Coleção de Artigos Acadêmicos

URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3227

Navegar

Resultados da Pesquisa

Agora exibindo 1 - 10 de 476

Identification of segregated regions in the functional brain connectome of autistic patients by a combination of fuzzy spectral clustering and entropy analysis
(2016) Sato, João Ricardo; Balardin, Joana; MACIEL CALEBE VIDAL; André Fujita
Background: Several neuroimaging studies support the model of abnormal development of brain connectivity in patients with autism-spectrum disorders (ASD). In this study, we aimed to test the hypothesis of reduced functional network segregation in autistic patients compared with controls. Methods: Functional MRI data from children acquired under a resting-state protocol (Autism Brain Imaging Data Exchange [ABIDE]) were submitted to both fuzzy spectral clustering (FSC) with entropy analysis and graph modularity analysis. Results: We included data from 814 children in our analysis. We identified 5 regions of interest comprising the motor, temporal and occipito-temporal cortices with increased entropy (p < 0.05) in the clustering structure (i.e., more segregation in the controls). Moreover, we noticed a statistically reduced modularity (p < 0.001) in the autistic patients compared with the controls. Significantly reduced eigenvector centrality values (p < 0.05) in the patients were observed in the same regions that were identified in the FSC analysis. Limitations: There is considerable heterogeneity in the fMRI acquisition protocols among the sites that contributed to the ABIDE data set (e.g., scanner type, pulse sequence, duration of scan and resting-state protocol). Moreover, the sites differed in many variables related to sample characterization (e.g., age, IQ and ASD diagnostic criteria). Therefore, we cannot rule out the possibility that additional differences in functional network organization would be found in a more homogeneous data sample of individuals with ASD. Conclusion: Our results suggest that the organization of the whole-brain functional network in patients with ASD is different from that observed in controls, which implies a reduced modularity of the brain functional networks involved in sensorimotor, social, affective and cognitive processing.
A Statistical Method to Distinguish Functional Brain Networks
(2017) Fujita, André; MACIEL CALEBE VIDAL; Takahashi, Daniel Y.
One major problem in neuroscience is the comparison of functional brain networks of different populations, e.g., distinguishing the networks of controls and patients. Traditional algorithms are based on search for isomorphism between networks, assuming that they are deterministic. However, biological networks present randomness that cannot be well modeled by those algorithms. For instance, functional brain networks of distinct subjects of the same population can be different due to individual characteristics. Moreover, networks of subjects from different populations can be generated through the same stochastic process. Thus, a better hypothesis is that networks are generated by random processes. In this case, subjects from the same group are samples from the same random process, whereas subjects from different groups are generated by distinct processes. Using this idea, we developed a statistical test called ANOGVA to test whether two or more populations of graphs are generated by the same random graph model. Our simulations' results demonstrate that we can precisely control the rate of false positives and that the test is powerful to discriminate random graphs generated by different models and parameters. The method also showed to be robust for unbalanced data. As an example, we applied ANOGVA to an fMRI dataset composed of controls and patients diagnosed with autism or Asperger. ANOGVA identified the cerebellar functional sub-network as statistically different between controls and autism (p < 0.001).
Performance Measurement in a Brazilian Clinical Trials Unit
(2021) Aquino, Thomaz Martins de; Bonizio, Roni Cleber; Padua, Silvia Ines Dallavalle de; Coelho, Eduardo Barbosa; Faustino, Gabriela Gimenez
Background: There is growing interest on costs of clinical trials; critical topic for business decision making; therefore, the aim of this work is to identify how a successful Brazilian case measures its economic performance even with restriction regarding its accounting data. Methods: Single case qualitative method. Interviews with four people of different hierarchical levels and the analysis of the 2005 balance sheet, payrolls and payment slips were carried out. Results: Besides indicating how the clinical research unit of the case measures its results, a diagram of how other units and organizations could follow such procedure to carry out their own performance measurement was pointed out as well. Conclusion: The use of contribution margin and break-even point for the performance calculation benefited the managerial decision-making of the unit studied, serving as basis for its own strategy and use of its idleness. This is a reference model for decision-making of managers in other research units.
How do transaction costs, capabilities and networks influence the procurement strategies of small agri-food firms? Evidence from the wine industry
(2021) BRUNO VARELLA MIRANDA; Ross, Brent; Franken, Jason; Gomez, Miguel
Purpose – The purpose of this study is to disentangle the drivers of adoption of procurement strategies in situations where small agri-food firms deal with constrained organizational choices. More specifically, the authors investigate the role of transaction costs, capabilities and networks in the definition of feasible “make or-buy” choices in emerging wine regions. Design/methodology/approach – This article analyzes a unique dataset of small wineries from five US states: Illinois, Michigan, Missouri, New York and Vermont. The reported results derive from both a hurdle model (i.e. a probit model and a truncated regression model) and a tobit model. Findings – The results suggest the importance of trust as a replacement for formal governance structures whenever small firms deal with highly constrained sets of organizational choices. On the other hand, the level of dependence on a limited mix of winegrape varieties and the perception that these varieties are fundamental in building legitimacy help to explain higher rates of vertical integration. Originality/value – This study is important because it sheds light on organizational constraints that affect millions of farmers across the globe. The study of “make-or-buy” decisions in agri-food supply chains has mostly relied on the implicit assumption that all organizational choices are available to every firm. Nevertheless, limited capabilities and the participation in low-density networks may constrain the ability of a firm to adopt a governance mechanism. Stated organizational preferences and actual organizational choices may thus differ.
Primary care coverage and individual health: evidence from a likelihood model using biomarkers in Brazil
(2021) Postali, Fernando Antonio Slaibe; Diaz, Maria Dolores Montoya; Ferreira-Batista, Natalia Nunes; Teixeira, Adriano Dutra; Moreno-Serra, Rodrigo
Background Although the use of biomarkers to assess health outcomes has recently gained momentum, literature is still scarce for low- to middle-income countries. This paper explores the relationship between primary care coverage and individual health in Brazil using a dataset of blood-based biomarkers collected by the Brazilian National Health Survey. Both survey data and laboratory results were crossed with coverage data from the Family Health Strategy (ESF) program, the most important primary care program in Brazil; the coverage measures aim to capture both direct (household) and indirect (spill-over) effects. Methods The empirical strategy used a probit model to estimate the relationship between ESF program coverage and the likelihood of abnormal biomarker levels while controlling for a rich set of individual and household characteristics based on data from the national survey. Results Household ESF coverage was associated with a lower likelihood of abnormal results for biomarkers related to anemia (marginal effect between − 2.16 and − 2.18 percentage points), kidney failure (between − 1.01 and − 1.19 p.p.), and arterial hypertension (between − 1.48 and − 1.64 p.p). The likelihood of abnormal levels of white blood cells and thrombocytes was negatively related to primary care coverage (marginal effect between − 1.8 and − 2 p.p.). The spillover effects were relevant for kidney failure and arterial hypertension, depending on the regional level. Although not sensitive to household coverage, diabetes mellitus was negatively associated with the state supply of primary care, and abnormal cholesterol levels did not present any relationship with ESF program coverage. Conclusions The presence of spillover effects of ESF program coverage regarding these conditions reveals that the strengthening of primary care by increasing the household registration and the regional density of ESF teams is an efficient strategy to address important comorbidities.
Using bundling to visualize multivariate urban mobility structure patterns in the São Paulo metropolitan area
(2021) Martins, Tallys G.; Lago, Nelson; Santana, Eduardo F. Z.; Telea, Alexandru; Kon, Fabio; Souza, Higor A. de
Internet-based technologies such as IoT, GPS-based systems, and cellular networks enable the collection of geolocated mobility data of millions of people in large metropolitan areas. In addition, large, public datasets are made available on the Internet by open government programs, providing ways for citizens, NGOs, scientists, and public managers to perform a multitude of data analysis with the goal of better understanding the city dynamics to provide means for evidence-based public policymaking. However, it is challenging to visualize huge amounts of data from mobility datasets. Plotting raw trajectories on a map often causes data occlusion, impairing the visual analysis. Displaying the multiple attributes that these trajectories come with is an even larger challenge. One approach to solve this problem is trail bundling, which groups motion trails that are spatially close in a simplified representation. In this paper, we augment a recent bundling technique to support multi-attribute trail datasets for the visual analysis of urban mobility. Our case study is based on the travel survey from the São Paulo Metropolitan Area, which is one of the most intense traffic areas in the world. The results show that bundling helps the identification and analysis of various mobility patterns for different data attributes, such as peak hours, social strata, and transportation modes.
SNA-Based Reasoning for Multi-Agent Team Composition
(2015) ANDRE FILIPE DE MORAES BATISTA; Marietto, Maria das Graças Bruno
The social network analysis (SNA), branch of complex systems can be used in the construction of multi agent systems. This paper proposes a study of how social network analysis can assist in modeling multi agent systems, while addressing similarities and differences between the two theories. We built a prototype of multi-agent systems for resolution of tasks through the formation of teams of agents that are formed on the basis of the social network established between agents. Agents make use of performance indicators to assess when should change their social network to maximize the participation in teams.
Neonatal mortality prediction with routinely collected data: a machine learning approach
(2021) ANDRE FILIPE DE MORAES BATISTA; Diniz, Carmen S. G.; Bonilha, Eliana A.; Kawachi, Ichiro; Chiavegatto Filho, Alexandre D. P.
Background: Recent decreases in neonatal mortality have been slower than expected for most countries. This study aims to predict the risk of neonatal mortality using only data routinely available from birth records in the largest city of the Americas. Methods: A probabilistic linkage of every birth record occurring in the municipality of São Paulo, Brazil, between 2012 e 2017 was performed with the death records from 2012 to 2018 (1,202,843 births and 447,687 deaths), and a total of 7282 neonatal deaths were identified (a neonatal mortality rate of 6.46 per 1000 live births). Births from 2012 and 2016 (N = 941,308; or 83.44% of the total) were used to train five different machine learning algorithms, while births occurring in 2017 (N = 186,854; or 16.56% of the total) were used to test their predictive performance on new unseen data. Results: The best performance was obtained by the extreme gradient boosting trees (XGBoost) algorithm, with a very high AUC of 0.97 and F1-score of 0.55. The 5% births with the highest predicted risk of neonatal death included more than 90% of the actual neonatal deaths. On the other hand, there were no deaths among the 5% births with the lowest predicted risk. There were no significant differences in predictive performance for vulnerable subgroups. The use of a smaller number of variables (WHO’s five minimum perinatal indicators) decreased overall performance but the results still remained high (AUC of 0.91). With the addition of only three more variables, we achieved the same predictive performance (AUC of 0.97) as using all the 23 variables originally available from the Brazilian birth records. Conclusion: Machine learning algorithms were able to identify with very high predictive performance the neonatal mortality risk of newborns using only routinely collected data.
Predictors of tooth loss: A machine learning approach
(2021) Elani, Hawazin W.; ANDRE FILIPE DE MORAES BATISTA; W. Murray Thomson; Kawachi, Ichiro; Chiavegatto Filho, Alexandre D. P.
Introduction Little is understood about the socioeconomic predictors of tooth loss, a condition that can negatively impact individual’s quality of life. The goal of this study is to develop a machine-learning algorithm to predict complete and incremental tooth loss among adults and to compare the predictive performance of these models. Methods We used data from the National Health and Nutrition Examination Survey from 2011 to 2014. We developed multiple machine-learning algorithms and assessed their predictive performances by examining the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values. Results The extreme gradient boosting trees presented the highest performance in the prediction of edentulism (AUC = 88.7%; 95%CI: 87.1, 90.2), the absence of a functional dentition (AUC = 88.3% 95%CI: 87.3,89.3) and for predicting missing any tooth (AUC = 83.2%; 95%CI, 82.0, 84.4). Although, as expected, age and routine dental care emerged as strong predictors of tooth loss, the machine learning approach identified additional predictors, including socioeconomic conditions. Indeed, the performance of models incorporating socioeconomic characteristics was better at predicting tooth loss than those relying on clinical dental indicators alone. Conclusions Future application of machine-learning algorithm, with longitudinal cohorts, for identification of individuals at risk for tooth loss could assist clinicians to prioritize interventions directed toward the prevention of tooth loss.
Cause-specific mortality prediction in older residents of São Paulo, Brazil: a machine learning approach
(2021) Nascimento, Carla Ferreira do; Hellen Geremias dos Santos; ANDRE FILIPE DE MORAES BATISTA; Lay, Alejandra Andrea Roman; Duarte, Yeda Aparecida Oliveira
Background: Populational ageing has been increasing in a remarkable rate in developing countries. In this scenario, preventive strategies could help to decrease the burden of higher demands for healthcare services. Machine learning algorithms have been increasingly applied for identifying priority candidates for preventive actions, presenting a better predictive performance than traditional parsimonious models. Methods: Data were collected from the Health, Well Being and Aging (SABE) Study, a representative sample of older residents of São Paulo, Brazil. Machine learning algorithms were applied to predict death by diseases of respiratory system (DRS), diseases of circulatory system (DCS), neoplasms and other specific causes within 5 years, using socioeconomic, demographic and health features. The algorithms were trained in a random sample of 70% of subjects, and then tested in the other 30% unseen data. Results: The outcome with highest predictive performance was death by DRS (AUC−ROC = 0.89), followed by the other specific causes (AUC−ROC = 0.87), DCS (AUC−ROC = 0.67) and neoplasms (AUC−ROC = 0.52). Among only the 25% of individuals with the highest predicted risk of mortality from DRS were included 100% of the actual cases. The machine learning algorithms with the highest predictive performance were light gradient boosted machine and extreme gradient boosting. Conclusion: The algorithms had a high predictive performance for DRS, but lower for DCS and neoplasms. Mortality prediction with machine learning can improve clinical decisions especially regarding targeted preventive measures for older individuals.

Coleção de Artigos Acadêmicos

Navegar

Filtros

Configurações

Ordenar por

Resultados por página

Resultados da Pesquisa