Thomas Tabosa de Oliveira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thomas Tabosa de Oliveira has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Patricia Takako Endo
Programa de Pós-Graduação em Engenharia da Computação (PPGEC), Universidade de Pernambuco (UPE), Recife, Brazil
2 shared publications - Sebastião Rogério da Silva Neto
Universidade de Pernambuco
2 shared publications Theo Lynn
Affiliation Dublin City University, Dublin, Ireland
2 shared publicationsElyda Laisa Soares Xavier Freitas
Universidade Federal de Pernambuco / Universidade de Pernambuco
1 shared publicationFernando da Fonseca de Souza
Universidade Federal de Pernambuco
1 shared publication- Geovanne Oliveira Alves
University of Pernambuco, Caruaru, PE, Brazil
1 shared publication
Latest Publications
- Open Access
- 13 January 2022
- Published by Public Library of Science (PLoS) in PLOS Neglected Tropical Diseases
- Vol. 16 (1) , e0010061
Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: A systematic review
Background: Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms, inaccurate serologic tests resulting from cross-reaction and co-infection with other arboviruses.Objective: The goal of this paper is to present evidence on the state of the art of studies investigating the automatic classification of arboviral diseases to support clinical diagnosis based on Machine Learning (ML) and Deep Learning (DL) models.Method: We carried out a Systematic Literature Review (SLR) in which Google Scholar was searched to identify key papers on the topic. From an initial 963 records (956 from string-based search and seven from a single backward snowballing procedure), only 15 relevant papers were identified.Results: Results show that current research is focused on the binary classification of Dengue, primarily using tree-based ML algorithms. Only one paper was identified using DL. Five papers presented solutions for multi-class problems, covering Dengue (and its variants) and Chikungunya. No papers were identified that investigated models to differentiate between Dengue, Chikungunya, and Zika.Conclusions: The use of an efficient clinical decision support system for arboviral diseases can improve the quality of the entire clinical process, thus increasing the accuracy of the diagnosis and the associated treatment. It should help physicians in their decision-making process and, consequently, improve the use of resources and the patient’s quality of life.
- 13 January 2022
- Published by Public Library of Science (PLoS) in PLOS Neglected Tropical Diseases
- Vol. 16 (1) , e0010061
Open AccessMachine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: A systematic review
Background: Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms, inaccurate serologic tests resulting from cross-reaction and co-infection with other arboviruses.Objective: The goal of this paper is to present evidence on the state of the art of studies investigating the automatic classification of arboviral diseases to support clinical diagnosis based on Machine Learning (ML) and Deep Learning (DL) models.Method: We carried out a Systematic Literature Review (SLR) in which Google Scholar was searched to identify key papers on the topic. From an initial 963 records (956 from string-based search and seven from a single backward snowballing procedure), only 15 relevant papers were identified.Results: Results show that current research is focused on the binary classification of Dengue, primarily using tree-based ML algorithms. Only one paper was identified using DL. Five papers presented solutions for multi-class problems, covering Dengue (and its variants) and Chikungunya. No papers were identified that investigated models to differentiate between Dengue, Chikungunya, and Zika.Conclusions: The use of an efficient clinical decision support system for arboviral diseases can improve the quality of the entire clinical process, thus increasing the accuracy of the diagnosis and the associated treatment. It should help physicians in their decision-making process and, consequently, improve the use of resources and the patient’s quality of life.
- Open Access
- 1 April 2021
- Published by Revista de Engenharia e Pesquisa Aplicada in Revista de Engenharia e Pesquisa Aplicada
- Vol. 6 (3) , 12-20
Estudo Comparativo de Técnicas de Previsão para Casos de Dengue
A dengue é uma infecção viral que se espalha rapidamente e é endêmica em mais de 100 países tropicais e subtropicais da África, América e regiões da Ásia-Pacífico. Geralmente, a epidemiologia da dengue é influenciada por uma complexa interação de fatores que incluem rápida urbanização e aumento da densidade populacional, capacidade dos sistemas de saúde, eficácia dos sistemas de controle de vetores, limpeza urbana etc. No Brasil que é considerado um país tropical, há uma incidência de casos crescente nos últimos anos, em específico na capital Pernambucana Recife há um ambiente propício para o aumento expressivo dos casos de dengue como são apresentados pelo Boletim Epidemiológico da Secretaria de Vigilância em Saúde do Ministério da Saúde. O presente trabalho apresenta um estudo comparativo de técnicas de Mineração de Dados seguindo a abordagem CRISP-DM, para um modelo de previsão de casos de Dengue no Recife-PE.
- 1 April 2021
- Published by Revista de Engenharia e Pesquisa Aplicada in Revista de Engenharia e Pesquisa Aplicada
- Vol. 6 (3) , 12-20
Open AccessEstudo Comparativo de Técnicas de Previsão para Casos de Dengue
A dengue é uma infecção viral que se espalha rapidamente e é endêmica em mais de 100 países tropicais e subtropicais da África, América e regiões da Ásia-Pacífico. Geralmente, a epidemiologia da dengue é influenciada por uma complexa interação de fatores que incluem rápida urbanização e aumento da densidade populacional, capacidade dos sistemas de saúde, eficácia dos sistemas de controle de vetores, limpeza urbana etc. No Brasil que é considerado um país tropical, há uma incidência de casos crescente nos últimos anos, em específico na capital Pernambucana Recife há um ambiente propício para o aumento expressivo dos casos de dengue como são apresentados pelo Boletim Epidemiológico da Secretaria de Vigilância em Saúde do Ministério da Saúde. O presente trabalho apresenta um estudo comparativo de técnicas de Mineração de Dados seguindo a abordagem CRISP-DM, para um modelo de previsão de casos de Dengue no Recife-PE.
- 15 September 2020
- Published by Sociedade Brasileira de Computação
- p. 87-92
Configuração de hyper-parâmetros de modelos deep learning para auxílio no pós-diagnóstico de Tuberculose
A Tuberculose (TB) é reconhecida como a doença mais mortal do mundo, segundo a World Health Organization (WHO), sendo umas das dez maiores causas de morte no mundo, além de ser a principal causa de morte de pessoas HIV-positivas. O Brasil é um dos países com alta carga de TB, e uma das maiores taxas de mortalidade do país encontra-se no estado do Amazonas. O objetivo deste trabalho é analisar modelos de deep learning (DL) para auxiliar no pós-diagnóstico de TB, predizendo a gravidade da doença no paciente. Dois modelos de DL são propostos e a técnica de Grid-search é aplicada para definir as configurações com os melhores desempenhos. Os modelos de DL apresentam resultados interessantes, com uma configuração da DL totalmente conectada atingindo 83,4% de especificidade.
- 15 September 2020
- Published by Sociedade Brasileira de Computação
- p. 87-92
Configuração de hyper-parâmetros de modelos deep learning para auxílio no pós-diagnóstico de Tuberculose
A Tuberculose (TB) é reconhecida como a doença mais mortal do mundo, segundo a World Health Organization (WHO), sendo umas das dez maiores causas de morte no mundo, além de ser a principal causa de morte de pessoas HIV-positivas. O Brasil é um dos países com alta carga de TB, e uma das maiores taxas de mortalidade do país encontra-se no estado do Amazonas. O objetivo deste trabalho é analisar modelos de deep learning (DL) para auxiliar no pós-diagnóstico de TB, predizendo a gravidade da doença no paciente. Dois modelos de DL são propostos e a técnica de Grid-search é aplicada para definir as configurações com os melhores desempenhos. Os modelos de DL apresentam resultados interessantes, com uma configuração da DL totalmente conectada atingindo 83,4% de especificidade.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Platform for monitoring and clinical diagnosis of arboviruses using computational models
As part of SDG, the members of the UN aim to end epidemics of neglected tropical diseases by 2030. These include wide range communicable diseases that prevail in tropical and subtropical conditions. These diseases are present in over 149 countries worldwide and are a significant burden on health systems and economies. One major category of neglected tropical disease are arthropod-borne viruses or arboviruses including West Nile virus, yellow fever, dengue, chikungunya and Zika. Arboviruses spread rapidly and as they present very similar symptoms, it is hard to diagnose and select the best treatment. The use of machine learning for the diagnosis and prognosis of these diseases has become increasingly common however there is a paucity of research on deep learning and associated decision support platforms for frontline staff. This work-in-progress proposes a platform for arbovirus monitoring and clinical diagnosis using deep learning models.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Platform for monitoring and clinical diagnosis of arboviruses using computational models
As part of SDG, the members of the UN aim to end epidemics of neglected tropical diseases by 2030. These include wide range communicable diseases that prevail in tropical and subtropical conditions. These diseases are present in over 149 countries worldwide and are a significant burden on health systems and economies. One major category of neglected tropical disease are arthropod-borne viruses or arboviruses including West Nile virus, yellow fever, dengue, chikungunya and Zika. Arboviruses spread rapidly and as they present very similar symptoms, it is hard to diagnose and select the best treatment. The use of machine learning for the diagnosis and prognosis of these diseases has become increasingly common however there is a paucity of research on deep learning and associated decision support platforms for frontline staff. This work-in-progress proposes a platform for arbovirus monitoring and clinical diagnosis using deep learning models.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2161-377X, 190-191
Learning Analytics: A Brief Overview about Applications and its Advantages
Learning Analytics (LA) is concerned with the use of data resulting from students' interaction with Learning Management Systems (LMS) to carry out analyses that can help students and teachers to understand and evaluate the learning process. However, several works on the subject only expose future expectations of what LA applications can perform. Thus, this paper aims at finding out practical results of LA and if its use has improved teaching and learning.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2161-377X, 190-191
Learning Analytics: A Brief Overview about Applications and its Advantages
Learning Analytics (LA) is concerned with the use of data resulting from students' interaction with Learning Management Systems (LMS) to carry out analyses that can help students and teachers to understand and evaluate the learning process. However, several works on the subject only expose future expectations of what LA applications can perform. Thus, this paper aims at finding out practical results of LA and if its use has improved teaching and learning.