Publications by authors named "João Tavares"

149 Publications

Explainable Deep Learning for Personalized Age Prediction With Brain Morphology.

Front Neurosci 2021 28;15:674055. Epub 2021 May 28.

Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy.

Predicting brain age has become one of the most attractive challenges in computational neuroscience due to the role of the predicted age as an effective biomarker for different brain diseases and conditions. A great variety of machine learning (ML) approaches and deep learning (DL) techniques have been proposed to predict age from brain magnetic resonance imaging scans. If on one hand, DL models could improve performance and reduce model bias compared to other less complex ML methods, on the other hand, they are typically black boxes as do not provide an in-depth understanding of the underlying mechanisms. Explainable Artificial Intelligence (XAI) methods have been recently introduced to provide interpretable decisions of ML and DL algorithms both at local and global level. In this work, we present an explainable DL framework to predict the age of a healthy cohort of subjects from ABIDE I database by using the morphological features extracted from their MRI scans. We embed the two local XAI methods SHAP and LIME to explain the outcomes of the DL models, determine the contribution of each brain morphological descriptor to the final predicted age of each subject and investigate the reliability of the two methods. Our findings indicate that the SHAP method can provide more reliable explanations for the morphological aging mechanisms and be exploited to identify personalized age-related imaging biomarker.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fnins.2021.674055DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8192966PMC
May 2021

Benzodiazepine Use in Opioid Maintenance Treatment Programme: Risks and Clinical Outcomes.

Acta Med Port 2021 Mar 1;34(3):209-216. Epub 2021 Mar 1.

Drug Addiction Treatment Centre. Agualva-Cacém. Cacém. Portugal.

Introduction: The co-association of benzodiazepines and opioids is associated with an increased risk of overdose, death, and poorer psychosocial prognosis. The aim of this study is to characterize the prevalence, pattern of use, and primary clinical outcomes in benzodiazepines users in a public opioid maintenance treatment unit.

Material And Methods: We conducted a cross-sectional study involving 236 patients treated with opioid substitutes (methadone and buprenorphine). We conducted a descriptive, bivariable, and multivariable analysis to determine clinical differences between benzodiazepines users and non-users.

Results: The prevalence of consumption of benzodiazepines was 25.4% (60). The benzodiazepines were obtained with a medical prescription (49.8%) or on the black market (42.6%). The most prescribed benzodiazepine was diazepam (29.1%), and the main reasons were to relieve insomnia (27.7%) or anxiety (26.9%) and to enhance the psychoactive effects of other drugs (19.7%). Regarding the clinical outcomes, we highlight: a very high prevalence of hepatitis C (51.7%); severe ongoing consumption of psychoactive drugs (73.7%); and a high rate of depression and anxiety (> 60%), significantly higher in the benzodiazepines-user group. In the multivariable analysis of benzodiazepine use, we found alcohol consumption (OR 0.482; IC 95% 0.247, 0.238) had a negative association and having hepatitis C (OR 2.544, IC 95% 1.273, 5.084) or anxiety symptoms (OR 5.591; IC 95% 2.345, 13.326) had positive associations.

Discussion: Our results suggest the BZD users had a complex drug addiction problem and underline the importance of adequately addressing BZD use, contemplating psychological and psychiatric approach in this particular population.

Conclusion: Past or current use of benzodiazepines is associated with poor clinical and psychiatric outcomes. A multidisciplinary approach with a focus on infectious diseases and mental health is critical in order to enhance the treatment effectiveness and overall prognosis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.20344/amp.13181DOI Listing
March 2021

Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model.

Sensors (Basel) 2021 Apr 24;21(9). Epub 2021 Apr 24.

Departamento de Engenharia Mecânica, Faculdade de Engenharia, Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Universidade do Porto, 4200-465 Porto, Portugal.

Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural network (CNN) named LeukNet that was inspired on convolutional blocks of VGG-16, but with smaller dense layers. To define the LeukNet parameters, we evaluated different CNNs models and fine-tuning methods using 18 image datasets, with different resolution, contrast, colour and texture characteristics. We applied data augmentation operations to expand the training dataset, and the 5-fold cross-validation led to an accuracy of 98.61%. To evaluate the CNNs generalisation ability, we applied a cross-dataset validation technique. The obtained accuracies using cross-dataset experiments on three datasets were 97.04, 82.46 and 70.24%, which overcome the accuracies obtained by current state-of-the-art methods. We conclude that using the most common and deepest CNNs may not be the best choice for applications where the images to be classified differ from those used in pre-training. Additionally, the adopted cross-dataset validation approach proved to be an excellent choice to evaluate the generalisation capability of a model, as it considers the model performance on unseen data, which is paramount for CAD systems.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/s21092989DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8123151PMC
April 2021

(Lack of) oral hygiene care for hospitalized elderly patients.

Rev Bras Enferm 2021 12;74(suppl 2):e20200415. Epub 2021 Feb 12.

Universidade Federal da Bahia. Salvador, Bahia, Brazil.

Objective: to analyze the oral hygiene care for hospitalized elderly patients provided by the nursing staff.

Method: this is a qualitative, exploratory-descriptive study carried out in a university hospital, with the participation of 35 professionals from the nursing staff. Data collection was carried out through semi-structured interviews, explored through thematic content analysis.

Results: two categories emerged: The oral hygiene of hospitalized elderly patients as an extension of body care and Barriers in (lack of) care with the oral hygiene of hospitalized elderly patients, with two subcategories: The oral hygiene and dental prosthesis technique performed divergently; Care hampered by deficit of materials and human resources.

Final Considerations: this study showed weaknesses in the oral hygiene care of hospitalized elderly patients, promoting reflections on the practice informed in data and management actions, allowing recommendations of care standards for the nursing staff.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1590/0034-7167-2020-0415DOI Listing
June 2021

What is the real impact of on-site percutaneous coronary intervention? A propensity score analysis of patients admitted with acute coronary syndrome.

Rev Port Cardiol (Engl Ed) 2021 Mar 29;40(3):169-188. Epub 2021 Jan 29.

Serviço de Cardiologia do Centro Hospitalar Barreiro-Montijo, Lisboa, Portugal; Centro Nacional de Colheita de Dados em Cardiologia, Sociedade Portuguesa de Cardiologia, Coimbra, Portugal; Investigadores do Registo Nacional de Síndromes Coronárias Agudas.

Introduction: In an era in which coronary heart disease is one of the leading causes of death worldwide, several studies report the persistence of obstacles to accessing revascularization, and percutaneous coronary intervention in particular, which may be associated with worse outcomes.

Objectives: To compare cardiovascular outcomes in patients admitted to hospitals with and without on-site percutaneous coronary intervention (PCI) capabilities.

Material And Methods: A retrospective study based on the National Registry of Acute Coronary Syndromes (ACS) - with data collection from 2010 to 2018. Division of the patients into two groups: with and without ST-elevation. Two subgroups were subsequently created according to the presence/absence of on-site PCI. A propensity score was performed to standardize the results. Patients without information about hospital admission (with/without PCI) were excluded.

Results: 6008 patients were included after exclusion criteria and propensity score were applied. We found that patients admitted for ACS with ST-elevation (STE-ACS) had more episodes of sustained ventricular tachycardia (OR 2.14; CI (1.26-3.61); p=0.004) in hospitals without on-site PCI. Regarding ACS without ST elevation (NSTE-ACS), there were more cases of congestive heart failure (OR 0.79; CI (0.65-0.98)) in hospitals with on-site PCI.

Conclusion: The incidence of a greater number of major adverse events in hospitalizations without on-site PCI, particularly in the case of STE-ACS, is a consequence of the delay before revascularization. National and local strategies must be established to reduce the negative impact of the absence of on-site PCI and the resulting time before revascularization.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.repc.2020.06.019DOI Listing
March 2021

Hospitalized older adult: predictors of functional decline.

Rev Lat Am Enfermagem 2021 8;29:e3399. Epub 2021 Jan 8.

Centro Hospitalar e Universitário de Coimbra, Serviço de Cirurgia Maxilo-Facial e Cirurgia Plástica, Coimbra, Portugal.

Objective: to identify the predictors of functional decline in hospitalized individuals aged 70 or over, between: baseline and discharge; discharge and follow-up, and baseline and three-month follow-up.

Method: a prospective cohort study conducted in internal medicine services. A questionnaire was applied (clinical and demographic variables, and predictors of functional decline) at three moments. The predictors were determined using the binary logistic regression model.

Results: the sample included 101 patients, 53.3% female, mean age of 82.47 ± 6.57 years old. The predictors that most contributed to decline in hospitalization were the following: previous hospitalization (OR=1.8), access to social support (OR=4.86), cognitive deficit (OR=6.35), mechanical restraint (OR=7.82), and not having a partner (OR=4.34). Age (OR=1.18) and medical diagnosis (OR=0.10) were the predictors between discharge and follow-up. Being older, delirium during hospitalization (OR=5.92), and presenting risk of functional decline (OR=5.53) were predictors of decline between the baseline and follow-up.

Conclusion: the most relevant predictors were age, previous hospitalization, cognitive deficit, restraint, social support, not having a partner, and delirium. Carrying out interventions aimed at minimizing the impact of these predictors can be an important contribution in the prevention of functional decline.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1590/1518-8345.3612.3399DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7798389PMC
January 2021

Persistent Diaper Rash in a 5-month-old Girl.

Pediatr Rev 2021 Jan;42(1):e1-e4

Serviço de Dermatologia do Centro Hospitalar do Porto, Porto, Portugal.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1542/pir.2018-0141DOI Listing
January 2021

Older adult care in nursing education: How have curricula been developed?

Nurse Educ Pract 2021 Jan 8;50:102947. Epub 2020 Dec 8.

Nursing School of Coimbra, Health Sciences Research Unit: Nursing, Researcher at the Health Sciences Research Unit: Nursing, Portugal; Portugal Centre for Evidence-Based Practice: A JBI Centre of Excellence, Portugal. Electronic address:

Given the rapidly growing older adult population, future nurses should increase their knowledge and skills in gerontological nursing to deliver high-quality care to older adults. The aim of this national survey (n = 40 nursing schools) was to analyse the status of gerontology education in Portuguese baccalaureate nursing programmes. Data were collected using a 51-item questionnaire about baccalaureate nursing education programmes and gerontology-related topics. Descriptive analysis was used. A total of 18 nursing schools returned the questionnaire (response rate = 45%). Results showed that 66.7% (n = 12) of nursing schools integrated gerontology content into several courses, 38.9% (n = 7) of them had stand-alone courses, and 11.1% (n = 2) of them had both options. The most significant factor inhibiting the development of the gerontological nursing curriculum was the negative image of gerontological nursing (44.4%). Gerontological-related competencies were identified in only two nursing programmes. Thirteen schools reported needing help to strengthen the gerontological content in the nursing curriculum. This study has demonstrated that gerontological content is covered in the nursing curriculum of all nursing schools. The increase of knowledge and skills in gerontological nursing and the development of a standard gerontological curriculum could contribute to enhancing gerontological nursing education and practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.nepr.2020.102947DOI Listing
January 2021

Alzheimer's diagnosis using deep learning in segmenting and classifying 3D brain MR images.

Int J Neurosci 2020 Nov 4:1-10. Epub 2020 Nov 4.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Porto, Portugal.

Background And Objectives: Dementia is one of the brain diseases with serious symptoms such as memory loss, and thinking problems. According to the World Alzheimer Report 2016, in the world, there are 47 million people having dementia and it can be 131 million by 2050. There is no standard method to diagnose dementia, and consequently unable to access the treatment effectively. Hence, the computational diagnosis of the disease from brain Magnetic Resonance Image (MRI) scans plays an important role in supporting the early diagnosis. Alzheimer's Disease (AD), a common type of Dementia, includes problems related to disorientation, mood swings, not managing self-care, and behavioral issues. In this article, we present a new computational method to diagnosis Alzheimer's disease from 3D brain MR images.

Methods: An efficient approach to diagnosis Alzheimer's disease from brain MRI scans is proposed comprising two phases: I) segmentation and II) classification, both based on deep learning. After the brain tissues are segmented by a model that combines Gaussian Mixture Model (GMM) and Convolutional Neural Network (CNN), a new model combining Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) is used to classify Alzheimer's disease based on the segmented tissues.

Results: We present two evaluations for segmentation and classification. For comparison, the new method was evaluated using the AD-86 and AD-126 datasets leading to Dice 0.96 for segmentation in both datasets and accuracies 0.88, and 0.80 for classification, respectively.

Conclusion: Deep learning gives prominent results for segmentation and feature extraction in medical image processing. The combination of XGboost and SVM improves the results obtained.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/00207454.2020.1835900DOI Listing
November 2020

Deep Learning in Radiation Oncology Treatment Planning for Prostate Cancer: A Systematic Review.

J Med Syst 2020 Aug 30;44(10):179. Epub 2020 Aug 30.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Porto, Portugal.

Radiation oncology for prostate cancer is important as it can decrease the morbidity and mortality associated with this disease. Planning for this modality of treatment is both fundamental, time-consuming and prone to human-errors, leading to potentially avoidable delays in start of treatment. A fundamental step in radiotherapy planning is contouring of radiation targets, where medical specialists contouring, i.e., segment, the boundaries of the structures to be irradiated. Automating this step can potentially lead to faster treatment planning without a decrease in quality, while increasing time available to physicians and also more consistent treatment results. This can be framed as an image segmentation task, which has been studied for many decades in the fields of Computer Vision and Machine Learning. With the advent of Deep Learning, there have been many proposals for different network architectures achieving high performance levels. In this review, we searched the literature for those methods and describe them briefly, grouping those based on Computed Tomography (CT) or Magnetic Resonance Imaging (MRI). This is a booming field, evidenced by the date of the publications found. However, most publications use data from a very limited number of patients, which presents an obstacle to deep learning models training. Although the performance of the models has achieved very satisfactory results, there is still room for improvement, and there is arguably a long way before these models can be used safely and effectively in clinical practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10916-020-01641-3DOI Listing
August 2020

Using a distance map and an active contour model to segment the carotid artery boundary from the lumen contour in proton density weighted magnetic resonance images.

Comput Biol Med 2020 08 1;123:103901. Epub 2020 Jul 1.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465, Porto, Portugal. Electronic address:

Segmentation methods have assumed an important role in image-based diagnosis of several cardiovascular diseases. Particularly, the segmentation of the boundary of the carotid artery is demanded in the detection and characterization of atherosclerosis and assessment of the disease progression. In this article, a fully automatic approach for the segmentation of the carotid artery boundary in Proton Density Weighted Magnetic Resonance Images is presented. The approach relies on the expansion of the lumen contour based on a distance map built using the gray-weighted distance relative to the center of the identified lumen region in the image under analysis. Then, a Snake model with a modified weighted external energy based on the combination of a balloon force along with a Gradient Vector Flow-based external energy is applied to the expanded contour towards the correct boundary of the carotid artery. The average values of the Dice coefficient, Polyline distance, mean contour distance and centroid distance found in the segmentation of 139 carotid arteries were 0.83 ± 0.11, 2.70 ± 1.69 pixels, 2.79 ± 1.89 pixels and 3.44 ± 2.82 pixels, respectively. The segmentation results of the proposed approach were also compared against the ones obtained by related approaches found in the literature, which confirmed the outstanding performance of the new approach. Additionally, the proposed weighted external energy for the Snake model was shown to be also robust to carotid arteries with large thickness and weak boundary image edges.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2020.103901DOI Listing
August 2020

Dark Proteome Database: Studies on Disorder.

High Throughput 2020 Jun 30;9(3). Epub 2020 Jun 30.

Instituto de Sistemas e Robótica, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal.

There is a misconception that intrinsic disorder in proteins is equivalent to darkness. The present study aims to establish, in the scope of the Swiss-Prot and Dark Proteome databases, the relationship between disorder and darkness. Three distinct predictors were used to calculate the disorder of Swiss-Prot proteins. The analysis of the results obtained with the used predictors and visualization paradigms resulted in the same conclusion that was reached before: disorder is mostly unrelated to darkness.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/ht9030015DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7563470PMC
June 2020

Users' Perceptions of Signage Systems at Three Portuguese Hospitals.

HERD 2020 07 14;13(3):36-53. Epub 2020 May 14.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Portugal.

This article is a report on the quantitative data collected from patients, family members, and visitors using the outpatient areas of three hospitals in Portugal. It details the users' views regarding the existing signage and presents suggestions to improve the design and implementation of the signage systems. A questionnaire was used with 1,287 respondents. The results showed that almost all users had a positive opinion regarding the current signage. However, some of the users' answers and observed behaviors indicated that the majority tended to ignore the signs and preferred to ask staff for help. Additionally, when asked for suggestions, many of the respondents were able to point out existing problems that affected their wayfinding. Although the signage was generally evaluated as good, many of the users perceived a variety of problems and, as already mentioned, asked the staff for directions, which results in lost time and hidden costs for the institutions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1937586720924761DOI Listing
July 2020

An innovative endotracheal tube clamp for use in COVID-19.

Can J Anaesth 2020 10 11;67(10):1468-1470. Epub 2020 May 11.

Intensive Care Medicine Department, Algarve University and Hospitalar Center, Faro, Portugal.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12630-020-01703-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7212844PMC
October 2020

Triple-valve infective endocarditis and complications.

Acta Cardiol 2020 Dec 3;75(8):801-802. Epub 2019 Nov 3.

Cardiology Department, Centro Hospitalar Barreiro Montijo E.P.E, Barreiro, Portugal.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/00015385.2019.1684016DOI Listing
December 2020

Levosimendan In Single Ventricle Heart Failure After Longterm Survival Of A Modified Blalock-Taussig Shunt.

Rev Port Cir Cardiotorac Vasc 2019 Apr-Jun;26(2):147-149

Cardiovascular Surgical Department, Hospital, Portugal.

We report the case of a 44 year-old patient with complex ACHD, admitted with acute decompensated heart failure (ADHF) in hemodynamic profile B. He had a single ventricle with pulmonary atresia, previously submitted to three modified Blalock-Taussig shunts (mBTs) at the age of 2, 12 and 19 years old. Despite conventional treatment with diuretics, β-blockers (BB) and isosorbide dinitrate the patient progressed to profile C and the transthoracic echocardiogram disclosed a reduced systolic function. Likewise, levosimendan was commenced and an appropriate decongestion and a marked reduction in the NT-proBNP were seen. Treatment with angiotensin-converting-enzyme inhibitor, BB, ivabradine and mineralocorticoid receptor was optimized. The patient was discharged home after 26 days in NYHA class III and referred for heart transplant after right heart catheterization. To our knowledge, this is the first report of successful levosimendan's use in ADHF in a mBTs long-term survivor.
View Article and Find Full Text PDF

Download full-text PDF

Source
October 2019

Global Ultrasound Check for the Critically lll (GUCCI)-a new systematized protocol unifying point-of-care ultrasound in critically ill patients based on clinical presentation.

Open Access Emerg Med 2019 10;11:133-145. Epub 2019 Jul 10.

Intensive Care Unit, Hospital CUF Infante Santo, Lisbon, Portugal.

Ultrasound technology is an essential tool in the management of critically ill patients. Point-of-care ultrasonography (POCUS) enables data collection from different anatomic areas to achieve the most probable diagnosis and administer the right therapy at the right time. Despite the increasing utilization of POCUS, there is still a lack of standards to establish how to use different bedside ultrasound protocols, and it is imperative to develop a unifying protocol. Thus, the aim of this paper is to establish a new systematized approach that can be adopted by all physicians to implement POCUS for critically ill patient management. To achieve this, we propose a new systematized approach-Global Ultrasound Check for the Critically Ill (GUCCI)-that integrates multiple protocols. This protocol is organized based on three syndromes (acute respiratory failure, shock, and cardiac arrest) and includes ultrasound-guided procedures.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2147/OAEM.S199137DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6628156PMC
July 2019

Behçet Syndrome and Crohn's Disease: What Are the Differences?

Eur J Case Rep Intern Med 2019 1;6(3):001044. Epub 2019 Mar 1.

Pathology Department, Hospital da Luz, Lisbon, Portugal.

Behçet syndrome (BS) is a variable vessel vasculitis that has pleiotropic manifestations. A 43-year-old male with a previous diagnosis of Crohn's disease (CD) presented with deep venous thrombosis and bilateral superficial femoral artery aneurysms. A diagnosis of BS was made, and the patient was treated aggressively with immunosuppressive therapy and bilateral bypass surgery, attaining a favourable outcome. CD has many features that overlap with BS, and it may be challenging to distinguish between these two conditions, as our case illustrates. Nonetheless, the combination of venous thrombosis and arterial aneurysms should point the clinician towards a diagnosis of BS.

Learning Points: Behçet syndrome is a variable vessel vasculitis of unknown aetiology that has pleiotropic manifestations.Crohn's disease has many overlapping features with Behçet syndrome, namely gastrointestinal, cutaneous, articular, ocular and cardiac manifestations.The combination of venous thrombosis and arterial aneurysms should point the clinician towards a diagnosis of Behçet syndrome.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.12890/2019_001044DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6438111PMC
March 2019

Pernicious Anaemia with Normal Vitamin B12.

Eur J Case Rep Intern Med 2019 18;6(2):001045. Epub 2019 Feb 18.

Medicine Department, Hospital da Luz, Lisbon, Portugal.

A 49-year-old female patient presented to our hospital with asthenia, odynophagia, low grade fever, worsening symptoms of chronic depression, and symmetric leg paresthesias. Investigations showed macrocytic anaemia, leucopenia, thrombocytopenia, high lactate dehydrogenase levels and a normal Coombs test. Trilineage dysplasia was detected in the bone marrow biopsy specimen. The diagnostic work-up led us to the diagnosis of pernicious anaemia with a spuriously normal value of vitamin B12 and high titres of anti-intrinsic factor autoantibodies. This case highlights the importance of considering vitamin B12 deficiency in the differential diagnosis of myelodysplasia, even when vitamin B12 levels seem to be normal.

Learning Points: Vitamin B12 deficiency is characterized by neuropsychiatric manifestations and bone marrow failure with accompanying dysplastic changes.Spuriously normal vitamin B12 levels can occur in pernicious anaemia due to anti-intrinsic factor autoantibody interference in the laboratory assay.Myelodysplastic syndromes and vitamin B12 deficiency share clinical and laboratory similarities, so a correct differential diagnosis is crucial for adequate treatment.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.12890/2019_001045DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6432825PMC
February 2019

Mediastinum Teratoma Rupture: A Rare Manifestation.

Eur J Case Rep Intern Med 2019 28;6(2):001022. Epub 2019 Jan 28.

Medicine Department, Hospital da Luz, Lisbon, Portugal.

We present the case of a 22-year-old man who presented with cough, haemoptysis and fever of 3 days' duration. A teratoma had been diagnosed 2 years previously. Physical examination was unremarkable but laboratory tests showed anaemia, neutrophilic leucocytosis and an increase in C-reactive protein. Chest CT revealed a teratoma of the anterior mediastinum with post-obstructive pneumonitis suggestive of tumour rupture. Antibiotic treatment resulted in a good clinical outcome. The patient was submitted to a left upper lobectomy and pathological examination revealed a mature teratoma. Teratomas are germ cell tumours that are usually asymptomatic and their rupture is a rare event.

Learning Points: Mature teratomas are usually asymptomatic.Teratoma bronchial rupture is rare.The most frequent location for mature teratomas is the anterior mediastinum.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.12890/2019_001022DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6432830PMC
January 2019

Semiautomatic Estimation of Device Size for Left Atrial Appendage Occlusion in 3-D TEE Images.

IEEE Trans Ultrason Ferroelectr Freq Control 2019 05 8;66(5):922-929. Epub 2019 Mar 8.

Left atrial appendage (LAA) occlusion is used to reduce the risk of thromboembolism in patients with nonvalvular atrial fibrillation by obstructing the LAA through a percutaneously delivered device. Nonetheless, correct device sizing is complex, requiring the manual estimation of different measurements in preprocedural/periprocedural images, which is tedious and time-consuming and with high interobserver and intraobserver variability. In this paper, a semiautomatic solution to estimate the required relevant clinical measurements is described. This solution starts with the 3-D segmentation of the LAA in 3-D transesophageal echocardiographic images, using a constant blind-ended model initialized through a manually defined spline. Then, the segmented LAA surface is aligned with a set of templates, i.e., 3-D surfaces plus relevant measurement planes (manually defined by one observer), transferring the latter to the unknown situation. Specifically, the alignment is performed in three consecutive steps, namely: 1) rigid alignment using the LAA clipping plane position; 2) orientation compensation using the circumflex artery location; and 3) anatomical refinement through a weighted iterative closest point algorithm. The novel solution was evaluated in a clinical database with 20 volumetric TEE images. Two experiments were set up to assess: 1) the sensitivity of the model's parameters and 2) the accuracy of the proposed solution for the estimation of the clinical measurements. Measurement levels manually identified by two observers were used as ground truth. The proposed solution obtained results comparable to the interobserver variability, presenting narrower limits of agreement for all measurements. Moreover, this solution proved to be fast, taking nearly 40 s (manual analysis took 3 min) to estimate the relevant measurements while being robust to the variation of the model's parameters. Overall, the proposed solution showed its potential for fast and robust estimation of the clinical measurements for occluding device selection, proving its added value for clinical practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TUFFC.2019.2903886DOI Listing
May 2019

Recent Advances in Brain Signal Analysis: Methods and Applications 2018.

Comput Intell Neurosci 2018;2018:5971086. Epub 2018 Dec 9.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Porto, Portugal.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2018/5971086DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6305111PMC
May 2019

Sex estimation using the mandibular canine index components.

Forensic Sci Med Pathol 2019 Jun 10;15(2):191-197. Epub 2018 Dec 10.

Faculdade de Medicina Dentária da Universidade do Porto, Rua Dr. Manuel Pereira da Silva, 4200 - 393, Porto, Portugal.

The mandibular canine index (MCI) has been described as a suitable methodology for sex estimation in forensic scenarios but there are contradictory reports about its accuracy. Moreover, the two mandibular canine teeth must be available, which is not always a viable option. The aim of this study was to strip the MCI by analyzing the MCI itself and its components, in order to optimize its use for sex estimation. The mesiodistal dimensions of the mandibular canine crown and the mandibular canine arch width were measured in a sample of 120 cast models. Five predictor variables were considered in this study: the standard MCI, a variation of the MCI using the left canine, and MCI components (MD43, MD33 and D33-43). Multivariate binary logistic regression was performed using stepwise forward approach to select the most statistical relevant variables on the probability of a cast being from a female. The estimated probability was then analyzed with respect to performance in sex classification (ROC analysis and optimal cut-offs accuracy) and compared with the performance of the univariate variables. MCI43 and MCI33 presented the lowest performance (64.2% and 63.3% respectively), and the highest overall accuracy was attained using the MD43 and MD33 (85.8% in both cases). The multivariate logistic model obtained (using MD43 and MD33) exhibited the same accuracy as the logistic model based solely on MD43 (85.8%). Our results suggest that MD43 should be used instead of MCI for sex estimation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12024-018-0051-2DOI Listing
June 2019

Healthcare Signage Design: A Review on Recommendations for Effective Signing Systems.

HERD 2019 07 3;12(3):45-65. Epub 2018 Dec 3.

3 Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Porto, Portugal.

This article provides a set of recommendations, selected from the systematic literature review carried out, regarding signage systems for healthcare institutions that can be used for designing or redesigning more competent signage systems. The signage systems in healthcare settings are usually poorly designed due to the expansion of the original facilities, a lack of awareness of existing guidelines by the developers, and a lack of agreement between the existing recommendations. There are several guidelines and recommendations available in the literature; however, each work was developed for specific cultural contexts, so there is a lack of uniformity among them. Hence, there is a need to uniformize the guidelines for signage design in healthcare, in order to provide supportive information for developers to build and implement effective and efficient signage systems. This study examined the available literature on the subject and established a set of guidelines organized in categories to help the design process. A literature review was conducted, and 34 selected publications were analyzed from which recommendations were created. A best practices manual was also studied and used as the analytical framework to establish the design categories of the developed recommendations. This review resulted in guidelines divided into nine design categories that should be considered in the design and implementation process of signage systems in healthcare facilities.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1937586718814822DOI Listing
July 2019

Time-varying pharmacodynamics in a simple non-integer HIV infection model.

Math Biosci 2019 01 3;307:1-12. Epub 2018 Nov 3.

Faculty of Sciences, University of Porto, Rua do Campo Alegre s/n, Porto 4440-452, Portugal.

In this paper we study the effect of time-varying drug exposure in the dynamics of a fractional order model for the human immunodeficiency virus infection. We compute the reproduction number of the model and verify the stability of the disease-free equilibrium. The model is simulated for parameters directly modelling the pharmacodynamics of HIV, namely the slope of the dose-response curve, the drug's half-life, and the dosing interval. The later affect in a significant way the infection patterns. The order of the fractional derivative is also a key player of the model, adding more information, which could be useful for a deeper understanding of the pharmacodynamics of HIV, necessary for more accurate therapeutic regimens.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.mbs.2018.11.001DOI Listing
January 2019

Resident-to-resident elder mistreatment (R-REM): a study in residential structures for elderly people (ERI) in Portugal.

J Elder Abuse Negl 2019 Jan-Feb;31(1):66-76. Epub 2018 Oct 25.

c Department of Education and Psychology , CINTESIS (Center for Health Technology and Services Research) University of Aveiro , Aveiro , Portugal.

This study explores patterns of resident-to-resident elder mistreatment (R-REM) in Portuguese Residential Structures for Elderly People (ERI: Estruturas Residenciais para Idosos). Results display a serious situation of R-REM, which occurs in different patterns.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/08946566.2018.1539690DOI Listing
February 2020

Fast Segmentation of the Left Atrial Appendage in 3-D Transesophageal Echocardiographic Images.

IEEE Trans Ultrason Ferroelectr Freq Control 2018 12 28;65(12):2332-2342. Epub 2018 Sep 28.

Left atrial appendage (LAA) has been generally described as "our most lethal attachment," being considered the major source of thromboembolism in patients with nonvalvular atrial fibrillation. Currently, LAA occlusion can be offered as a treatment for these patients, obstructing the LAA through a percutaneously delivered device. Nevertheless, correct device sizing is not straightforward, requiring manual analysis of peri-procedural images. This approach is suboptimal, time demanding, and highly variable between experts, which can result in lengthy procedures and excess manipulations. In this paper, a semiautomatic LAA segmentation technique for 3-D transesophageal echocardiography (TEE) images is presented. Specifically, the proposed technique relies on a novel segmentation pipeline where a curvilinear blind-ended model is optimized through a double stage strategy: 1) fast contour evolution using global terms and 2) contour refinement based on regional energies. To reduce its computational cost, and thus make it more attractive to real interventions, the B-spline explicit active surface framework was used. This novel method was evaluated in a clinical database of 20 patients. Manual analysis performed by two observers was used as ground truth. The 3-D segmentation results corroborated the accuracy, robustness to the variation of the parameters, and computationally attractiveness of the proposed method, taking approximately 14 s to segment the LAA with an average accuracy of ~0.9 mm. Moreover, a performance comparable to the interobserver variability was found. Finally, the advantages of the segmented model were evaluated, while semiautomatically extracting the clinical measurements for device selection, showing a similar accuracy but with a higher reproducibility when compared to the current practice. Overall, the proposed segmentation method shows potential for an improved planning of LAA occlusion, demonstrating its added value for normal clinical practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TUFFC.2018.2872816DOI Listing
December 2018

Cerebral Venous Sinus Thrombosis in a Child with Idiopathic Nephrotic Syndrome: a case report.

J Bras Nefrol 2018 Oct-Dec;40(4):418-422. Epub 2018 Aug 2.

Centro Hospitalar e Universitário de Coimbra, Hospital Pediátrico, Unidade de Nefrologia Pediátrica, Coimbra, Portugal.

Complications are rare in pediatric cases of idiopathic nephrotic syndrome (NS). Thromboembolism ranks among the most uncommon and difficult complications to diagnose, particularly in the first episode of NS, since clinical signs might be unspecific. This report describes the case of a 5-year-old girl with NS for the first time presenting with severe hypoalbuminemia (< 2g/dL). The patient responded poorly to therapy with corticosteroids. On day 8 of hospitalization she started having headaches and vomiting; she did not present hemodynamic alterations, fever or exanthems, and her neurological parameters were normal. The patient was suspected for intracranial hypertension, and computed tomography scans revealed she had cerebral venous sinus thrombosis (CVST). She was started on anticoagulants and showed clinical signs of improvement. The patient had no evident prothrombotic risk factors. She had three other episodes since she was diagnosed, one in which her plasma antithrombin level was low. Although antithrombin levels were normal in her first episode, she was tested after the resolution of proteinuria. The low levels of antithrombin seen in the first recurrence might have mirrored the initial drop in plasma antithrombin levels, an idea supported by the severe hypoalbuminemia she had when diagnosed. This severe manifestation of acquired thrombophilia might be in the origin of CVST. This report presents a rare case of thromboembolic complication in a pediatric patient with NS. The patient progressed well since she was started on anticoagulants. Although she did not present any evident risk factors at first, the development of her case indicated that severe acquired thrombophilia might have worked as the pathophysiological mechanism leading to CVST.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1590/2175-8239-jbn-2018-0009DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6534000PMC
September 2019

EEG-Based Biometrics: Challenges And Applications.

Comput Intell Neurosci 2018;2018:5483921. Epub 2018 Jun 7.

Programa de Pós Graduação em Informática Aplicada, Laboratório de Bioinformática, Universidade de Fortaleza, Fortaleza, CE, Brazil.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2018/5483921DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6011092PMC
May 2019

Automated segmentation of the atrial region and fossa ovalis towards computer-aided planning of inter-atrial wall interventions.

Comput Methods Programs Biomed 2018 Jul 18;161:73-84. Epub 2018 Apr 18.

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Faculdade de Engenharia, Universidade do Porto, Portugal. Electronic address:

Background And Objective: Image-fusion strategies have been applied to improve inter-atrial septal (IAS) wall minimally-invasive interventions. Hereto, several landmarks are initially identified on richly-detailed datasets throughout the planning stage and then combined with intra-operative images, enhancing the relevant structures and easing the procedure. Nevertheless, such planning is still performed manually, which is time-consuming and not necessarily reproducible, hampering its regular application. In this article, we present a novel automatic strategy to segment the atrial region (left/right atrium and aortic tract) and the fossa ovalis (FO).

Methods: The method starts by initializing multiple 3D contours based on an atlas-based approach with global transforms only and refining them to the desired anatomy using a competitive segmentation strategy. The obtained contours are then applied to estimate the FO by evaluating both IAS wall thickness and the expected FO spatial location.

Results: The proposed method was evaluated in 41 computed tomography datasets, by comparing the atrial region segmentation and FO estimation results against manually delineated contours. The automatic segmentation method presented a performance similar to the state-of-the-art techniques and a high feasibility, failing only in the segmentation of one aortic tract and of one right atrium. The FO estimation method presented an acceptable result in all the patients with a performance comparable to the inter-observer variability. Moreover, it was faster and fully user-interaction free.

Conclusions: Hence, the proposed method proved to be feasible to automatically segment the anatomical models for the planning of IAS wall interventions, making it exceptionally attractive for use in the clinical practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2018.04.014DOI Listing
July 2018