Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by LIAAD

2023

Intra-hospital virtual communities and wellbeing of cancer patients: Impact of features on healthcare relationships

Authors
Silva, RJ; Pires, PB; Delgado, C; Santos, JD;

Publication
Effective Digital Marketing for Improving Society Behavior Toward DEI and SDGs

Abstract
The use of social media in health is emerging as a means of bringing the various actors together with several benefits. In the specific case of cancer disease, these tools can help patients to improve their psychological well-being and their outcomes. As cancer is the cause of a quarter of deaths in Portugal, it is a pressing issue to understand which tools and information both patients and health professionals find most useful to build effective health social media. It was observed that there is a latent need for an oncology social environment, allowing greater well-being for patients and strengthening their relationship with health professionals and institutions, constituting an asset to the services provided. This chapter fills a gap in the bibliography by bringing together the views of both patients and health professionals from several areas, in close collaboration with the Francisco Gentil Portuguese Oncology Institute of Porto, E.P.E. © 2024, IGI Global. All rights reserved.

2023

Curbing Dropout: Predictive Analytics at the University of Porto

Authors
Blanquet, L; Grilo, J; Strecht, P; Camanho, A;

Publication
Atas da Conferencia da Associacao Portuguesa de Sistemas de Informacao

Abstract
This study explores data mining techniques for predicting student dropout in higher education. The research compares different methodological approaches, including alternative algorithms and variations in model specifications. Additionally, we examine the impact of employing either a single model for all university programs or separate models per program. The performance of models with students grouped according to their position on the program study plan was also tested. The training datasets were explored with varying time series lengths (2, 4, 6, and 8 years) and the experiments use academic data from the University of Porto, spanning the academic years from 2012 to 2022. The algorithm that yielded the best results was XGBoost. The best predictions were obtained with models trained with two years of data, both with separate models for each program and with a single model. The findings highlight the potential of data mining approaches in predicting student dropout, offering valuable insights for higher education institutions aiming to improve student retention and success. © 2023 Associacao Portuguesa de Sistemas de Informacao. All rights reserved.

2023

STUDD: a student-teacher method for unsupervised concept drift detection

Authors
Cerqueira, V; Gomes, HM; Bifet, A; Torgo, L;

Publication
Mach. Learn.

Abstract

2023

Automated imbalanced classification via layered learning

Authors
Cerqueira, V; Torgo, L; Branco, P; Bellinger, C;

Publication
Mach. Learn.

Abstract

2023

From the first to the fourth critical period of COVID-19: what has changed in nursing practice environments in hospital settings?

Authors
Ribeiro, OMPL; Cardoso, MF; Trindade, LD; da Rocha, CG; Teles, PJFC; Pereira, S; Coimbra, V; Ribeiro, MP; Reis, A; Faria, ADA; da Silva, JMAV; Leite, P; Barros, S; Sousa, C;

Publication
BMC NURSING

Abstract
BackgroundThe COVID-19 pandemic reinforced the need to invest in nursing practice environments and health institutions were led to implement several changes. In this sense, this study aimed to analyze the impact of the changes that occurred in nursing practice environments between the first and fourth critical periods of the pandemic.MethodsQuantitative, observational study, conducted in a University Hospital, with the participation of 713 registered nurses. Data were collected through a questionnaire with sociodemographic and professional characterization and the Scale for the Environments Evaluation of Professional Nursing Practice, applied at two different points in time: from 1 to 30 June 2020 and from 15 August to 15 September 2021. Data were processed using descriptive and inferential statistics.ResultsOverall, the pandemic had a positive impact on nursing practice environments. However, the Process component remained favourable to quality of care, while the Structure and Outcome components only moderately favourable. Nurses working in Medicine Department services showed lower scores in several dimensions of the Structure, Process and Outcome components. On the other hand, nurses working in areas caring for patients with COVID-19 showed higher scores in several dimensions of the Structure, Process and Outcome components.ConclusionsThe pandemic had a positive impact on various dimensions of nursing practice environments, which denotes that regardless of the adversities and moments of crisis that may arise, investment in work environments will have positive repercussions.However, more investment is needed in Medicine Department services, which have historically been characterised by high workloads and structural conditions that make it difficult to promote positive and sustainable workplaces.

2023

Impact of Fire Recurrence and Induced Water Stress on Seed Germination and Root Mitotic Cell Cycle of Pinus pinaster Aiton

Authors
Ribeiro, S; Gaspar, MJ; Lima-Brito, J; Fonseca, T; Soares, P; Cerveira, A; Fernandes, PM; Louzada, J; Carvalho, A;

Publication
FORESTS

Abstract
Climate change will increase the frequency of drought, heat waves, and wildfires. We intended to analyse how fire recurrence and/or induced water stress can affect seed germination and root cell division in Pinus pinaster Aiton. Seeds from stands with no prior fire history and from post-fire regeneration (in areas burnt once, twice, and thrice) in northern Portugal were germinated in distilled water (control) and polyethylene glycol (PEG) to simulate water stress for four weeks, followed by a recovery period. Roots were analysed cytogenetically. The germination index of the Pinus pinaster seeds was not statistically influenced by the induction of osmotic stress, nor by the fire recurrence of the stands. The mean germination time (MGT) was 10-29 days and 1-36 days for the stress and recovery periods, respectively, and increased with PEG concentration. The 20% PEG treatment inhibited root growth after germination. The 10% PEG treatment induced a high frequency of cytogenetic anomalies, mostly in the sites which experienced fire exposure. While fire recurrence did not affect the germination rate, it seemed to reduce the water stress response, negatively impacting cell division and impair root growth.

  • 36
  • 429