Search

Abstract Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Resumo As lógicas institucionais representam os sistemas de valores e crenças que orientam a ação de indivíduos ou organizações. Este estudo tem por objetivo identificar as dinâmicas de interações das lógicas que moldam as práticas de sustentabilidade nas organizações. A sistematização das diferentes categorias de interações entre lógicas possibilita analisar como a sustentabilidade pode ser incorporada nas organizações. A pesquisa foi desenvolvida com uma abordagem qualitativa, por meio de revisão sistemática e com uma análise temática para síntese e interpretação dos resultados. Observou-se que, com a interpretação das diferentes lógicas, desenvolvem-se as inter-relações de dominância, concorrência, coexistência ou hibridismo, as quais foram sistematizadas em categorias para analisar os processos de mudança para desenvolvimento da sustentabilidade nas organizações. Conclui-se que a aplicação das lógicas institucionais no campo da sustentabilidade avança além da perspectiva de desempenho ambiental, pois as categorias analíticas identificadas possibilitam compreender os processos de mudança para incorporar a sustentabilidade nas organizações. Na gestão das organizações, as lógicas institucionais permitem a elaboração de quadros para que os atores consigam criar uma linguagem comum para equacionar lógicas contraditórias e um valor compartilhado para as partes interessadas, além da própria organização.

Abstract Emerging evidence of the relationship between the microbiome composition and the development of numerous diseases, including cancer, has led to an increasing interest in the study of the human microbiome. Technological breakthroughs regarding DNA sequencing methods propelled microbiome studies with a large number of samples, which called for the necessity of more sophisticated data-analytical tools to analyze this complex relationship. The aim of this work was to develop a machine learning-based approach to distinguish the type of cancer based on the analysis of the tissue-specific microbial information, assessing the human microbiome as valuable predictive information for cancer identification. For this purpose, Random Forest algorithms were trained for the classification of five types of cancer—head and neck, esophageal, stomach, colon, and rectum cancers—with samples provided by The Cancer Microbiome Atlas database. One versus all and multi-class classification studies were conducted to evaluate the discriminative capability of the microbial data across increasing levels of cancer site specificity, with results showing a progressive rise in difficulty for accurate sample classification. Random Forest models achieved promising performances when predicting head and neck, stomach, and colon cancer cases, with the latter returning accuracy scores above 90% across the different studies conducted. However, there was also an increased difficulty when discriminating esophageal and rectum cancers, failing to differentiate with adequate results rectum from colon cancer cases, and esophageal from head and neck and stomach cancers. These results point to the fact that anatomically adjacent cancers can be more complex to identify due to microbial similarities. Despite the limitations, microbiome data analysis using machine learning may advance novel strategies to improve cancer detection and prevention, and decrease disease burden.

Purpose – The study aims to investigate urban agriculture in the city of São Paulo from the perspective of social capital. The specific objectives are (1) to identify the effects of social capital on urban agriculture and (2) to investigate social capital formation (its sources and challenges imposed onto its development). Design/methodology/approach – Initially, a review of the literature was carried out in order to understand the main concepts used in the field of study. Semi-structured interviews were also carried out with people from urban agriculture initiatives, and they were analyzed under the lens of social capital. Findings – Aspects of social capital were recognized and organized in a framework including sources, effects and challenges. The first deals with consummatory or instrumental sources that generate social capital. The second deals with the following effects: generation of human capital, citizenship, engagement, access and mobilization of resources, and access to information. The third deals with the challenges to its formation related to homophily and the perception of benefits from this form of capital. Originality/value – Urban agriculture plays an increasingly important role in relieving the pressure generated by the food production system, being part of the solution to food security and sustainability issues. Many researchers recognize important social aspects acting on the dynamics of the movement and the effects of activities on the generation of social capital. The contribution of this work is to deepen the understanding of this type of capital in the context of urban agriculture.

Deep Learning (DL) based classification algorithms have been shown to achieve top results in clinical diagnosis, namely with lung cancer datasets. However, the complexity and opaqueness of the models together with the still scant training datasets call for the development of explainable modeling methods enabling the interpretation of the results. To this end, in this paper we propose a novel interpretability approach and demonstrate how it can be used on a malignancy lung cancer DL classifier to assess its stability and congruence even when fed a low amount of image samples. Additionally, by disclosing the regions of the medical images most relevant to the resulting classification the approach provides important insights to the correspondent clinical meaning apprehended by the algorithm. Explanations of the results provided by ten different models against the same test sample are compared. These attest the stability of the approach and the algorithm focus on the same image regions.

In a clinical context, physicians usually take into account information from more than one data modality when making decisions regarding cancer diagnosis and treatment planning. Artificial intelligence-based methods should mimic the clinical method and take into consideration different sources of data that allow a more comprehensive analysis of the patient and, as a consequence, a more accurate diagnosis. Lung cancer evaluation, in particular, can benefit from this approach since this pathology presents high mortality rates due to its late diagnosis. However, many related works make use of a single data source, namely imaging data. Therefore, this work aims to study the prediction of lung cancer when using more than one data modality. The National Lung Screening Trial dataset that contains data from different sources, specifically, computed tomography (CT) scans and clinical data, was used for the study, the development and comparison of single-modality and multimodality models, that may explore the predictive capability of these two types of data to their full potential. A ResNet18 network was trained to classify 3D CT nodule regions of interest (ROI), whereas a random forest algorithm was used to classify the clinical data, with the former achieving an area under the ROC curve (AUC) of 0.7897 and the latter 0.5241. Regarding the multimodality approaches, three strategies, based on intermediate and late fusion, were implemented to combine the information from the 3D CT nodule ROIs and the clinical data. From those, the best model—a fully connected layer that receives as input a combination of clinical data and deep imaging features, given by a ResNet18 inference model—presented an AUC of 0.8021. Lung cancer is a complex disease, characterized by a multitude of biological and physiological phenomena and influenced by multiple factors. It is thus imperative that the models are capable of responding to that need. The results obtained showed that the combination of different types may have the potential to produce more comprehensive analyses of the disease by the models.

BackgroundTraumatic Brain Injury (TBI) is one of the leading causes of injury related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences, complicating medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Machine learning (ML) methods can take advantage of the data and guide physicians toward a better prognosis and, consequently, better healthcare. The objective of this study was to develop and test a wide range of machine learning models and evaluate their capability of predicting mortality of TBI, at hospital discharge, while assessing the similarity between the predictive value of the data and clinical significance.MethodsThe used dataset is the Hackathon Pediatric Traumatic Brain Injury (HPTBI) dataset, composed of electronic health records containing clinical annotations and demographic data of 300 patients. Four different classification models were tested, either with or without feature selection. For each combination of the classification model and feature selection method, the area under the receiver operator curve (ROC-AUC), balanced accuracy, precision, and recall were calculated.ResultsMethods based on decision trees perform better when using all features (Random Forest, AUC = 0.86 and XGBoost, AUC = 0.91) but other models require prior feature selection to obtain the best results (k-Nearest Neighbors, AUC = 0.90 and Artificial Neural Networks, AUC = 0.84). Additionally, Random Forest and XGBoost allow assessing the feature's importance, which could give insights for future strategies on the clinical routine.ConclusionPredictive capability depends greatly on the combination of model and feature selection methods used but, overall, ML models showed a very good performance in mortality prediction for TBI. The feature importance results indicate that predictive value is not directly related to clinical significance.

Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model's attention are within expert annotations, whereas 36.03% of the two dimensional model's attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.

Statistics have demonstrated that one of the main factors responsible for the high mortality rate related to lung cancer is the late diagnosis. Precision medicine practices have shown advances in the individualized treatment according to the genetic profile of each patient, providing better control on cancer response. Medical imaging offers valuable information with an extensive perspective of the cancer, opening opportunities to explore the imaging manifestations associated with the tumor genotype in a non-invasive way. This work aims to study the relevance of physiological features captured from Computed Tomography images, using three different 2D regions of interest to assess the Epidermal growth factor receptor (EGFR) mutation status: nodule, lung containing the main nodule, and both lungs. A Convolutional Autoencoder was developed for the reconstruction of the input image. Thereafter, the encoder block was used as a feature extractor, stacking a classifier on top to assess the EGFR mutation status. Results showed that extending the analysis beyond the local nodule allowed the capture of more relevant information, suggesting the presence of useful biomarkers using the lung with nodule region of interest, which allowed to obtain the best prediction ability. This comparative study represents an innovative approach for gene mutations status assessment, contributing to the discussion on the extent of pathological phenomena associated with cancer development, and its contribution to more accurate Artificial Intelligence-based solutions, and constituting, to the best of our knowledge, the first deep learning approach that explores a comprehensive analysis for the EGFR mutation status classification.

Abstract Atrial fibrillation (AF) is a cardiac rhythm disorder associated with increased morbidity and mortality. It is the leading risk factor for cardioembolic stroke and its early detection is crucial in both primary and secondary stroke prevention. Continuous monitoring of cardiac rhythm is today possible thanks to consumer-grade wearable devices, enabling transformative diagnostic and patient management tools. Such monitoring is possible using low-cost easy-to-implement optical sensors that today equip the majority of wearables. These sensors record blood volume variations—a technology known as photoplethysmography (PPG)—from which the heart rate and other physiological parameters can be extracted to inform about user activity, fitness, sleep, and health. Recently, new wearable devices were introduced as being capable of AF detection, evidenced by large prospective trials in some cases. Such devices would allow for early screening of AF and initiation of therapy to prevent stroke. This review is a summary of a body of work on AF detection using PPG. A thorough account of the signal processing, machine learning, and deep learning approaches used in these studies is presented, followed by a discussion of their limitations and challenges towards clinical applications.

(1) Background: Human frataxin is an iron binding protein that participates in the biogenesis of iron sulfur clusters and enhances ferrochelatase activity. While frataxin association to other proteins has been extensively characterized up to the structural level, much less is known about the putative capacity of frataxin to interact with functionally related metabolites. In turn, current knowledge about frataxin’s capacity to coordinate metal ions is limited to iron (II and III); (2) Methods: here, we used NMR spectroscopy, Molecular Dynamics, and Docking approaches to demonstrate new roles of frataxin; (3) Results: We demonstrate that frataxin also binds Zn2+ in a structurally similar way to Fe2+, but with lower affinity. In turn, both Fe2+-loaded and Zn2+-loaded frataxins specifically associate to protoporphyrin IX with micromolar affinity, while apo-frataxin does not bind to the porphyrin. Protoporphyrin IX association to metal-loaded frataxin shares the binding epitope with ferrochelatase; and (4) Conclusions: these findings expand the plethora of relevant molecular targets for frataxin and may help to elucidate the yet unknown different roles that this protein exerts in iron regulation and metabolism.

Artificial Intelligence (AI) is one of the big hopes for the future of a positive revolution in the use of medical data to improve clinical routine and personalized medicine [...]

Bone marrow edema (BME) is the term given to the abnormal fluid signal seen within the bone marrow on magnetic resonance imaging (MRI). It usually indicates the presence of underlying pathology and is associated with a myriad of conditions/causes. However, it can be misleading, as in some cases, it may be associated with normal changes in the bone, especially during the growth period of childhood, and objective methods for assessment are lacking. In this work, learning models for BME detection were developed. Transfer learning was used to overcome the size limitations of the dataset, and two different regions of interest (ROI) were defined and compared to evaluate their impact on the performance of the model: bone segmention and intensity mask. The best model was obtained for the high intensity masking technique, which achieved a balanced accuracy of 0.792 ± 0.034. This study represents a comparison of different models and data regularization techniques for BME detection and showed promising results, even in the most difficult range of ages: children and adolescents. The application of machine learning methods will help to decrease the dependence on the clinicians, providing an initial stratification of the patients based on the probability of edema presence and supporting their decisions on the diagnosis.

The use of deep learning methods in medical imaging has been able to deliver promising results; however, the success of such models highly relies on large, properly annotated datasets. The annotation of medical images is a laborious, expensive, and time-consuming process. This difficulty is increased for the mutations status label since these require additional exams (usually biopsies) to be obtained. On the other hand, raw images, without annotations, are extensively collected as part of the clinical routine. This work investigated methods that could mitigate the labelled data scarcity problem by using both labelled and unlabelled data to improve the efficiency of predictive models. A semi-supervised learning (SSL) approach was developed to predict epidermal growth factor receptor (EGFR) mutation status in lung cancer in a less invasive manner using 3D CT scans.The proposed approach consists of combining a variational autoencoder (VAE) and exploiting the power of adversarial training, intending that the features extracted from unlabelled data to discriminate images can help in the classification task. To incorporate labelled and unlabelled images, adversarial training was used, extending a traditional variational autoencoder. With the developed method, a mean AUC of 0.701 was achieved with the best-performing model, with only 14% of the training data being labelled. This SSL approach improved the discrimination ability by nearly 7 percentage points over a fully supervised model developed with the same amount of labelled data, confirming the advantage of using such methods when few annotated examples are available.

Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses on the impact of label noise on the performance of learning models by examining the effect of random and class-dependent label noise on a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal is used to detect physiological changes and its quality can have a significant impact on the subsequent tasks, which makes PPG quality assessment a particularly good target for examining the impact of label noise in the field of biomedicine. Random and class-dependent label noise was introduced separately into the training set to emulate the errors associated with fatigue and bias in labeling data samples. We also tested different representations of the PPG, including features defined by domain experts, 1D raw signal and 2D image. Three different classifiers are tested on the noisy training data, including support vector machine (SVM), XGBoost, 1D Resnet and 2D Resnet, which handle three representations, respectively. The results showed that the two deep learning models were more robust than the two traditional machine learning models for both the random and class-dependent label noise. From the representation perspective, the 2D image shows better robustness compared to the 1D raw signal. The logits from three classifiers are also analyzed, the predicted probabilities intend to be more dispersed when more label noise is introduced. From this work, we investigated various factors related to label noise, including representations, label noise type, and data imbalance, which can be a good guidebook for designing more robust methods for label noise in future work.

Liquid biopsy is an emerging technology with a potential role in the screening and early detection of lung cancer. Several liquid biopsy-derived biomarkers have been identified and are currently under ongoing investigation. In this article, we review the available data on the use of circulating biomarkers for the early detection of lung cancer, focusing on the circulating tumor cells, circulating cell-free DNA, circulating micro-RNAs, tumor-derived exosomes, and tumor-educated platelets, providing an overview of future potential applicability in the clinical practice. While several biomarkers have shown exciting results, diagnostic performance and clinical applicability is still limited. The combination of different biomarkers, as well as their combination with other diagnostic tools show great promise, although further research is still required to define and validate the role of liquid biopsies in clinical practice.

Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances of survival, improving the cancer early detection capacity is crucial, for which computed tomography (CT) scans represent a key role. The manual evaluation of the CTs is a time-consuming task and computer-aided diagnosis (CAD) systems can help relieve that burden. The segmentation of the lung is one of the first steps in these systems, yet it is very challenging given the heterogeneity of lung diseases usually present and associated with cancer development. In our previous work, a segmentation model based on a ResNet34 and U-Net combination was developed on a cross-cohort dataset that yielded good segmentation masks for multiple pathological conditions but misclassified some of the lung nodules. The multiple datasets used for the model development were originated from different annotation protocols, which generated inconsistencies for the learning process, and the annotations are usually not adequate for lung cancer studies since they did not comprise lung nodules. In addition, the initial datasets used for training presented a reduced number of nodules, which was showed not to be enough to allow the segmentation model to learn to include them as a lung part. In this work, an objective protocol for the lung mask’s segmentation was defined and the previous annotations were carefully reviewed and corrected to create consistent and adequate ground-truth masks for the development of the segmentation model. Data augmentation with domain knowledge was used to create lung nodules in the cases used to train the model. The model developed achieved a Dice similarity coefficient (DSC) above 0.9350 for all test datasets and it showed an ability to cope, not only with a variety of lung patterns, but also with the presence of lung nodules as well. This study shows the importance of using consistent annotations for the supervised learning process, which is a very time-consuming task, but that has great importance to healthcare applications. Due to the lack of massive datasets in the medical field, which consequently brings a lack of wide representativity, data augmentation with domain knowledge could represent a promising help to overcome this limitation for learning models development.

Lung cancer is one of the most common causes of cancer-related mortality, and since the majority of cases are diagnosed when the tumor is in an advanced stage, the 5-year survival rate is dismally low. Nevertheless, the chances of survival can increase if the tumor is identified early on, which can be achieved through screening with computed tomography (CT). The clinical evaluation of CT images is a very time-consuming task and computed-aided diagnosis systems can help reduce this burden. The segmentation of the lungs is usually the first step taken in image analysis automatic models of the thorax. However, this task is very challenging since the lungs present high variability in shape and size. Moreover, the co-occurrence of other respiratory comorbidities alongside lung cancer is frequent, and each pathology can present its own scope of CT imaging appearances. This work investigated the development of a deep learning model, whose architecture consists of the combination of two structures, a U-Net and a ResNet34. The proposed model was designed on a cross-cohort dataset and it achieved a mean dice similarity coefficient (DSC) higher than 0.93 for the 4 different cohorts tested. The segmentation masks were qualitatively evaluated by two experienced radiologists to identify the main limitations of the developed model, despite the good overall performance obtained. The performance per pathology was assessed, and the results confirmed a small degradation for consolidation and pneumocystis pneumonia cases, with a DSC of 0.9015 ± 0.2140 and 0.8750 ± 0.1290, respectively. This work represents a relevant assessment of the lung segmentation model, taking into consideration the pathological cases that can be found in the clinical routine, since a global assessment could not detail the fragilities of the model.

Summary: Microorganisms evolved adaptive responses to survive stressful challenges in ever-changing environments. Understanding the relationships between the physiological/metabolic adjustments allowing cellular stress adaptation and gene expression changes being used by organisms to achieve such adjustments may significantly impact our ability to understand and/or guide evolution. Here, we studied those relationships during adaptation to various stress challenges in Saccharomyces cerevisiae, focusing on heat stress responses. We combined dozens of independent experiments measuring whole-genome gene expression changes during stress responses with a simplified kinetic model of central metabolism. We identified alternative quantitative ranges for a set of physiological variables in the model (production of ATP, trehalose, NADH, etc.) that are specific for adaptation to either heat stress or desiccation/rehydration. Our approach is scalable to other adaptive responses and could assist in developing biotechnological applications to manipulate cells for medical, biotechnological, or synthetic biology purposes. : Evolution selects coordinated adaptive changes in gene expression and metabolism that ensure survival to stress challenges. Pereira et al. identify quantitative ranges for those changes in a set of genes and physiological variables (production of ATP, trehalose, NADH, etc.) that are specific for adaptation to heat stress, desiccation/rehydration, or pH. Keywords: biological design principles, systems biology, computational biology, multilevel modeling, integrative biology, metabolism, optimization

Artificial intelligence (AI)-based solutions have revolutionized our world, using extensive datasets and computational resources to create automatic tools for complex tasks that, until now, have been performed by humans. Massive data is a fundamental aspect of the most powerful AI-based algorithms. However, for AI-based healthcare solutions, there are several socioeconomic, technical/infrastructural, and most importantly, legal restrictions, which limit the large collection and access of biomedical data, especially medical imaging. To overcome this important limitation, several alternative solutions have been suggested, including transfer learning approaches, generation of artificial data, adoption of blockchain technology, and creation of an infrastructure composed of anonymous and abstract data. However, none of these strategies is currently able to completely solve this challenge. The need to build large datasets that can be used to develop healthcare solutions deserves special attention from the scientific community, clinicians, all the healthcare players, engineers, ethicists, legislators, and society in general. This paper offers an overview of the data limitation in medical predictive models; its impact on the development of healthcare solutions; benefits and barriers of sharing data; and finally, suggests future directions to overcome data limitations in the medical field and enable AI to enhance healthcare. This perspective is dedicated to the technical requirements of the learning models, and it explains the limitation that comes from poor and small datasets in the medical domain and the technical options that try or can solve the problem related to the lack of massive healthcare data.

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Lung cancer late diagnosis has a large impact on the mortality rate numbers, leading to a very low five-year survival rate of 5%. This issue emphasises the importance of developing systems to support a diagnostic at earlier stages. Clinicians use Computed Tomography (CT) scans to assess the nodules and the likelihood of malignancy. Automatic solutions can help to make a faster and more accurate diagnosis, which is crucial for the early detection of lung cancer. Convolutional neural networks (CNN) based approaches have shown to provide a reliable feature extraction ability to detect the malignancy risk associated with pulmonary nodules. This type of approach requires a massive amount of data to model training, which usually represents a limitation in the biomedical field due to medical data privacy and security issues. Transfer learning (TL) methods have been widely explored in medical imaging applications, offering a solution to overcome problems related to the lack of training data publicly available. For the clinical annotations experts with a deep understanding of the complex physiological phenomena represented in the data are required, which represents a huge investment. In this direction, this work explored a TL method based on unsupervised learning achieved when training a Convolutional Autoencoder (CAE) using images in the same domain. For this, lung nodules from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) were extracted and used to train a CAE. Then, the encoder part was transferred, and the malignancy risk was assessed in a binary classification—benign and malignant lung nodules, achieving an Area Under the Curve (AUC) value of 0.936. To evaluate the reliability of this TL approach, the same architecture was trained from scratch and achieved an AUC value of 0.928. The results reported in this comparison suggested that the feature learning achieved when reconstructing the input with an encoder-decoder based architecture can be considered an useful knowledge that might allow overcoming labelling constraints.

Purpose: This study proposes to map the barriers to scaling the microfinance industry in the U.S., as it pertains to home maintenance and improvement for low-income households. The selected context of analysis is the American city of Baltimore, due to the city’s high need for housing repair and large percentage of residents with limited access to finance. Originality/Value: Most research has discarded microfinance as a viable option for a housing market solution in the U.S. This paper discusses how the market of microfinance for housing repair could improve its financial sustainability seizing the smaller dollar value of repair loans, relative to housing purchase, and the high and recurring need for repair. Design/methodology/approach: Qualitative research was conducted on how microfinance for housing repair works in Baltimore City, leveraging secondary government and private research, along with interviews with lenders and borrowers. Data were analyzed through PESTEL framework, describing the macro-environmental context. Findings: The market for Housing Microfinance (HM) loan products in Baltimore matches the academic literature. Similar market demands exist as they relate to an increasingly aging housing stock. Lender supply of financing seems “healthy”, but it is mostly from philanthropic or government sources favoring “affordability” over financial sustainability.

We analyse new genomic data (0.05-2.95x) from 14 ancient individuals from Portugal distributed from the Middle Neolithic (4200-3500 BC) to the Middle Bronze Age (1740-1430 BC) and impute genomewide diploid genotypes in these together with published ancient Eurasians. While discontinuity is evident in the transition to agriculture across the region, sensitive haplotype-based analyses suggest a significant degree of local hunter-gatherer contribution to later Iberian Neolithic populations. A more subtle genetic influx is also apparent in the Bronze Age, detectable from analyses including haplotype sharing with both ancient and modern genomes, D-statistics and Y-chromosome lineages. However, the limited nature of this introgression contrasts with the major Steppe migration turnovers within third Millennium northern Europe and echoes the survival of non-Indo-European language in Iberia. Changes in genomic estimates of individual height across Europe are also associated with these major cultural transitions, and ancestral components continue to correlate with modern differences in stature.

O objetivo do estudo foi verificar riscos da interação droga-nutriente nos idosos residentes em Instituição de Longa Permanência. Trata-se de estudo descritivo, de abordagem quantitativa, realizado em 73 idosos. A coleta dos dados ocorreu em 2008, através da análise dos prontuários, história dietética e avaliação do IMC. Os dados evidenciaram que os medicamentos mais utilizados foram do sistema nervoso e cardiovascular, totalizando 66% das prescrições. Entre 375 medicamentos prescritos, 166 fazem algum tipo de interação, 32,0% diminuem o efeito de absorção do fármaco quando há utilização de cafeína e 14,3% diminuem absorção de vitamina B12. A utilização de diversos medicamentos de uso contínuo pode acarretar prejuízo na absorção de nutrientes, aumentando o risco de desnutrição em idosos. Torna-se indispensável a ação da equipe de saúde, através da avaliação criteriosa dos medicamentos administrados, dietoterapia e a interação entre os mesmos, para beneficiar idosos com melhor aproveitamento da terapêutica e melhoria das condições nutricionais.El objetivo fue verificar el riesgo de interacciones fármaco-nutriente en los ancianos residentes en Institución de Larga Permanencia. Estudio descriptivo, cuantitativo, realizado en 73 ancianos. La recolección de datos se realizó en 2008 a través del análisis de los registros médicos, historia dietética y la evaluación del IMC. Los datos evidenciaron que los medicamentos más utilizados fueron del sistema nervioso y cardiovascular, totalizando el 66% de las prescripciones; entre los 375 medicamentos prescriptos, 166 hacen algún tipo de interacción, el 32,0% disminuye el efecto de absorción del fármaco cuando hay utilización de cafeína y el 14,3% disminuye la absorción de vitamina B12. La utilización de diversos medicamentos de uso continuo puede acarrear perjuicio en la absorción de nutrientes. Vuelve indispensable la acción del equipo de salud a través de una cuidadosa evaluación de los medicamentos, la dieta y la interacción entre ellos, para beneficiar a los ancianos con mejor aprovechamiento de la terapéutica.This study was aimed at verifying the risks of drug-nutrient interactions in the elderly residents of a Long-Term Care Institution. Descriptive study of quantitative approach, performed in 73 elderly people. Data collection occurred in 2008 through analysis of medical records, diet history and evaluation of the BMI. Data evidenced that the drugs more frequently used were the ones for nervous and cardiovascular systems, totaling approximately 66% of the prescriptions; among the 375 drugs prescribed, 166 make some type of interaction, 32.0% reduce the effect of drug absorption when there is use with caffeine and 14.3% reduce the B12 vitamin absorption. Taking several drugs of continuous use may cause damage to the absorption of nutrients. The action of the health team becomes vital, through careful evaluation of the administered drugs, diet and interaction between them, to benefit the elderly with a better use of the therapeutics and improvement of the nutritional conditions.

Os gestores modernos sofrem e muitas vezes reconhecem o sofrimento no trabalho, mas raramente manifestam insatisfação, por motivos que incluem desde insegurança até falta de clareza sobre o momento atual. Este trabalho busca analisar algumas das causas desse sofrimento e analisar a percepção dos gestores sobre a integração de aspectos da qualidade de vida no trabalho a suas vidas pessoais. A relevância do estudo justifica-se não somente pela insatisfação do indivíduo, que não compreende o fenômeno nem consegue lidar com suas causas, mas também pelo fato de que isso afeta a produtividade das organizações. Para averiguar a percepção dos gestores, foram analisados os discursos de 30 deles com relação aos fatores: satisfação, identificação com os objetivos da organização, relacionamento com os pares, com superiores e subordinados, relacionamento com a empresa, segurança e prazer, a partir de respostas a questionários. A conclusão é de que há, de fato, forte incoerência no discurso dos gestores, relativa à satisfação com o trabalho e à simultânea insatisfação com os sacrifícios que ele impõe às suas vidas pessoais.Modern managers suffer and often recognize this at work but they rarely show dissatisfaction for reasons that range from distrust to a lack of understanding of their feelings. Several reasons for this suffering were examined to analyze the perception of managers in relation to the integration of quality of life at work and in their personal lives. The importance of this study was related to the dissatisfaction that this lack of understanding produced in the individual who was incapable of dealing with the causes, and also to the detriment on organization productivity. Speeches made by 30 managers were analyzed concerning satisfaction, identification with organization objectives, relationships with their company, superiors, peers and subordinates as well as feelings of assurance and pleasure and then compared to their replies to questionnaires. A great discrepancy was found between these speeches and replies in relation to work satisfaction and the simultaneous dissatisfaction related to the sacrifice that work imposed on their personal lives.

Este ensaio tem como objetivo apresentar o software livre como objeto viável de estratégia de comercialização no mercado de software. A partir da análise de seus efeitos sobre as receitas e o market share das firmas dominantes, o F/LOSS (Free/Libre Open Source Software) emerge como alternativa de modelo de negócio nos segmentos em que o software livre apresenta vantagens competitivas sobre o software proprietário. Descrevemos as potencialidades e limitações, os aspectos tecnológicos, econômicos e sociológicos da organização da produção de empresas que comercializam produtos ou serviços relacionados ao F/LOSS. Utilizando-se a perspectiva da Economia dos Custos de Transação e da Economia da Informação, apresenta-se o modelo híbrido de desenvolvimento do F/LOSS nos mesmos moldes de um condomínio - em que a administração central coordena a ação coletiva, enquanto a comunidade, ao mesmo tempo em que integra o processo, monitora as ações da direção centralizada -, como estratégia competitiva alternativa aos modelos de desenvolvimento aberto (Bazar) e proprietário (Catedral).Free Open Source Software is described as viable software for commercialization. Considering the revenues and market shares of the dominant suppliers, this software emerges as an alternative business model for segments in which open source software presents competitive advantages over the traditional model. Potentials, limitations and technological, economic and sociological aspects of organizational structures of companies that produce products and services related to Free Open Source Software are described. From the transaction cost and information economy perspectives, a hybrid model to develop Free Open Source Software is presented which is structured according to the concept of a condominium. That is, a central administration coordinates collective action, while the community works and monitors the action of the central direction. This model may be considered as an alternative competitive strategy to peer production (Bazaar) and centralized (Cathedral) models.

Soil insects are very difficult to be managed. We reviewed the characterization of the CO2 as larval attractants to soil insects. Most studies were achieved with larvae of Diabrotica spp. First instar larvae used CO2 to find host plant. We discussed the possibilities of utilization of this attractant in pest management, including tactics like, to keep larvae far from of plants; to confuse their ability to find the host or to attract them to bait with insectides.As pragas de hábito subterrâneo estão entre as que apresentam maiores dificuldades de manejo. Revisouse a caracterização do CO2 como atraente larval de insetos de solo. A grande maioria dos estudos fora realizados com larvas de Diabrotica spp. Larvas de primeiro ínstar utilizam CO2 para localização da planta hospedeira. Discute-se a possibilidade de utilização deste atraente no manejo de pragas, o que inclui manter as larvas longe das plantas; confundi-las na habilidade de localizar o hospedeiro, ou em associação com inseticidas como isca.

The beetle Astylus variegatus (Germ.) (Coleoptera: Melyridae) is frequently found in flowers feeding on pollen. Responses of A. variegatus to volatile floral attractants were studied in common beans (Phaseolus vulgaris L.) fields. Traps originally designed to capture Diabrotica speciosa (Germ.) (Coleoptera: Chrysomelidae), consisted of plastic bottles (2 L) with 150 holes (5-mm diameter) yellow gold painted and containing inside a plastic strip (3.5 ´ 25 cm) with Lagenaria vulgaris (L.) powder (0.28% B cucurbitacin - feeding stimulant and arrestant for diabroticites) sprayed with carbaril insecticide. Treatments consisted of 1,4-dimethoxybenzene (one or two dispensers per trap), 1,4-dimethoxybenze + indole, 1,4-dimethoxybenzene + cinnameldehyde and control. Volatile average release rates (over ten days) was approximately 32 mg day-1 per dispenser under laboratory conditions. 1,4-dimethoxybenzene-lured traps caught significantly more beetles than the control, three and seven days after trap setting. Ten days after the onset of the experiment, there were no differences in number of beetles caught by treatments. Captures were higher in the 1,4-dimethoxybenzene + cinnamaldehyde treatment than in 1,4-dimethoxybenzene only in the first assessment. Adding indole to 1,4-dimethoxybenzene did not improve beetle captures.O besouro Astylus variegatus (Germ.) (Coleoptera: Melyridae) é freqüentemente encontrado em flores onde se alimenta de pólen. Respostas de A. variegatus a atraentes voláteis florais foram estudadas em campos de feijão, Phaseolus vulgaris L. Armadilhas, originalmente desenvolvidas para capturar Diabrotica speciosa (Germ.) (Coleoptera: Chrysomelidae), consistiram de garrafas plástica (2 L) com 150 perfurações (5 mm de diâmetro) pintadas com tinta amarelo ouro contendo no seu interior uma fita plástica (3,5 ´ 25,0 cm) com pó seco de frutos de Lagenaria vulgaris (L.) (0,28% de cucurbitacina B estimulante alimentar e arrestante para diabroticíneos) pulverizados com inseticida carbaril. Os tratamentos foram: 1,4-dimetoxibenzeno (um ou dois liberadores por armadilha); 1,4-dimetoxibenzeno + indol; 1,4-dimetoxibenzeno + cinamaldeído e testemunha (sem volátil). As taxas de liberação dos semioquímicos (por 10 dias) foram de aproximadamente 32 mg dia-1 por liberador em condições de laboratório. Armadilhas iscadas com 1,4-dimetoxibenzeno capturaram mais insetos que a testemunha, três e sete dias após instalação das armadilhas. Dez dias após o início dos experimentos, não foram verificadas diferenças entre os tratamentos, no número de besouros capturados. Capturas foram maiores no tratamento com 1,4-dimetoxibenzeno + cinamaldeído do que no 1,4-dimetoxibenzeno sozinho na primeira avaliação. Adição do indole ao 1,4-dimetoxibenzeno não aumentou as capturas.