Scientific Publications
Overview
During my time as a research scholarship holder at GECAD, I actively participated in several scientific projects, namely RM4HEALTH and PROFIT, developing and co-authoring scientific articles in the areas of remote health monitoring, explainable deep learning and computer vision applications for health. These publications reflect the contribution of my work in applied research and in the development of innovative solutions in artificial intelligence for the health sector.
Research Profiles
RM4HEALTH Project Publications
A Systematic Review on Wearable-enabled Remote Health Monitoring
Publication: PROSPERO
Year: 2025
Abstract:
This systematic review investigates the application of wearable technologies for remote health monitoring, with a particular focus on their effectiveness in improving patient care. Using the PRISMA methodology, the review describes the stages of study selection, data extraction, and properties of findings. The analysis reveals a significant reliance on traditional statistical methods among the reviewed studies, with limited integration of advanced artificial intelligence techniques. Despite the potential of machine learning algorithms to improve health monitoring and predictive capabilities, their adoption remains scarce. The review emphasizes the importance of personalized feedback mechanisms in promoting patient engagement and adherence to health interventions. Furthermore, notable gap in research addressing cognitive and psychological well-being was identified, so that future studies should adopt a more holistic approach to health monitoring. The findings highlight the need for more rigorous methodologies, including scientific clinical trials, to strengthen the evidence base for the effectiveness of wearable technologies in remote health monitoring. This work aims to provide a comprehensive understanding of the current state of the art in the field and inform future research directions.
Enhancing Medication Adherence with Computer Vision
Conference: WorldCist 2025 – 13th World Conference on Information Systems and Technologies
Year: 2025
Abstract:
As the global population ages, ensuring proper medication adherence has become a critical healthcare challenge, particularly among seniors who often manage multiple chronic conditions. Medication errors, especially in this demographic, significantly contribute to hospital admissions and adverse outcomes. This paper proposes a computer vision-based approach using the YOLOv8 architecture to automate pill monitoring within a specific and controlled context. After evaluating multiple pre-trained backbones (EfficientNetV2, CSPDarknet, and others), the YOLOv8 emerged as a top performer, achieving 94.0% recall on a dataset with pills in a semi-controlled background, sourced from the literature, which closely simulates the conditions of the project in which this study is inserted. Additional tests were also performed with a less controlled dataset to verify if the trained models were capable of performing in more generic contexts, with EfficientNetV2 B2 achieving a 68.6% recall score. This research offers a significant step forward in applying AI for healthcare, providing an accessible, scalable solution for automated pill identification, particularly in supporting elderly patients with their medication regimens.
Supporting Elderly Care through an AI-driven and FHIR-based Remote Monitoring System
Conference: DCAI 2024 – 21st International Conference on Distributed Computing and Artificial Intelligence
Year: 2024
Abstract:
An increase in the elderly population has led to a growing demand for constant health care. Remote monitoring of seniors aims to provide more effective care and promote patient independence, whether they live in residential homes, or their own homes supported by a domiciliary care service. It encompasses several issues present in their lives that may benefit from being assisted and monitored remotely. There are many successful studies and products focused on one of these issues, but fewer are the study cases for a broad remote monitoring system that works as a solution for various of those topics simultaneously. This paper proposes an architecture for an intelligent health monitoring ecosystem to interact with these various aspects of the elderly’s daily life, including monitoring of vital signs, movement and medication intake, detection of falls, sleep quality analysis, access control, and patient–caregiver communication. This solution will make use of wearables and medication dispensers, and it will securely store all patient-related information into an HL7 FHIR standardized database, from where machine learning models can import data for predicting important information and generating alerts when necessary. Next steps involve the development of this proposed system and testing it with elderly volunteers living in a residential home or subscribed to its domiciliary care services.
Dissertation and PROFIT Project
An Explainable Deep Learning Architecture for the Detection of Gastrointestinal Lesions
Conference: EPIA 2025 – 23rd Portuguese Conference on Artificial Intelligence
Year: 2025
Abstract:
Gastrointestinal diseases have a growing impact on public health, often requiring timely and accurate diagnosis to prevent complications and improve patient outcomes. In this context, artificial intelligence (AI) has emerged as a promising tool to support clinicians in image-based diagnosis. This study presents the design and evaluation of an explainable deep learning system for the automatic detection and classification of gastrointestinal anomalies in colonoscopy images. Using transfer learning and convolutional neural networks, the proposed architecture incorporates a fine-tuned ResNet18 model alongside explainable AI (XAI) methods to ensure both high diagnostic performance and model transparency. The system was trained and validated using the Kvasir dataset, a clinically annotated collection of endoscopic images covering multiple gastrointestinal conditions. Experimental results show that the use of transfer learning significantly improved classification outcomes, with F1-scores exceeding 0.90 for several key categories. A web-based interface was also developed to facilitate clinical adoption, providing visual explanation tools such as heatmaps. These allow healthcare professionals to understand the basis of each prediction, promoting trust and supporting informed decision-making. Overall, the system contributes to more accurate, interpretable, and efficient diagnostic processes in the field of gastrointestinal healthcare.
