Márcio Eloi Colombo Filho
Research Interests
Márcio Eloi Colombo Filho has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Domingos Alves
Ribeirao Preto Medical School, University of Sao Paulo, Ribeirao Preto, Brazil
4 shared publications - Filipe Andrade Bernardi
Ribeirão Preto Medical School, University of São Paulo
4 shared publications - Têmis Maria Félix
Medical Genetics Service, Hospital de Clínicas de Porto Alegre, Porto Alegre, Brazil
3 shared publications - Vinícius Costa Lima
Ribeirao Preto Medical School, University of Sao Paulo, Ribeirao Preto, Brazil
3 shared publications - Diego Bettiol Yamada
Ribeirao Preto Medical School, University of Sao Paulo, Ribeirao Preto, Brazil
2 shared publications - Isabelle Carvalho
Albert Einstein Israelite Hospital, Brazil
2 shared publications
Latest Publications
- 26 June 2023
- Published by Springer Nature
- p. 170-184
Supervised Machine Learning Techniques Applied to Medical Records Toward the Diagnosis of Rare Autoimmune Diseases
- 26 June 2023
- Published by Springer Nature
- p. 170-184
Supervised Machine Learning Techniques Applied to Medical Records Toward the Diagnosis of Rare Autoimmune Diseases
- Open Access
- 22 January 2021
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 10 (1) , e24826
Mapping, Infrastructure, and Data Analysis for the Brazilian Network of Rare Diseases: Protocol for the RARASnet Observational Cohort Study
Background: A rare disease is a medical condition with low prevalence in the general population, but these can collectively affect up to 10% of the population. Thus, rare diseases have a significant impact on the health care system, and health professionals must be familiar with their diagnosis, management, and treatment.Objective: This paper aims to provide health indicators regarding the rare diseases in Brazil and to create a network of reference centers with health professionals from different regions of the country. RARASnet proposes to map, analyze, and communicate all the data regarding the infrastructure of the centers and the patients’ progress or needs. The focus of the proposed study is to provide all the technical infrastructure and analysis, following the World Health Organization and the Brazilian Ministry of Health guidelines.Methods: To build this digitized system, we will provide a security framework to assure the privacy and protection of each patient when collecting data. Systems development life cycle methodologies will also be applied to align software development, infrastructure operation, and quality assurance. After data collection of all information designed by the specialists, the computational analysis, modeling, and results will be communicated in scientific research papers and a digital health observatory.Results: The project has several activities, and it is in an initial stage. Initially, a survey was given to all health care centers to understand the technical aspects of each network member, such as the existence of computers, technical support staff, and digitized systems. In this survey, we detected that 59% (23/39) of participating health units have electronic medical records, while 41% (16/39) have paper records. Therefore, we will have different strategies to access the data from each center in the data collection phase. Later, we will standardize and analyze the clinical and epidemiological data and use these data to develop a national network for monitoring rare diseases and a digital health observatory to make the information available. The project had its financing approved in December 2019. Retrospective data collection started in October 2020, and we expect to finish in January 2021. During the third quarter of 2020, we enrolled 40 health institutions from all regions of Brazil.Conclusions: The nature of rare disease diagnosis is complex and diverse, and many problems will be faced in the evolution of the project. However, decisions based on data analysis are the best option for the improvement of the rare disease network in Brazil. The creation of RARASnet, along with all the digitized infrastructure, can improve the accessibility of information and standardization of rare diseases in the country.International Registered Report Identifier (IRRID): DERR1-10.2196/24826
- 22 January 2021
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 10 (1) , e24826
Open AccessMapping, Infrastructure, and Data Analysis for the Brazilian Network of Rare Diseases: Protocol for the RARASnet Observational Cohort Study
Background: A rare disease is a medical condition with low prevalence in the general population, but these can collectively affect up to 10% of the population. Thus, rare diseases have a significant impact on the health care system, and health professionals must be familiar with their diagnosis, management, and treatment.Objective: This paper aims to provide health indicators regarding the rare diseases in Brazil and to create a network of reference centers with health professionals from different regions of the country. RARASnet proposes to map, analyze, and communicate all the data regarding the infrastructure of the centers and the patients’ progress or needs. The focus of the proposed study is to provide all the technical infrastructure and analysis, following the World Health Organization and the Brazilian Ministry of Health guidelines.Methods: To build this digitized system, we will provide a security framework to assure the privacy and protection of each patient when collecting data. Systems development life cycle methodologies will also be applied to align software development, infrastructure operation, and quality assurance. After data collection of all information designed by the specialists, the computational analysis, modeling, and results will be communicated in scientific research papers and a digital health observatory.Results: The project has several activities, and it is in an initial stage. Initially, a survey was given to all health care centers to understand the technical aspects of each network member, such as the existence of computers, technical support staff, and digitized systems. In this survey, we detected that 59% (23/39) of participating health units have electronic medical records, while 41% (16/39) have paper records. Therefore, we will have different strategies to access the data from each center in the data collection phase. Later, we will standardize and analyze the clinical and epidemiological data and use these data to develop a national network for monitoring rare diseases and a digital health observatory to make the information available. The project had its financing approved in December 2019. Retrospective data collection started in October 2020, and we expect to finish in January 2021. During the third quarter of 2020, we enrolled 40 health institutions from all regions of Brazil.Conclusions: The nature of rare disease diagnosis is complex and diverse, and many problems will be faced in the evolution of the project. However, decisions based on data analysis are the best option for the improvement of the rare disease network in Brazil. The creation of RARASnet, along with all the digitized infrastructure, can improve the accessibility of information and standardization of rare diseases in the country.International Registered Report Identifier (IRRID): DERR1-10.2196/24826
- Open Access
- 7 October 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Mapping, Infrastructure, and Data Analysis for the Brazilian Network of Rare Diseases: Protocol for the RARASnet Observational Cohort Study (Preprint)
BACKGROUND A rare disease is a medical condition with low prevalence in the general population, but these can collectively affect up to 10% of the population. Thus, rare diseases have a significant impact on the health care system, and health professionals must be familiar with their diagnosis, management, and treatment. OBJECTIVE This paper aims to provide health indicators regarding the rare diseases in Brazil and to create a network of reference centers with health professionals from different regions of the country. RARASnet proposes to map, analyze, and communicate all the data regarding the infrastructure of the centers and the patients’ progress or needs. The focus of the proposed study is to provide all the technical infrastructure and analysis, following the World Health Organization and the Brazilian Ministry of Health guidelines. METHODS To build this digitized system, we will provide a security framework to assure the privacy and protection of each patient when collecting data. Systems development life cycle methodologies will also be applied to align software development, infrastructure operation, and quality assurance. After data collection of all information designed by the specialists, the computational analysis, modeling, and results will be communicated in scientific research papers and a digital health observatory. RESULTS The project has several activities, and it is in an initial stage. Initially, a survey was given to all health care centers to understand the technical aspects of each network member, such as the existence of computers, technical support staff, and digitized systems. In this survey, we detected that 59% (23/39) of participating health units have electronic medical records, while 41% (16/39) have paper records. Therefore, we will have different strategies to access the data from each center in the data collection phase. Later, we will standardize and analyze the clinical and epidemiological data and use these data to develop a national network for monitoring rare diseases and a digital health observatory to make the information available. The project had its financing approved in December 2019. Retrospective data collection started in October 2020, and we expect to finish in January 2021. During the third quarter of 2020, we enrolled 40 health institutions from all regions of Brazil. CONCLUSIONS The nature of rare disease diagnosis is complex and diverse, and many problems will be faced in the evolution of the project. However, decisions based on data analysis are the best option for the improvement of the rare disease network in Brazil. The creation of RARASnet, along with all the digitized infrastructure, can improve the accessibility of information and standardization of rare diseases in the country. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/24826
- 7 October 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMapping, Infrastructure, and Data Analysis for the Brazilian Network of Rare Diseases: Protocol for the RARASnet Observational Cohort Study (Preprint)
BACKGROUND A rare disease is a medical condition with low prevalence in the general population, but these can collectively affect up to 10% of the population. Thus, rare diseases have a significant impact on the health care system, and health professionals must be familiar with their diagnosis, management, and treatment. OBJECTIVE This paper aims to provide health indicators regarding the rare diseases in Brazil and to create a network of reference centers with health professionals from different regions of the country. RARASnet proposes to map, analyze, and communicate all the data regarding the infrastructure of the centers and the patients’ progress or needs. The focus of the proposed study is to provide all the technical infrastructure and analysis, following the World Health Organization and the Brazilian Ministry of Health guidelines. METHODS To build this digitized system, we will provide a security framework to assure the privacy and protection of each patient when collecting data. Systems development life cycle methodologies will also be applied to align software development, infrastructure operation, and quality assurance. After data collection of all information designed by the specialists, the computational analysis, modeling, and results will be communicated in scientific research papers and a digital health observatory. RESULTS The project has several activities, and it is in an initial stage. Initially, a survey was given to all health care centers to understand the technical aspects of each network member, such as the existence of computers, technical support staff, and digitized systems. In this survey, we detected that 59% (23/39) of participating health units have electronic medical records, while 41% (16/39) have paper records. Therefore, we will have different strategies to access the data from each center in the data collection phase. Later, we will standardize and analyze the clinical and epidemiological data and use these data to develop a national network for monitoring rare diseases and a digital health observatory to make the information available. The project had its financing approved in December 2019. Retrospective data collection started in October 2020, and we expect to finish in January 2021. During the third quarter of 2020, we enrolled 40 health institutions from all regions of Brazil. CONCLUSIONS The nature of rare disease diagnosis is complex and diverse, and many problems will be faced in the evolution of the project. However, decisions based on data analysis are the best option for the improvement of the rare disease network in Brazil. The creation of RARASnet, along with all the digitized infrastructure, can improve the accessibility of information and standardization of rare diseases in the country. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/24826
- 15 June 2020
- Published by Springer Nature
- Vol. 12140, 563-576
Preliminary Results on Pulmonary Tuberculosis Detection in Chest X-Ray Using Convolutional Neural Networks
Tuberculosis (TB), is an ancient disease that probably affects humans since pre-hominids. This disease is caused by bacteria belonging to the mycobacterium tuberculosis complex and usually affects the lungs in up to 67% of cases. In 2019, there were estimated to be over 10 million tuberculosis cases in the world, in the same year TB was between the ten leading causes of death, and the deadliest from a single infectious agent. Chest X-ray (CXR) has recently been promoted by the WHO as a tool possibly placed early in screening and triaging algorithms for TB detection. Numerous TB prevalence surveys have demonstrated that CXR is the most sensitive screening tool for pulmonary TB and that a significant proportion of people with TB are asymptomatic in the early stages of the disease. This study presents experimentation of classic convolutional neural network architectures on public CRX databases in order to create a tool applied to the diagnostic aid of TB in chest X-ray images. As result the study has an AUC ranging from 0.78 to 0.84, sensitivity from 0.76 to 0.86 and specificity from 0.58 to 0.74 depending on the network architecture. The observed performance by these metrics alone are within the range of metrics found in the literature, although there is much room for metrics improvement and bias avoiding. Also, the usage of the model in a triage use-case could be used to validate the efficiency of the model in the future.
- 15 June 2020
- Published by Springer Nature
- Vol. 12140, 563-576
Preliminary Results on Pulmonary Tuberculosis Detection in Chest X-Ray Using Convolutional Neural Networks
Tuberculosis (TB), is an ancient disease that probably affects humans since pre-hominids. This disease is caused by bacteria belonging to the mycobacterium tuberculosis complex and usually affects the lungs in up to 67% of cases. In 2019, there were estimated to be over 10 million tuberculosis cases in the world, in the same year TB was between the ten leading causes of death, and the deadliest from a single infectious agent. Chest X-ray (CXR) has recently been promoted by the WHO as a tool possibly placed early in screening and triaging algorithms for TB detection. Numerous TB prevalence surveys have demonstrated that CXR is the most sensitive screening tool for pulmonary TB and that a significant proportion of people with TB are asymptomatic in the early stages of the disease. This study presents experimentation of classic convolutional neural network architectures on public CRX databases in order to create a tool applied to the diagnostic aid of TB in chest X-ray images. As result the study has an AUC ranging from 0.78 to 0.84, sensitivity from 0.76 to 0.86 and specificity from 0.58 to 0.74 depending on the network architecture. The observed performance by these metrics alone are within the range of metrics found in the literature, although there is much room for metrics improvement and bias avoiding. Also, the usage of the model in a triage use-case could be used to validate the efficiency of the model in the future.