experience progressive sensorineural HL during observation.
OTOLARYNGOLOGY-HEAD AND NECK SURGERY
(2023)
Article
Clinical Neurology
Kimberley S. Koetsier, William A. Mehan, Karen Buch, D. Bradley Welling, Peter Paul G. van Benthem, Erik F. Hensen, Helen A. Shih
Summary: This study aimed to quantitatively evaluate the occurrence and course of signal intensity (SI) loss on T2-weighted MRI in vestibular schwannoma patients, and its possible association with proton radiotherapy and hearing loss. The results demonstrated that the relative mean cochlear SI was diminished on the treated side, but did not further decrease after proton radiotherapy. The diminished cochlear SI was not correlated with subsequent loss of hearing.
OTOLOGY & NEUROTOLOGY
(2023)
Article
Multidisciplinary Sciences
Jesus Villar, Jesus M. Gonzalez-Martin, Jose M. Anon, Carlos Ferrando, Juan A. Soler, Fernando Mosteiro, Juan M. Mora-Ordonez, Alfonso Ambros, Lorena Fernandez, Raquel Montiel, Anxela Vidal, Tomas Munoz, Lina Perez-Mendez, Pedro Rodriguez-Suarez, Cristina Fernandez, Rosa L. L. Fernandez, Tamas Szakmany, Karen E. A. Burns, Ewout W. Steyerberg, Arthur S. Slutsky
Summary: Mortality assessment in clinical studies of acute respiratory distress syndrome (ARDS) has not been well-defined. This study aimed to determine the timing of mortality assessment in ICU patients with moderate-to-severe ARDS, and its predictive value for treatment response. Observational cohorts and a randomized trial were analyzed, and it was found that ICU mortality rates closely approximated 28-day mortality rates. ICU mortality assessment within the first week of a trial could serve as an early predictor of treatment response for moderate-to-severe ARDS patients.
SCIENTIFIC REPORTS
(2023)
Article
Mathematical & Computational Biology
Doranne Thomassen, Ewout Steyerberg, Saskia le Cessie
Summary: In clinical practice, it is crucial to determine the absolute risk reduction of treatment for individual patients. However, logistic regression in trials with binary outcomes provides estimates of treatment effects in terms of log odds differences. In this study, we propose a new Bayesian regression model for binary outcomes on the additive risk scale, allowing for direct estimation of treatment effects on the linear scale of clinical interest. Comparisons were made with a previously proposed additive risk model and backtransforming predictions from a logistic model. Results showed that modelling untransformed risk can yield significantly different treatment effect estimates, particularly for small sample sizes or extreme predicted risks close to 0% or 100%. Our proposed model proved to be more sensitive in detecting all information in the data in a network meta-analysis.
STATISTICS IN MEDICINE
(2023)
Article
Medicine, General & Internal
Nicole von Steinbuechel, Stefanie Hahm, Holger Muehlan, Juan Carlos Arango-Lasprilla, Fabian Bockhop, Amra Covic, Silke W. Schmidt, Ewout Steyerberg, Andrew I. R. Maas, David Menon, Nada Andelic, Marina Zeldovich, CTR TBI Participants Investigators
Summary: Traumatic brain injury (TBI) is a major cause of death and disability worldwide. This study aims to understand the impact of TBI on various outcome domains, evaluating factors contributing to worsening or improving outcomes. The study used patient-reported outcome measures and identified different trajectory classes for outcome after TBI, including stable good health, persistent impairments, improving health, and deteriorating health. Individuals with persistent impairments and deterioration need special attention and long-term clinical monitoring and therapy.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Otorhinolaryngology
Olaf M. Neve, Stephan R. Romeijn, Yunjie Chen, Larissa Nagtegaal, Willem Grootjans, Jeroen C. Jansen, Marius Staring, Berit M. Verbist, Erik F. Hensen
Summary: This study validates the accuracy of automated 2D diameter measurements of vestibular schwannomas on MRI by comparing them with manual measurements. The results show high correlation and agreement between automated and human measurements, with automated measurements performing better in tumor progression detection.
OTOLARYNGOLOGY-HEAD AND NECK SURGERY
(2023)
Article
Clinical Neurology
M. C. Kleijwegt, C. Wever, E. F. Hensen, J. C. Jansen, R. W. Koot, M. J. A. Malessy
Summary: This study assessed the ability to smile after a hypoglossal-facial nerve transfer (N12-N7). It was found that there was good facial symmetry at rest but asymmetry during smiling. Additional procedures are needed to improve the ability to smile after N12-N7 transfer.
JOURNAL OF NEUROLOGICAL SURGERY PART B-SKULL BASE
(2023)