Carlos Eduardo Pedreira

Prof. Carlos Eduardo Pedreira

Federal University of Rio de Janeiro, Rio de Janeiro, Brazil

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2022 in Artificial Intelligence Review
Verified
Journal Article
Closed access
PDF file
VCVinícius G. Costa
Vinícius G. Costa
CPCarlos Eduardo Pedreira
Carlos Eduardo Pedreira

1 September 2019 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
LML.O. Moraes
L.O. Moraes
CPCarlos Eduardo Pedreira
Carlos Eduardo Pedreira
SBS. Barrena
S. Barrena
ALA. Lopez
A. Lopez
AOAlberto Orfao
Alberto Orfao

21 March 2022 in Cancers
Verified
Journal Article
Open access
PDF file
NBNienke Brouwer
Nienke Brouwer
SMSergio Matarraz
Sergio Matarraz
SNStefan Nierkens
Stefan Nierkens
MHMattias Hofmans
Mattias Hofmans
MNMichaela Nováková
Michaela Nováková
OCon behalf of the EuroFlow Consortium
on behalf of the EuroFlow Consortium
Acute megakaryoblastic leukemia (AMKL) is a rare and heterogeneous subtype of acute myeloid leukemia (AML). We evaluated the immunophenotypic profile of 72 AMKL and 114 non-AMKL AML patients using the EuroFlow AML panel. Univariate and multivariate/multidimensional analyses were performed to identify most relevant markers contributing to the diagnosis of AMKL. AMKL patients were subdivided into transient abnormal myelopoiesis (TAM), myeloid leukemia associated with Down syndrome (ML-DS), AML—not otherwise specified with megakaryocytic differentiation (NOS-AMKL), and AMKL—other patients (AML patients with other WHO classification but with flowcytometric features of megakaryocytic differentiation). Flowcytometric analysis showed good discrimination between AMKL and non-AMKL patients based on differential expression of, in particular, CD42a.CD61, CD41, CD42b, HLADR, CD15 and CD13. Combining CD42a.CD61 (positive) and CD13 (negative) resulted in a sensitivity of 71% and a specificity of 99%. Within AMKL patients, TAM and ML-DS patients showed higher frequencies of immature CD34+/CD117+ leukemic cells as compared to NOS-AMKL and AMKL-Other patients. In addition, ML-DS patients showed a significantly higher expression of CD33, CD11b, CD38 and CD7 as compared to the other three subgroups, allowing for good distinction of these patients. Overall, our data show that the EuroFlow AML panel allows for straightforward diagnosis of AMKL and that ML-DS is associated with a unique immunophenotypic profile.

1 July 2017 in Neural Networks
Verified
Journal Article
Closed access
HCHugo C.C. Carneiro
Hugo C.C. Carneiro
CPCarlos Eduardo Pedreira
Carlos Eduardo Pedreira
FFFelipe M.G. França
Felipe M.G. França
PLPRISCILA Machado Vieira LIMA
PRISCILA Machado Vieira LIMA

1 January 2019 in Neural Computation
Verified
Journal Article
Closed access
HCHugo C. C. Carneiro
Hugo C. C. Carneiro
CPCarlos Eduardo Pedreira
Carlos Eduardo Pedreira
FFFelipe M. G. França
Felipe M. G. França
PLPRISCILA Machado Vieira LIMA
PRISCILA Machado Vieira LIMA
The Wilkie, Stoneham, and Aleksander recognition device (WiSARD) n -tuple classifier is a multiclass weightless neural network capable of learning a given pattern in a single step. Its architecture is determined by the number of classes it should discriminate. A target class is represented by a structure called a discriminator, which is composed of N RAM nodes, each of them addressed by an n -tuple. Previous studies were carried out in order to mitigate an important problem of the WiSARD n -tuple classifier: having its RAM nodes saturated when trained by a large data set. Finding the VC dimension of the WiSARD n -tuple classifier was one of those studies. Although no exact value was found, tight bounds were discovered. Later, the bleaching technique was proposed as a means to avoid saturation. Recent empirical results with the bleaching extension showed that the WiSARD n -tuple classifier can achieve high accuracies with low variance in a great range of tasks. Theoretical studies had not been conducted with that extension previously. This work presents the exact VC dimension of the basic two-class WiSARD n -tuple classifier, which is linearly proportional to the number of RAM nodes belonging to a discriminator, and exponentially to their addressing tuple length, precisely N(2n-1)+1 . The exact VC dimension of the bleaching extension to the WiSARD n -tuple classifier, whose value is the same as that of the basic model, is also produced. Such a result confirms that the bleaching technique is indeed an enhancement to the basic WiSARD n -tuple classifier as it does no harm to the generalization capability of the original paradigm. The Wilkie, Stoneham, and Aleksander recognition device (WiSARD) n -tuple classifier is a multiclass weightless neural network capable of learning a given pattern in a single step. Its architecture is determined by the number of classes it should discriminate. A target class is represented by a structure called a discriminator, which is composed of N RAM nodes, each of them addressed by an n -tuple. Previous studies were carried out in order to mitigate an important problem of the WiSARD n -tuple classifier: having its RAM nodes saturated when trained by a large data set. Finding the VC dimension of the WiSARD n -tuple classifier was one of those studies. Although no exact value was found, tight bounds were discovered. Later, the bleaching technique was proposed as a means to avoid saturation. Recent empirical results with the bleaching extension showed that the WiSARD n -tuple classifier can achieve high accuracies with low variance in a great range of tasks. Theoretical studies had not been conducted with that extension previously. This work presents the exact VC dimension of the basic two-class WiSARD n -tuple classifier, which is linearly proportional to the number of RAM nodes belonging to a discriminator, and exponentially to their addressing tuple length, precisely N(2n-1)+1 . The exact VC dimension of the bleaching extension to the WiSARD n -tuple classifier, whose value is the same as that of the basic model, is also produced. Such a result confirms that the bleaching technique is indeed an enhancement to the basic WiSARD n -tuple classifier as it does no harm to the generalization capability of the original paradigm. The Wilkie, Stoneham, and Aleksander recognition device (WiSARD) n -tuple classifier is a multiclass weightless neural network capable of learning a given pattern in a single step. Its architecture is determined by the number of classes it should discriminate. A target class is represented by a structure called a discriminator, which is composed of N RAM nodes, each of them addressed by an n -tuple. Previous studies were carried out in order to mitigate an important problem of the WiSARD n -tuple classifier: having its RAM nodes saturated when trained by a large data set. Finding the VC dimension of the WiSARD n -tuple classifier was one of those studies. Although no exact value was found, tight bounds were discovered. Later, the bleaching technique was proposed as a means to avoid saturation. Recent empirical results with the bleaching extension showed that the WiSARD n -tuple classifier can achieve high accuracies with low variance in a great range of tasks. Theoretical studies had not been conducted with that extension previously. This work presents the exact VC dimension of the basic two-class WiSARD n -tuple classifier, which is linearly proportional to the number of RAM nodes belonging to a discriminator, and exponentially to their addressing tuple length, precisely N(2n-1)+1 . The exact VC dimension of the bleaching extension to the WiSARD n -tuple classifier, whose value is the same as that of the basic model, is also produced. Such a result confirms that the bleaching technique is indeed an enhancement to the basic WiSARD n -tuple classifier as it does no harm to the generalization capability of the original paradigm.

31 January 2023 in Cancers
Verified
Journal Article
Open access
PDF file
AVAlicia Landeira Viñuela
Alicia Landeira Viñuela
MAMiguel Alcoceba
Miguel Alcoceba
ANAlmudena Navarro-Bailón
Almudena Navarro-Bailón
CACarlota Arias-Hidalgo
Carlota Arias-Hidalgo
PJPablo Juanes-Velasco
Pablo Juanes-Velasco
Manuel FuentesManuel Fuentes
Manuel Fuentes
Chronic lymphocytic leukemia (CLL) is the most common leukemia in the Western world. Studies of CLL antibody reactivity have shown differential targets to autoantigens and antimicrobial molecular motifs that support the current hypothesis of CLL pathogenesis. Methods: In this study, we conducted a quantitative serum analysis of 7 immunoglobulins in CLL and monoclonal B-cell lymphocytosis (MBL) patients (bead-suspension protein arrays) and a serological profile (IgG and IgM) study of autoantibodies and antimicrobial antigens (protein microarrays). Results: Significant differences in the IgA levels were observed according to disease progression and evolution as well as significant alterations in IgG1 according to IGHV mutational status. More representative IgG autoantibodies in the cohort were against nonmutagenic proteins and IgM autoantibodies were against vesicle proteins. Antimicrobial IgG and IgM were detected against microbes associated with respiratory tract infections. Conclusions: Quantitative differences in immunoglobulin serum levels could be potential biomarkers for disease progression. In the top 5 tumoral antigens, we detected autoantibodies (IgM and IgG) against proteins related to cell homeostasis and metabolism in the studied cohort. The top 5 microbial antigens were associated with respiratory and gastrointestinal infections; moreover, the subsets with better prognostics were characterized by a reactivation of Cytomegalovirus. The viral humoral response could be a potential prognosis biomarker for disease progression.