Matilde Pos-de-Mina Pato
@isel.pt
Department of Electronical Engineering, Telecommunications and Computers (DEETC)
Instituto Superior de Engenharia de Lisboa
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Engineering, Information Systems, Health Informatics, Biomedical Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Matilde Pato, Márcia Barros, and Francisco M. Couto
Association for Computing Machinery (ACM)
The generation of biomedical data is of such magnitude that its retrieval and analysis have posed several challenges. A survey of recommender system (RS) approaches in biomedical fields is provided in this analysis, along with a discussion of existing challenges related to large-scale biomedical information retrieval systems. We collect original studies, identify entities and models, and discuss how knowledge graphs (KGs) can improve results. As a result, most of the papers used model-based collaborative filtering algorithms, most of the available datasets did not follow the standard format < user, item, rating >, and regarding qualitative evaluations of RSs use mainly classification metrics. Finally, we have assembled and coded a unique dataset of 60 papers — Sur-RS4BioT, available for download at DOI:10.34740/kaggle/ds/2346894
Pedro Santos, Matilde Pato, Nuno Datia, José Sobral, Noel Leitão, Manuel Ramos Ferreira, and Nuno Gomes
MDPI AG
Asset management involves the coordinated activities of an organisation to derive value from assets, which may include physical assets. It encompasses activities related to design, construction, installation, operation, maintenance, renewal, and asset disposal. Asset management ensures the coordination of all activities, resources, and data related to physical assets. Recording and monitoring all maintenance activities is a key part of asset management, often done using work orders (WOs). Technicians typically create WOs using “free text”, which can result in missing or ungrammatical words, making it difficult to identify trends and analyse information. To standardise the terminology used for the same asset maintenance operation, this paper proposes a method that suggests words to technicians as they complete WOs. The word suggestion algorithm is based on past maintenance records, and a Bayesian network-based recommender system adapts to present needs verified by technicians using implicit user feedback. Implementing this system aims to normalise the terms used by technicians when filling in a WO. The corpus for this work comes from asset management records collected in a health facility in Portugal operated by a private company.
João Pedro Vitorino, José Simão, Nuno Datia, and Matilde Pato
MDPI AG
This paper presents IRONEDGE, an architectural framework that can be used in different edge Stream Processing solutions for “Smart Infrastructure” scenarios, on a case-by-case basis. The architectural framework identifies the common components that any such solution should implement and a generic processing pipeline. In particular, the framework is considered in the context of a study case regarding Internet of Things (IoT) devices to be attached to rolling stock in a railway. A lack of computation and storage resources available in edge devices and infrequent network connectivity are not often seen in the existing literature, but were considered in this paper. Two distinct implementations of IRONEDGE were considered and tested. One, identified as Apache Kafka with Kafka Connect (K0-WC), uses Kafka Connect to pass messages from MQ Telemetry Transport (MQTT) to Apache Kafka. The second scenario, identified as Apache Kafka with No Kafka Connect (K1-NC), allows Apache Storm to consume messages directly. When the data rate increased, K0-WC showed low throughput resulting from high losses, whereas K1-NC displayed an increase in throughput, but did not match the input rate for the Data Reports. The results showed that the framework can be used for defining new solutions for edge Stream Processing scenarios and identified a reference implementation for the considered study case. In future work, the authors propose to extend the evaluation of the architectural variation of K1-NC.
Nuno Gomes, Matilde Pato, André Ribeiro Lourenço, and Nuno Datia
MDPI AG
Mental illness, whether it is medically diagnosed or undiagnosed, affects a large proportion of the population. It is one of the causes of extensive disability, and f not properly treated, it can lead to severe emotional, behavioral, and physical health problems. In most mental health research studies, the focus is on treatment, but fewer resources are focused on technical solutions to mental health issues. The present paper carried out a systematic review of available literature using PRISMA guidelines to address various monitoring solutions in mental health through the use of wearable sensors. Wearable sensors can offer several advantages over traditional methods of mental health assessment, including convenience, cost-effectiveness, and the ability to capture data in real-world settings. Their ability to collect data related to anxiety and stress levels, as well as panic attacks, is discussed. The available sensors on the market are described, as well as their success in providing data that can be correlated with the aforementioned health issues. The current wearable landscape is quite dynamic, and the current offerings have enough quality to deliver meaningful data targeted for machine learning algorithms. The results indicate that mental health monitoring is feasible.
Matilde Pato, Ricardo Eleutério, Raquel C. Conceição, and Daniela M. Godinho
MDPI AG
Breast cancer is the most common and the fifth deadliest cancer worldwide. In more advanced stages of cancer, cancer cells metastasize through lymphatic and blood vessels. Currently there is no satisfactory neoadjuvant (i.e., preoperative) diagnosis to assess whether cancer has spread to neighboring Axillary Lymph Nodes (ALN). This paper addresses the use of radar Microwave Imaging (MWI) to detect and determine whether ALNs have been metastasized, presenting an analysis of the performance of different artifact removal and beamformer algorithms in distinct anatomical scenarios. We assess distinct axillary region models and the effect of varying the shape of the skin, muscle and subcutaneous adipose tissue layers on single ALN detection. We also study multiple ALN detection and contrast between healthy and metastasized ALNs. We propose a new beamformer algorithm denominated Channel-Ranked Delay-Multiply-And-Sum (CR-DMAS), which allows the successful detection of ALNs in order to achieve better Signal-to-Clutter Ratio, e.g., with the muscle layer up to 3.07 dB, a Signal-to-Mean Ratio of up to 20.78 dB and a Location Error of 1.58 mm. In multiple target detection, CR-DMAS outperformed other well established beamformers used in the context of breast MWI. Overall, this work provides new insights into the performance of algorithms in axillary MWI.
Nuno Gomes, Matilde Pato, André Lourenço, Renato Marcelo, Pedro Santos, and Nuno Datia
IEEE
Anxiety disorders refer to mental health conditions characterized by excessive and persistent worry, fear or dread, which can interfere with daily life. These disorders are pervasive worldwide but can be treated with psychotherapy, medication, or both. Detecting them in time is key to avoid further severe development after an initial crisis. In this paper, we present a solution based on self-monitoring, using wearables, smartphones and Machine Learning (ML) to assess users' anxiety and panic levels. This is the first paper to embrace and present a visualisation system for mental health focused on patients. User studies support the solution's quality. With this system, patients are empowered to control their situation better, helping the medical staff to get more insight into when and where a crisis occurs.
Pedro Santos, Nuno Datia, Matilde Pato, José Sobral, Nuno Gomes, Noel Leitão, and Manuel R. Ferreira
IEEE
In the field of asset management, a Work Order refers to a document that outlines the necessary steps to carry out a maintenance operation on a specific physical asset. The text on this Work orders providing details about the problem and the actions required are open-ended, not normalized, and Technician’ dependant, presenting challenges for automating asset management Work Order processing. To address the issue of automating the analysis of Work Orders, Natural Language Processing techniques are employed to process the content of these documents. The aim is to identify and extract relevant information related to actions and components within the sentences. This paper presents the Reliability Centred Maintenance for Assets solution, which utilizes a semi-automatic, human-in-the-loop approach to determine a standardised and condensed set of actions and components. The results indicate a significant increase in the number of annotations, reaching a ratio of 1:14. By implementing this solution, the manual workload associated with analysing Work Orders can be reduced, thereby improving decision support and analytical processing of the data contained within these documents.
Joao Vaz, Nuno Datia, Matilde Pato, and Joao Moura Pires
IEEE
Road traffic inside cities is responsible for noise and pollution, that causes health problems, fuel consumption and waste of time in jams. Mitigation solutions are usually used to soften the impact of this problem in most cities. In particular, the city of Lisbon has taken measures to reduce pollution by closing areas of the city to the most polluting cars - the zero emission zones. However, the city still lacks visual analytics support for traffic decisions in real-time. In this paper we present a traffic flow indicator that can indicate the road traffic fluidity inside a region of interest for a given time frame, and integrated it into a interactive dashboard supported by a predictive model. With this solution, decision makers can analyse historical data and predict short-term traffic behaviour.
Pedro Santos, Nuno Datia, Matilde Pato, and Jose Sobral
IEEE
Asset management is a branch of facilities management that is responsible for the operation and maintenance of assets. The most common means of managing assets and their life-cycle is through requests and work orders. A request is used to report an occurrence that is detected either by a sensory device, a technician, or non-technical personnel; they are used to pointing out that something is wrong in a given asset, and needs appropriate attention. Depending on the problem, a request can give rise to a work order if the solution is not trivial. Work orders consist in technical reports that specify the asset that needs intervention and has the details about the work to be done or, in the case that the work is unknown from the start, the characteristics of the malfunctioning. Work orders contain a set of words, free text, that are not restricted from a fixed set of vocabulary, making it difficult to automatically analyse them. In this paper, we discuss the application of modern Natural Language Processing techniques to process the work order's description, while presenting a comparison between two Word Embedding models - Word2Vec and Fasttext- through semantic similarity tests between the encoded words, and a visualisation of the vector space through dimensionality reduction of the encoded vectors. The results show a better performance of the Fasttext approach, considering the semantics of the results.
Nuno Datia, M. P. M. Pato, Ruben Taborda, and João Moura Pires
Springer International Publishing
Marcia Barros, Francisco M. Couto, Matilde Pato, and Pedro Ruas
ACM
Recommender systems (RS) have been successfully explored in a vast number of domains, e.g. movies and tv shows, music, or e-commerce. In these domains we have a large number of datasets freely available for testing and evaluating new recommender algorithms. For example, Movielens and Netflix datasets for movies, Spotify for music, and Amazon for e-commerce, which translates into a large number of algorithms applied to these fields. In scientific fields, such as Health and Chemistry, standard and open access datasets with the information about the preferences of the users are scarce. First, it is important to understand the application domain, i.e. "what the recommended item is". Second, who are the end users: researchers, pharmacists, clinicians or policy makers. Third, the availability of data. Thus, if we wish to develop an algorithm for recommending scientific items, we do not have access to datasets with information about the past preferences of a group of users. Given this limitation, we developed a methodology, called LIBRETTI - LIterature Based RecommEndaTion of scienTific Items, whose goal is the creation of datasets, related with scientific fields. These datasets are created based on the major resource of knowledge that Science has: scientific literature. We consider the users as the authors of the publications, the items as the scientific entities (for example chemical compounds or diseases), and the ratings as the number of publications an author wrote about an entity. In this tutorial we will approach state-of-the-art recommender systems in scientific fields, explain what is Named Entity Recognition/Linking (NER/NEL) in research literature, and to demonstrate how to create a dataset for recommending drugs and diseases through research literature related to COVID-19. Our goal is to spread the use of LIBRETTI methodology in order to help in the development of recommender algorithms in scientific fields. These datasets are created based on the major resource of knowledge that Science has: scientific literature. We consider the users as the authors of the publications, the items as the scientific entities (for example chemical compounds or diseases), and the ratings as the number of publications an author wrote about an entity. In this tutorial we will approach state-of-the-art recommender systems in scientific fields, explain what is Named Entity Recognition/Linking (NER/NEL) in research literature, and to demonstrate how to create a dataset for recommending drugs and diseases through research literature related to COVID-19. Our goal is to spread the use of LIBRETTI methodology in order to help in the development of recommender algorithms in scientific fields. More info about the tutorial at https://lasigebiotm.github.io/RecSys.Scifi/.
Ruben Taborda, Nuno Datia, M.P.M. Pato, and Joao Moura Pires
IEEE
Air quality is monitored using data recollected using fixed selected stations in a region, generally a city. Such approach does not support a fine-grained comprehension about the air quality, namely, in areas distant from the collector's stations, specially in residential urban places. In this paper, we describe a platform that will provide to city council decision-makers a visualization of air pollution data, using an interactive map-based dashboard with multiple spatial resolution. The air quality data is collected using low-cost portable sensors. Air pollution data is then integrated with other environmental contextual data and displayed into the dashboard. Such data includes, among other, spatio-temporal mobility data, providing contextual information about air pollution. The solution is tailored to city council decision-makers enabling a better understanding of air quality issues, and acting as a supporting tool for different communities, exploiting synergies to promote the sustainability of the city.
Vitor Cruz, Joao Nuno Matos, Pedro Pinho, and M. P. M. Pato
IEEE
Medical imaging based on different technologies is an essential tool in clinical practice, either to provide an accurate initial diagnosis or to monitoring diseases evolution. Microwave imaging technique has recently emerged as complementary method for breast imaging with high potential to become quite important for biomedical applications. This paper contributes to the technological development of this new technique, with the development of a broadband antenna (3 to 10 GHz) that operate in the range of the microwaves, which can be used for the detection of possible tumors, in particular, breast cancer. Also, some preliminary experience in a test bed is considered in order to detect possible differences between three samples which represent different situations: healthy breast, benign and malignant tumor breast.
Pedro Cardoso, Nuno Datia, and M.P.M. Pato
IEEE
For the analysis and comparison of electromyography (EMG) signals from different patients, standardization techniques are used to calculate the integrated EMG signal (iEMG), useful to evaluate the level of activity of different muscles. The iEMG corresponds to the area under the rectified curve (AUC). Currently, monitoring and follow-up of these patients is done in regular health exams where the evolution of patients is assessed. The monitoring includes performing multiple clinical trials. The goal of this paper is to help medical staff assessing the evolution of amyotrophic lateral sclerosis (ALS) disease by analyzing the collected data. The signal, described by the electromyogram, can be measured applying conductive elements or electrodes to the skin surface. The electrical activity of skeletal muscles is continuously measured for at least 24 hours. In this work we used an appropriate data model to store data generated by EMGs, optimized for analytical processing. We implemented aWeb API in order to provide access to the model data in an agnostic way, both to database management systems and data consumers. We implemented a web application to visualize data through the use of several interactive charts. Usability testing helped to validate the solution, confirming the ease of use of the web application and the fulfillment of all the proposed goals. The telemonitoring ALS patients doesn't change mortality but reduces the need for hospitalization and costs for patient.
V. Santos, N. Datia and Matilde Pato
CRC Press
M. P.M. Pato, N. J.G. Santos, P. Areias, E. B. Pires, M. de Carvalho, S. Pinto, and D. S. Lopes
Informa UK Limited
The diaphragm is a muscular membrane separating the abdominal and thoracic cavities, and its motion is directly linked to respiration. In this study, using data from a 59-year-old female cadaver obtained from the Visible Human Project, the diaphragm is reconstructed and, from the corresponding solid object, a shell finite element mesh is generated and used in several analyses performed with the ABAQUS 6.7 software. These analyses consider the direction of the muscle fibres and the incompressibility of the tissue. The constitutive model for the isotropic strain energy as well as the passive and active strain energy stored in the fibres is adapted from Humphrey's model for cardiac muscles. Furthermore, numerical results for the diaphragmatic floor under pressure and active contraction in normal and pathological cases are presented.
M. P. M. Pato and P. Areias
Wiley
A new active‐contraction visco‐elastic numerical model of the pelvic floor (skeletal) muscle is presented. Our model includes all elements that represent the muscle constitutive behavior, contraction and relaxation. In contrast with the previous models, the activation function can be null. The complete equations are shown and exactly linearized. Small verification and validation tests are performed and the pelvis is modeled using the data from the intra‐abdominal pressure tests. Copyright © 2009 John Wiley & Sons, Ltd.
J. A. C. MARTINS, M. P. M. PATO, E. B. PIRES, R. M. N. JORGE, M. PARENTE, and T. MASCARENHAS
Wiley
Abstract: This article describes research involving finite element simulations of women's pelvic floor, undertaken in the engineering schools of Lisbon and Oporto, in collaboration with the medical school of Oporto. These studies are motivated by the pelvic floor dysfunctions that lead namely to urinary incontinence and pelvic organ prolapse. This research ultimately aims at: (i) contributing to clarify the primary mechanism behind such disorders; (ii) providing tools to simulate the pelvic floor function and the effects of its dysfunctions; (iii) contributing to planning and performing surgeries in a more controlled and reliable way. The finite element meshes of the levator ani are based on a publicly available geometric data set, and use triangular thin shell or special brick elements. Muscle and soft tissues are assumed as (quasi‐)incompressible hyperelastic materials. Skeletal muscles are transversely isotropic with a single fiber direction, embedded in an isotropic matrix. The fibers considered in this work may be purely passive, or active with input of neuronal excitation and consideration of the muscle activation process. The first assumption may be adequate to simulate passive deformations of the pelvic muscles and tissues (namely, under the extreme loading conditions of childbirth). The latter may be adequate to model faster contractions that occur in time intervals of the same order as those of muscle activation and deactivation (as in preventing urinary incontinence in coughing or sneezing). Numerical simulations are presented for the active deformation of the levator ani muscle under constant pressure and neural excitation, and for the deformation induced by a vaginal childbirth.
J. A. C. Martins, M. P. M. Pato, and E. B. Pires
Informa UK Limited
The present paper surveys recent developments in constitutive and computational modelling of skeletal muscles, concerning mainly the generalization to two- and three-dimensional (2D, 3D) continuum deformation analysis of typical one-dimensional (1D) Hill-type muscle models. Extending our previous work in the field and recent contributions by other authors, we describe a constitutive model for skeletal muscles that incorporates all the features of the 3 typical elements (parallel elastic, series elastic and contractile elements) in Hill's muscle model. In particular the proposed incompressible transversely isotropic model incorporates: a multiplicative split of the fibre stretch into contractile and (series) elastic stretches; the possibility of energy storage in the series elastic element; the dependence of the contractile stress on the strain rate; the governing equation of activation dynamics, so that general histories of neural stimulation may be taken as input data. The resulting 2D or 3D constitutive equations are implemented as user subroutines in the large deformation finite element software package ABAQUS. Simple numerical tests are presented and discussed, as well as an example that involves passive or active deformations of a pelvic floor muscle using shell finite elements.