Search results for "Text mining"

showing 10 items of 510 documents

Statistically Validated Networks for evaluating coherence in topic models

2022

Probabilistic topic models have become one of the most widespread machine learning technique for textual analysis purpose. In this framework, Latent Dirichlet Allocation (LDA) gained more and more popularity as a text modelling technique. The idea is that documents are represented as random mixtures over latent topics, where a distribution over words characterizes each topic. Unfortunately, topic models do not guarantee the interpretability of their outputs. The topics learned from the model may be characterized by a set of irrelevant or unchained words, being useless for the interpretation. In the framework of topic quality evaluation, the pairwise semantic cohesion among the top-N most pr…

Settore SECS-S/06 -Metodi Mat. dell'Economia e d. Scienze Attuariali e Finanz.Text Mining Probabilistic Topic Models Topic coherence Statistically Validated NetworksSettore SECS-S/01 - Statistica
researchProduct

Melanoma Extirpation with Immediate Reconstruction

2017

Letter to Editor

Single stagebusiness.industryMelanomaSettore MED/19 - Chirurgia Plasticamedicine.diseaseCost savings030207 dermatology & venereal diseases03 medical and health sciences0302 clinical medicineText miningCost Savings030220 oncology & carcinogenesismedicineHumansSurgeryOperations managementmelanoma surgerybusinessMelanomaPlastic and Reconstructive Surgery
researchProduct

Tackling the Limitations of Copolymeric Small Interfering RNA Delivery Agents by a Combined Experimental–Computational Approach

2019

Despite the first successful applications of nonviral delivery vectors for small interfering RNA in the treatment of illnesses, such as the respiratory syncytial virus infection, the preparation of a clinically suitable, safe, and efficient delivery system still remains a challenge. In this study, we tackle the drawbacks of the existing systems by a combined experimental-computational in-depth investigation of the influence of the polymer architecture over the binding and transfection efficiency. For that purpose, a library of diblock copolymers with a molar mass of 30 kDa and a narrow dispersity (Đ1.12) was synthesized. We studied in detail the impact of an altered block size and/or compos…

Small interfering RNAPolymers and PlasticsBioengineering02 engineering and technologyComputational biologyBiology010402 general chemistry01 natural sciencesVirusBiomaterialsDrug Delivery SystemsText miningMaterials ChemistryHumansComputer SimulationRNA Small Interferingbusiness.industryRNA021001 nanoscience & nanotechnology0104 chemical sciencesHEK293 CellsModels ChemicalMCF-7 Cells0210 nano-technologybusinessHeLa CellsBiomacromolecules
researchProduct

Ranking coherence in topic models using statistically validated networks

2023

Probabilistic topic models have become one of the most widespread machine learning techniques in textual analysis. Topic discovering is an unsupervised process that does not guarantee the interpretability of its output. Hence, the automatic evaluation of topic coherence has attracted the interest of many researchers over the last decade, and it is an open research area. This article offers a new quality evaluation method based on statistically validated networks (SVNs). The proposed probabilistic approach consists of representing each topic as a weighted network of its most probable words. The presence of a link between each pair of words is assessed by statistically validating their co-oc…

Statistically Validated NetworksTopic coherenceText MiningProbabilistic Topic modelLibrary and Information SciencesInformation SystemsJournal of Information Science
researchProduct

LipiDisease: associate lipids to diseases using literature mining

2021

Abstract Summary Lipids exhibit an essential role in cellular assembly and signaling. Dysregulation of these functions has been linked with many complications including obesity, diabetes, metabolic disorders, cancer and more. Investigating lipid profiles in such conditions can provide insights into cellular functions and possible interventions. Hence the field of lipidomics is expanding in recent years. Even though the role of individual lipids in diseases has been investigated, there is no resource to perform disease enrichment analysis considering the cumulative association of a lipid set. To address this, we have implemented the LipiDisease web server. The tool analyzes millions of recor…

Statistics and ProbabilitySupplementary dataWeb serverAcademicSubjects/SCI01060Computer scienceCellular functionsComputational biologyDiseasecomputer.software_genreApplications NotesBiochemistryField (computer science)Computer Science ApplicationsComputational MathematicsComputational Theory and MathematicsLipidomicsData and Text MiningMolecular BiologycomputerBioinformatics
researchProduct

Adaptive Responses in Hepatic and Intestinal Cholesterogenesis Following Ileal Resection in the Rat

1974

Taurocholic Acidmedicine.medical_specialtybusiness.industryChemistryClinical BiochemistryGeneral MedicineBiochemistryGastroenterologyRatsIleal resectionFecesSterolsCholesterolJejunumEndocrinologyText miningLiverIleumInternal medicineIntestine SmallmedicineAnimalsbusinessEuropean Journal of Clinical Investigation
researchProduct

Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class

2021

Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest. Objective: To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVEF), by using available data from Electronic Health Records (EHR). Subjects and methods: 2854 subjects over 25 years old with a diagnosis of HF and LVEF, measured by echocardiography, were selected to develop an algorithm to predict patients with reduced EF using supervised analysis. The performance of the developed algorithm was tested in heart failure patients from Primary Care. To select the mo…

Technologymedicine.medical_specialtyphenotypeQH301-705.5heart failureBioengineering030204 cardiovascular system & hematologyArticleprimary care03 medical and health sciences0302 clinical medicineText miningLasso (statistics)Internal medicinemedicine030212 general & internal medicineMyocardial infarctionBiology (General)Cluster analysisEjection fractionbusiness.industryUnstable anginaTallergologyleft ventricular ejection fractionAtrial fibrillationartificial intelligencemedicine.disease3. Good healthRandom forestHeart failureCardiologysupervised analysisbusiness
researchProduct

Correction: Mechanical properties of provisional dental materials: A systematic review and meta-analysis.

2018

Provisional restorations represent an important phase during the rehabilitation process, knowledge of the mechanical properties of the available materials allows us to predict their clinical performance. At present, there is no systematic review, which supports the clinicians’ criteria, in the selection of a specific material over another for a particular clinical situation. The purpose of this systematic review and meta-analysis was to assess and compare the mechanical properties of dimethacrylates and monomethacrylates used in fabricating direct provisional restorations, in terms of flexural strength, fracture toughness and hardness. This review followed the PRISMA guidelines. The searche…

TeethComputer sciencePolymerslcsh:MedicineChemical Composition02 engineering and technologycomputer.software_genre01 natural sciencesPolymerizationMathematical and Statistical TechniquesMedicine and Health Scienceslcsh:Science010302 applied physicsMultidisciplinaryChemical ReactionsResearch Assessment021001 nanoscience & nanotechnologyChemistryMacromoleculesMeta-analysisPhysical SciencesAnatomy0210 nano-technologyPlasticsNatural language processingStatistics (Mathematics)Research ArticleSystematic ReviewsMaterials by StructureMaterials ScienceMaterial PropertiesResearch and Analysis MethodsText mining0103 physical sciencesMechanical PropertiesStatistical MethodsMaterials by Attributebusiness.industrylcsh:RBiology and Life SciencesPolymer ChemistryJawlcsh:QArtificial intelligencebusinesscomputerDigestive SystemHeadMathematicsMeta-AnalysisPLoS ONE
researchProduct

Aspects Concerning SVM Method’s Scalability

2008

In the last years the quantity of text documents is increasing continually and automatic document classification is an important challenge. In the text document classification the training step is essential in obtaining a good classifier. The quality of learning depends on the dimension of the training data. When working with huge learning data sets, problems regarding the training time that increases exponentially are occurring. In this paper we are presenting a method that allows working with huge data sets into the training step without increasing exponentially the training time and without significantly decreasing the classification accuracy.

Text document classificationStructured support vector machinebusiness.industryComputer scienceDocument classificationcomputer.software_genreSupport vector machineText miningScalabilityData miningbusinessCluster analysiscomputerClassifier (UML)
researchProduct

Studying mitochondrial CB1 receptors: Yes we can

2014

Text miningCannabinoid receptorbusiness.industryCorrespondenceMEDLINEMedicineCell BiologyComputational biologybusinessReceptorMolecular BiologyMolecular Metabolism
researchProduct