Mostrar el registro sencillo del ítem

dc.contributor.authorSánchez-de-Madariaga, Ricardo 
dc.contributor.authorMartinez-Romo, Juan
dc.contributor.authorCantero-Escribano, José M
dc.contributor.authorAraujo, Lourdes
dc.date.accessioned2022-05-20T07:49:34Z
dc.date.available2022-05-20T07:49:34Z
dc.date.issued2022-01-24
dc.identifier.citationBMC Med Inform Decis Mak. 2022 Jan 24;22(1):20.es_ES
dc.identifier.urihttp://hdl.handle.net/20.500.12105/14424
dc.description.abstractBackground: Association Rules are one of the main ways to represent structural patterns underlying raw data. They represent dependencies between sets of observations contained in the data. The associations established by these rules are very useful in the medical domain, for example in the predictive health field. Classic algorithms for association rule mining give rise to huge amounts of possible rules that should be filtered in order to select those most likely to be true. Most of the proposed techniques for these tasks are unsupervised. However, the accuracy provided by unsupervised systems is limited. Conversely, resorting to annotated data for training supervised systems is expensive and time-consuming. The purpose of this research is to design a new semi-supervised algorithm that performs like supervised algorithms but uses an affordable amount of training data. Methods: In this work we propose a new semi-supervised data mining model that combines unsupervised techniques (Fisher's exact test) with limited supervision. Starting with a small seed of annotated data, the model improves results (F-measure) obtained, using a fully supervised system (standard supervised ML algorithms). The idea is based on utilising the agreement between the predictions of the supervised system and those of the unsupervised techniques in a series of iterative steps. Results: The new semi-supervised ML algorithm improves the results of supervised algorithms computed using the F-measure in the task of mining medical association rules, but training with an affordable amount of manually annotated data. Conclusions: Using a small amount of annotated data (which is easily achievable) leads to results similar to those of a supervised system. The proposal may be an important step for the practical development of techniques for mining association rules and generating new valuable scientific medical knowledge.es_ES
dc.description.sponsorshipThis work has been partially supported by projects DOTT-HEALTH (PID2019-106942RB-C32, MCI/AEI/FEDER, UE). (Design of the study. Analysis and interpretation of data) and EXTRAE II (IMIENS 2019). (Design of the study. Analysis and interpretation of data. HUF corpus manual tagging. Writing of the manuscript), PI18CIII/00004 “Infobanco para uso secundario de datos basado en estándares de tecnología y conocimiento: implementación y evaluación de un infobanco de salud para CoRIS (Info-bank for the secondary use of data based on technology and knowledge standards: implementation and evaluation of a health info-bank for CoRIS) – SmartPITeS” (Data collection and HUF corpus construction), and PI18CIII/00019 - PI18/00890 - PI18/00981 “Arquitectura normalizada de datos clínicos para la generación de infobancos y su uso secundario en investigación: solución tecnológica (Clinical data normalized architecture for the genaration of info-banks and their secondary use in research: technological solution) – CAMAMA 4” (Data collection and HUF corpus construction) from Fondo de Investigación Sanitaria (FIS) Plan Nacional de I+D+i.es_ES
dc.language.isoenges_ES
dc.publisherBioMed Central (BMC) es_ES
dc.type.hasVersionVoRes_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectAssociation rules discoveryes_ES
dc.subjectMachine learninges_ES
dc.subjectMedical recordses_ES
dc.subjectSemi-supervised approaches_ES
dc.titleSemi-supervised incremental learning with few examples for discovering medical association ruleses_ES
dc.typejournal articlees_ES
dc.rights.licenseAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.identifier.pubmedID35073885es_ES
dc.format.volume22es_ES
dc.format.number1es_ES
dc.format.page20es_ES
dc.identifier.doi10.1186/s12911-022-01755-3es_ES
dc.contributor.funderAgencia Estatal de Investigación (España) es_ES
dc.contributor.funderUnión Europea. Fondo Europeo de Desarrollo Regional (FEDER/ERDF) es_ES
dc.contributor.funderInstituto de Salud Carlos III es_ES
dc.contributor.funderPlan Nacional de I+D+i (España) es_ES
dc.description.peerreviewedes_ES
dc.identifier.e-issn1472-6947es_ES
dc.relation.publisherversionhttps://doi.org/10.1186/s12911-022-01755-3es_ES
dc.identifier.journalBMC Medical Informatics and Decision Makinges_ES
dc.repisalud.centroISCIII::Unidad de Investigación en Telemedicina y eSaludes_ES
dc.repisalud.institucionISCIIIes_ES
dc.rights.accessRightsopen accesses_ES
dc.relation.projectFECYTinfo:eu-repo/grantAgreement/ES/PID2019-106942RB-C32es_ES
dc.relation.projectFISinfo:fis/Instituto de Salud Carlos III/Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia/Subprograma Estatal de Generación de Conocimiento/PI18-ISCIII Modalidad Proyectos de Investigacion en Salud Intramurales. (2018)/PI18CIII/00004es_ES
dc.relation.projectFISinfo:fis/Instituto de Salud Carlos III/Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia/Subprograma Estatal de Generación de Conocimiento/PI18-ISCIII Modalidad Proyectos de Investigacion en Salud Intramurales. (2018)/PI18CIII/00019es_ES
dc.relation.projectFISinfo:fis/Instituto de Salud Carlos III/Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia/Subprograma Estatal de Generación de Conocimiento/PI18 - Proyectos de investigacion en salud (AES 2018). Modalidad proyectos en salud. (2018)/PI18/00890es_ES
dc.relation.projectFISinfo:fis/Instituto de Salud Carlos III/Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia/Subprograma Estatal de Generación de Conocimiento/PI18 - Proyectos de investigacion en salud (AES 2018). Modalidad proyectos en salud. (2018)/PI18/00981es_ES


Ficheros en el ítem

Acceso Abierto
Thumbnail
Acceso Abierto
Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Este Item está sujeto a una licencia Creative Commons: Attribution-NonCommercial-NoDerivatives 4.0 Internacional