https://www.um.edu.mt/library/oar/handle/123456789/325 2026-05-28T13:22:36Z 2026-05-28T13:22:36Z Haber, Martina Montebello, Matthew Gauci, Gian Paul Zarb, Francis Borg Grima, Karen https://www.um.edu.mt/library/oar/handle/123456789/146808 2026-05-26T11:47:55Z 2026-01-01T00:00:00Z

Title: Bridging the gap between artificial intelligence and clinical readiness in endometriosis diagnosis : a systematic review Authors: Haber, Martina; Montebello, Matthew; Gauci, Gian Paul; Zarb, Francis; Borg Grima, Karen Abstract: Objective: To systematically evaluate the methodological quality and diagnostic performance of artificial intelligence (AI) applications, specifically machine learning (ML) and deep learning (DL), in the diagnosis of endometriosis through imaging and clinical symptomology.; Data Sources: A systematic search was conducted across seven databases for studies published between 2015 and 2025; Method of Study Selection: Inclusion criteria focused on primary research utilizing AI for endometriosis diagnosis via MRI, ultrasound, or patient-reported symptoms. Methodological quality was appraised using the QUADAS-2 tool. Study selection adhered to a double-blinded protocol to minimize selection bias. Clinical and methodological conflicts were addressed by a Professor of Radiography, while technical AI complexities were adjudicated by a Professor of Artificial Intelligence.; Tabulations, Integration and Results: AI models demonstrated high technical efficacy, with imaging-based algorithms achieving diagnostic accuracies up to 94.32% (MRI) and AUCs of 0.90 (Ultrasound). Symptom-based models reported accuracies reaching 95.95%, utilizing classifiers such as Random Forest and XGBoost. However, quality appraisal revealed significant clinical heterogeneity and systemic vulnerabilities. Spectrum bias was prevalent, as most models were trained on advanced-stage cohorts, limiting applicability for early-stage detection. Furthermore, symptom-based models often relied on self-reported data from social media, introducing significant selection and verification bias.; Conclusion: While AI demonstrates high potential for automating endometriosis detection, current literature is constrained by retrospective designs and narrow patient selection. To move from experimental prototypes to clinical screening tools, future research must prioritize prospective validation in undifferentiated populations using a combination of diagnostic reference methods. Journal of Minimally Invasive Gynecology (2026) 00, 1−9. © 2026 Published by Elsevier Inc. on behalf of AAGL.

2026-01-01T00:00:00Z Flood, Terry O Neill, A. Oliveira, Celeste M. Barbosa, Barbara Soares, Ana Luísa Muscat, Kyle Guille, Sharon McClure, Patricia Hughes, Ciara M. McFadden, Sonyia L. https://www.um.edu.mt/library/oar/handle/123456789/146250 2026-05-08T08:19:24Z 2023-01-01T00:00:00Z

Title: Patients’ perspectives of the skills and competencies of therapy radiographers/radiation therapists (TRs/RTTs) in the UK, Portugal and Malta ; a qualitative study from the SAFE Europe project Authors: Flood, Terry; O Neill, A.; Oliveira, Celeste M.; Barbosa, Barbara; Soares, Ana Luísa; Muscat, Kyle; Guille, Sharon; McClure, Patricia; Hughes, Ciara M.; McFadden, Sonyia L. Abstract: Introduction: The role of the Therapy Radiographer/Radiation Therapist (TR/RTT) is to provide radiotherapy to patients with a cancer diagnosis. This includes, not only administration of treatment, but also management of side-effects and provision of support/care. Despite this role being consistent throughout Europe, there is currently no standardisation of education for TRs/RTTs. The SAFE EUROPE project aims to standardize TR/RTT education to enable ‘safe and free exchange’ of TRs/RTTs across Europe. Consequently, this study aims to explore patients' perspectives regarding the current skills and competencies of TRs/RTTs.; Methods: From May 2021 to February 2022, semi-structured interviews were conducted with patients who had recently received radiotherapy in the UK, Malta and Portugal. Ethical approval for this study was granted by the NHS Research Ethics Committee with additional local approvals obtained.; Results: Forty-eight participants from the UK (n = 18), Portugal (n = 19), and Malta (n = 11) completed interviews. Participants described high satisfaction with TRs'/RTTs’ competence and skills in all three countries. The main theme arising from the analysis was the importance of trust building with TRs/RTTs. Six factors were identified as influencing levels of trust: communication; side-effect management; team consistency; relational skills; patient dignity; and competence. A small number of patients reported feeling rushed and not having their physical and emotional needs met by TRs/RTTs.; Conclusion: This multicentre study demonstrated that patients perceive TRs/RTTs in the UK, Malta and Portugal as highly competent and skilled. Practical recommendations are provided to address identified deficits in practice, which can be addressed through adaptation of TR/RTT education/training and clinical practice.; Implications for practice: Recommendations arising from this study are important to ensure that TRs/RTTs have transferable skills that provide consistently high quality care to patients throughout Europe.

2023-01-01T00:00:00Z Tomaselli, Gianpaolo Macassa, Gloria Borg, Karen Maria Couto, Jose Guilherme Portelli, Jonathan L. Borg Grima, Karen Buttigieg, Sandra C. https://www.um.edu.mt/library/oar/handle/123456789/145456 2026-04-10T07:47:11Z 2026-01-01T00:00:00Z

Title: Rethinking hospital sustainability : integrating circular and green economy principles within strategic corporate social responsibility and management frameworks Authors: Tomaselli, Gianpaolo; Macassa, Gloria; Borg, Karen Maria; Couto, Jose Guilherme; Portelli, Jonathan L.; Borg Grima, Karen; Buttigieg, Sandra C. Abstract: Hospitals play a central role in promoting health and well-being, yet they are also among the most resource-intensive institutions, contributing significantly to environmental degradation through high energy and water consumption, extensive waste generation, and reliance on single-use materials. This conceptual paper explores how principles of the circular economy and green economy can be integrated into hospital operations through a strategic Corporate Social Responsibility (CSR) framework, reframing sustainability as a strategic management issue rather than a compliance-driven activity. Drawing on environmental economics, sustainability studies, and institutional theory, the paper develops an integrated conceptual model structured around the environmental, social, and economic pillars of sustainability. Within this framework, four interconnected operational domains are identified: waste management and circular practices, energy consumption and renewable integration, sustainable procurement and circular supply chains, and economic and policy incentives. The social dimension explicitly encompasses healthcare staff and patients, addressing issues of workforce well-being, health education, safety, quality of life, and equitable care delivery. This advances theory by positioning strategic CSR as a function of circular and green economy, yielding a new model for hospitals, S-CSR = f(CE, GE). The paper also examines institutional and cultural barriers that constrain sustainability implementation and highlights the role of strategic leadership, governance, and system-wide innovation in overcoming these challenges. While not empirical, the study provides a theoretical foundation to inform future research, policy development, and strategic decision-making aimed at advancing sustainable, low-carbon, and resilient healthcare systems.

2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/145226 2026-05-26T10:30:53Z 2025-01-01T00:00:00Z

Title: Beyond the bleeding : predicting pregnancy outcomes after threatened miscarriage Abstract: This three-phase research project examined pregnancy outcomes following first-trimester threatened miscarriage (TM). Phase 1 (retrospective epidemiological analysis) established local prevalence and outcome patterns in Malta for 2019. Phase 2 (scoping review) mapped existing ultrasound and biochemical markers for predicting miscarriage. Phase 3 (prospective case-control study) developed and validated predictive models using multivariate logistic regression (AUC 0.89 on test data) and Random Forest (AUC 0.97 on test data). Key predictive markers identified were progesterone, mean gestational sac diameter (MGSD), β-hCG, crown-rump length (CRL), cervical length, maternal age (35–46 years), fetal heart rate (FHR), and sFlt-1:PlGF ratio. The study provides the first Malta-specific data and a clinically usable algorithm to improve risk stratification and counselling for women experiencing early-pregnancy bleeding.

2025-01-01T00:00:00Z