Teresa Magalhães

Prof. Teresa Magalhães

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 April 2023 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
MOMariana Oliveira
Mariana Oliveira
JSJoana Seringa
Joana Seringa
FPFausto José Pinto
Fausto José Pinto
Roberto HenriquesRoberto Henriques
Roberto Henriques
TMTeresa Magalhães
Teresa Magalhães
Background: Acute Myocardial Infarction (AMI) is the leading cause of death in Portugal and globally. The present investigation created a model based on machine learning for predictive analysis of mortality in patients with AMI upon admission, using different variables to analyse their impact on predictive models. Methods: Three experiments were built for mortality in AMI in a Portuguese hospital between 2013 and 2015 using various machine learning techniques. The three experiments differed in the number and type of variables used. We used a discharged patients’ episodes database, including administrative data, laboratory data, and cardiac and physiologic test results, whose primary diagnosis was AMI. Results: Results show that for Experiment 1, Stochastic Gradient Descent was more suitable than the other classification models, with a classification accuracy of 80%, a recall of 77%, and a discriminatory capacity with an AUC of 79%. Adding new variables to the models increased AUC in Experiment 2 to 81% for the Support Vector Machine method. In Experiment 3, we obtained an AUC, in Stochastic Gradient Descent, of 88% and a recall of 80%. These results were obtained when applying feature selection and the SMOTE technique to overcome imbalanced data. Conclusions: Our results show that the introduction of new variables, namely laboratory data, impacts the performance of the methods, reinforcing the premise that no single approach is adapted to all situations regarding AMI mortality prediction. Instead, they must be selected, considering the context and the information available. Integrating Artificial Intelligence (AI) and machine learning with clinical decision-making can transform care, making clinical practice more efficient, faster, personalised, and effective. AI emerges as an alternative to traditional models since it has the potential to explore large amounts of information automatically and systematically.

DCDulce Cachata
Dulce Cachata
MCMónica Costa
Mónica Costa
TMTeresa Magalhães
Teresa Magalhães
FGFilomena Gaspar
Filomena Gaspar
The adoption of health technologies is occurring on an unprecedented scale, with enormous potential to improve the health of populations. In this context, information technology (IT) in nursing has emerged with a focus on quality and safety of care for the benefit of the patient. There is insufficient reliable evidence demonstrating how the integration of IT in nursing care influences methodologies for managing and organizing care in terms of structure and care practice, justifying a scoping review that synthesizes the knowledge produced so far. Online databases were used to identify papers published in 2012–2023, from which we selected nine publications that used information technology in the nursing care processes. The participants were hospital nurses and nurse managers. The results show that the integration of IT in healthcare organizations impacts the management and organization of nursing care, and changes in structure, process reorganization, management, training, and the development of nurses’ skills. To minimize this impact, the organizational structure must be prepared for a cultural change, with well-defined and communicated policies and procedures, and strong leadership. Within the teams, the importance of process reorganization, continuous training, and skill development emerges, thus enhancing the integration of IT into practice environments in conjunction with care.

29 October 2015 in Journal of Medical Systems
Verified
Journal Article
Closed access
PDF file
TMTeresa Magalhães
Teresa Magalhães
SLSílvia Lopes
Sílvia Lopes
JGJoão Gomes
João Gomes
FSFilipe Seixo
Filipe Seixo

20 January 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JSJoana Seringa
Joana Seringa
AHAnna Hirata
Anna Hirata
Universidade Nova de Lisboa / Escola Nacional de Saúde PúblicaUniversidade Nova de Lisboa / Escola Nacional de Saúde Pública
Universidade Nova de Lisboa / Escola Nacional de Saúde Pública
RSRui Santana
Rui Santana
TMTeresa Magalhães
Teresa Magalhães
Background: Heart failure (HF) is a significant global health problem, affecting approximately 64.34 million people worldwide. The worsening of HF, also known as HF decompensation, is a major factor behind hospitalizations, contributing to substantial health care costs related to this condition. Objective: This study aimed to explore the perspectives of health care professionals and data scientists regarding the relevance, challenges, and potential benefits of using machine learning (ML) models to predict decompensation from patients with HF. Methods: A total of 13 individual, semistructured, qualitative interviews were conducted in Portugal between October 31, 2022, and June 23, 2023. Participants represented different health care specialties and were selected from different contexts and regions of the country to ensure a comprehensive understanding of the topic. Data saturation was determined as the point at which no new themes emerged from participants’ perspectives, ensuring a sufficient sample size for analysis. The interviews were audio recorded, transcribed, and analyzed using MAXQDA (VERBI Software GmbH) through a reflexive thematic analysis. Two researchers (JS and AH) coded the interviews to ensure the consistency of the codes. Ethical approval was granted by the NOVA National School of Public Health ethics committee (CEENSP 14/2022), and informed consent was obtained from all participants. Results: The participants recognized the potential benefits of ML models for early detection, risk stratification, and personalized care of patients with HF. The importance of selecting appropriate variables for model development, such as rapid weight gain and symptoms, was emphasized. The use of wearables for recording vital signs was considered necessary, although challenges related to adoption among older patients were identified. Risk stratification emerged as a crucial aspect, with the model needing to identify patients at high-, medium-, and low-risk levels. Participants emphasized the need for a response model involving health care professionals to validate ML-generated alerts and determine appropriate interventions. Conclusions: The study’s findings highlight ML models’ potential benefits and challenges for predicting HF decompensation. The relevance of ML models for improving patient outcomes, reducing health care costs, and promoting patient engagement in disease management is highlighted. Adequate variable selection, risk stratification, and response models were identified as essential components for the effective implementation of ML models in health care. In addition, the study identified technical, regulatory and ethical, and adoption and acceptance challenges that need to be overcome for the successful integration of ML models into clinical workflows. Interpretation of the findings suggests that future research should focus on more extensive and diverse samples, incorporate the patient perspective, and explore the impact of ML models on patient outcomes and personalized care in HF management. Incorporation of this study’s findings into practice is expected to contribute to developing and implementing ML-based predictive models that positively impact HF management.

23 January 2025 in The International Journal of Health Planning and Management
Verified
Journal Article
Open access
GVGeorge Valiotis
George Valiotis
SBSandra C. Buttigieg
Sandra C. Buttigieg
ACAmerico Cicchetti
Americo Cicchetti
RDRui Dang
Rui Dang
NJNabil Jamshed
Nabil Jamshed
FMFederica Margheri
Federica Margheri
The practice of healthcare management is essential for the efficient operation of health services, encompassing leadership, management, and direction within healthcare organisations. ‘Health management’ extends beyond healthcare management by integrating principles of public health and health policy. As health management is commonly practised but not cohesively recognised, the European Health Management Association (EHMA) conducted this study to develop a cohesive definition of health management. Developed through a qualitative methodology comprising focus group discussions and validation through quantitative expert interviews, this study proposed a holistic definition of health management, incorporating social, environmental and economic determinants of health, cross‐sector collaboration, and the ‘One Health’ approach. The publication of this unified definition has important implications for professional training, policy development, and health outcomes. It provides a foundational framework for curricula, informs precise policy formulation, and promotes excellence through health service delivery that reflects efficiency, sustainability, and equity.

5 January 2026 in Frontiers in Public Health
Verified
Journal Article
Open access
PDF file
JFJoana Paias Ferreira
Joana Paias Ferreira
TMTeresa Magalhães
Teresa Magalhães
Background: The digital transformation of healthcare is reshaping clinical practice, healthcare management, patient-provider interactions, and traditional public health fields. These digital tools enhance safety, quality of care and efficacy, while also supporting the shift from cure to prevention, empowering patients, and promoting overall efficiency of healthcare management and delivery. In healthcare, digital competence remains inconsistently defined and its assessment is often limited by conflation with narrower constructs such as digital literacy. The aim of this scoping review is to identify instruments that capture multiple dimensions of digital health competencies, analyse their scope and reported psychometric properties. This provides a clear view of the essential digital competencies in healthcare, critical for improving patient care, development of targeted education and workforce strategies, and advancing public health functions, contributing to a more equitable and sustainable healthcare systems in the digital era. Methods: A scoping review was conducted according to the JBI Manual for Evidence Synthesis. Three databases (PubMed, Scopus, Web of Science) were searched for studies published from 2015 to June 2025, using established criteria. Identified instruments were mapped by the digital area they apply, healthcare sample and setting, dimensions of competencies assessed and number of items. Further analysis followed two frameworks for questionnaire development (ESS Handbook) and measurement properties (COSMIN). Results: Of the 441 identified studies, 19 met the inclusion criteria. Included studies predominantly used mixed professional samples; among single-group studies, nurses were most often targeted, and hospital settings dominated, with the public health field rarely represented. Most instruments adopted a generalist scope rather than focusing on a specific digital health area. Psychometric reporting was limited, with only three studies offering comprehensive psychometric validation. One instrument introduced a new perspective by explicitly assessing factors influencing the adoption of competencies. Conclusion: Interest in assessing digital health competencies has grown, and the field is continually evolving; however, psychometrically validated instruments remain scarce. Mapping multidimensional instruments reveals recurring core dimensions and adoption-related factors, providing a clear foundation for more specific, targeted, and practice-aligned education and training, and a generalizable core for a standardized, digital public health competency framework for the multi-professional public health workforce.