1 November 2017 in Geoderma
ASArturo Sánchez–González
1 September 2019 in Computational Statistics & Data Analysis
12 March 2021 in Environmental Monitoring and Assessment
MHManuel Hernández-Quiroz
19 July 2022 in Informatics in Medicine Unlocked
Understanding SARS-CoV-2 infection that causes COVID-19 disease among the population was fundamental to determine the risk factors associated with severe cases or even death. Amidst the study of the pandemic, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied in many areas such as biomedicine. Using a dataset from the Mexican Ministry of Health, we performed a multiclass classification scheme for the detection of risks in COVID-19 patients and implemented three Machine Learning algorithms achieving the following accuracy measures: Random Forest (89.86%), GBM (89.37%) XGBoost (89.97%). The key findings are the identification of relevant components associated with different severities of COVID-19 disease. Among these factors, we found sex, age, days elapsed from the beginning of symptoms, symptoms such as dyspnea and polypnea; and other comorbidities such as diabetes and hypertension. This setting allows us to establish predicting algorithms to model the risk that an individual or a specific group of people face after contracting COVID-19 and the factors associated with developing complications or receiving appropriate treatment.
22 May 2023 in Journal of Chemical Education
GNGeorgina Nieto-Castañeda
GAGiovanni Aldana-Gutiérrez
Giovanni Aldana-Gutiérrez
31 October 2023 in Revista Iberoamericana de Evaluación Educativa
The purpose of the study was to describe the trajectories of the score averages obtained on the teaching evaluations by the residents in a period of eight years. We analyzed the statistical evidence that demonstrates a positive effect trend of teaching evaluation on the score averages. Of 2,751 professors, 1,031 taught courses in three or more annual cycles. The averages were obtained from the teaching evaluation questionnaire responded by medical residents. To explore the possibility of clustering of longitudinal data with similar trajectory patterns, growth mixture models (GMM) with latent classes were used, the number of latent classes was chosen considering criteria based on likelihood (AIC, BIC) and entropy. Over the years, the averages were on the rise, except for the 2019-2020 cycle where a downward trend can be observed which recovers in subsequent years. The growth model found two latent classes, one with a growing trend that grouped 89% of teachers, and another decreasing trend of the remaining 11%. The averages decreased for women and increased for tenured professors. The results suggest that teacher evaluation can have positive effects over time, since the score given by residents when evaluating their teachers tends to increase.