Browsing by Subject "Decision tree"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Open Access
    Identification of predictors of sarcopenia in older adults using machine learning: English Longitudinal Study of Ageing
    (MDPI, 2024-11-12) Pavón Pulido, Nieves; Domínguez, Ligia; Blasco García, Jesús Damián; Veronese, Nicola; Lucas Ochoa, Ana María; Fernández Villalba, Emiliano; González Cuello, Ana María; Barbagallo, Mario; Herrero Ezquerro, María Trinidad; GOING FWD Investigators; Medicina Interna; Facultades de la UMU::Facultad de Medicina
    Background: After its introduction in the ICD-10-CM in 2016, sarcopenia is a condition widely considered to be a medical disease with important consequences for the elderly. Considering its high prevalence in older adults and its detrimental effects on health, it is essential to identify its risk factors to inform targeted interventions. Methods: Taking data from wave 2 of the ELSA, using ML-based methods, this study investigates which factors are significantly associated with sarcopenia. The Minimum Redundancy Maximum Relevance algorithm has been used to allow for an optimal set of features that could predict the dependent variable. Such a feature is the input of a ML-based prediction model, trained and validated to predict the risk of developing or not developing a disease. Results: The presented methods are suitable to identify the risk of acquired sarcopenia. Age and other relevant features related with dementia and musculoskeletal conditions agree with previous knowledge about sarcopenia. The present classifier has an excellent performance since the “true positive rate” is 0.81 and the low “false positive rate” is 0.26. Conclusions: There is a high prevalence of sarcopenia in elderly people, with age and the presence of dementia and musculoskeletal conditions being strong predictors. The new proposed approach paves the path to test the prediction of the incidence of sarcopenia in older adults.202
  • Thumbnail Image
    Publication
    Open Access
    Teaching quality: the satisfaction of university students with their professors
    (Editum, Servicio de Publicaciones, 2020-04-09) Cerro, Jesús Santos del; Ruiz Esteban, Cecilia; Psicología Evolutiva y de la Educación
    Abstract: For almost a century now, the concern of universities about student satisfaction with teaching quality has been increasing. A literature review has enabled the attributes of quality teaching to be classified into three main types: pedagogical, generic, and disciplinary. The aim of this paper is to identify the variables that, in the opinion of students, most influence student satisfaction regarding teaching quality. A total of 476 undergraduate students participated from Business Administration and Management of the University of Castilla-La Mancha (Spain). An ad hoc questionnaire was used to assess student satisfaction with teaching. Parametric (Logistic Regression Analysis) and non-parametric (Decision Tree) models were used. Our data indicate that if the professor explains the subject clearly, is concerned to find out whether the explanations have been understood, and carefully prepares the classes; the teaching-quality assessment will be very satisfactory. The identification of the attributes of quality teaching will enable universities to draw up initial and ongoing training plans for their teaching staff, bearing in mind the crucial role played by generic, pedagogical, and disciplinary competences in professor-student interaction.