Search

Your search keyword '"Renan Goulart Finger"' showing total 12 results
Start Over Author "Renan Goulart Finger"
12 results on '"Renan Goulart Finger"'

1. A New Natural Language Processing–Inspired Methodology (Detection, Initial Characterization, and Semantic Characterization) to Investigate Temporal Shifts (Drifts) in Health Care Data: Quantitative Study

Author

Bruno Paiva, Marcos André Gonçalves, Leonardo Chaves Dutra da Rocha, Milena Soriano Marcolino, Fernanda Cristina Barbosa Lana, Maira Viana Rego Souza-Silva, Jussara M Almeida, Polianna Delfino Pereira, Claudio Moisés Valiense de Andrade, Angélica Gomides dos Reis Gomes, Maria Angélica Pires Ferreira, Frederico Bartolazzi, Manuela Furtado Sacioto, Ana Paula Boscato, Milton Henriques Guimarães-Júnior, Priscilla Pereira dos Reis, Felício Roberto Costa, Alzira de Oliveira Jorge, Laryssa Reis Coelho, Marcelo Carneiro, Thaís Lorenna Souza Sales, Silvia Ferreira Araújo, Daniel Vitório Silveira, Karen Brasil Ruschel, Fernanda Caldeira Veloso Santos, Evelin Paola de Almeida Cenci, Luanna Silva Monteiro Menezes, Fernando Anschau, Maria Aparecida Camargos Bicalho, Euler Roberto Fernandes Manenti, Renan Goulart Finger, Daniela Ponce, Filipe Carrilho de Aguiar, Luiza Margoto Marques, Luís César de Castro, Giovanna Grünewald Vietta, Mariana Frizzo de Godoy, Mariana do Nascimento Vilaça, and Vivian Costa Morais

Subjects
Computer applications to medicine. Medical informatics, R858-859.7
Abstract

BackgroundProper analysis and interpretation of health care data can significantly improve patient outcomes by enhancing services and revealing the impacts of new technologies and treatments. Understanding the substantial impact of temporal shifts in these data is crucial. For example, COVID-19 vaccination initially lowered the mean age of at-risk patients and later changed the characteristics of those who died. This highlights the importance of understanding these shifts for assessing factors that affect patient outcomes. ObjectiveThis study aims to propose detection, initial characterization, and semantic characterization (DIS), a new methodology for analyzing changes in health outcomes and variables over time while discovering contextual changes for outcomes in large volumes of data. MethodsThe DIS methodology involves 3 steps: detection, initial characterization, and semantic characterization. Detection uses metrics such as Jensen-Shannon divergence to identify significant data drifts. Initial characterization offers a global analysis of changes in data distribution and predictive feature significance over time. Semantic characterization uses natural language processing–inspired techniques to understand the local context of these changes, helping identify factors driving changes in patient outcomes. By integrating the outcomes from these 3 steps, our results can identify specific factors (eg, interventions and modifications in health care practices) that drive changes in patient outcomes. DIS was applied to the Brazilian COVID-19 Registry and the Medical Information Mart for Intensive Care, version IV (MIMIC-IV) data sets. ResultsOur approach allowed us to (1) identify drifts effectively, especially using metrics such as the Jensen-Shannon divergence, and (2) uncover reasons for the decline in overall mortality in both the COVID-19 and MIMIC-IV data sets, as well as changes in the cooccurrence between different diseases and this particular outcome. Factors such as vaccination during the COVID-19 pandemic and reduced iatrogenic events and cancer-related deaths in MIMIC-IV were highlighted. The methodology also pinpointed shifts in patient demographics and disease patterns, providing insights into the evolving health care landscape during the study period. ConclusionsWe developed a novel methodology combining machine learning and natural language processing techniques to detect, characterize, and understand temporal shifts in health care data. This understanding can enhance predictive algorithms, improve patient outcomes, and optimize health care resource allocation, ultimately improving the effectiveness of machine learning predictive algorithms applied to health care data. Our methodology can be applied to a variety of scenarios beyond those discussed in this paper.

Published
2024
Full Text
View/download PDF

2. Clinical characteristics and outcomes of hospital-manifested COVID-19 among Brazilians

Author

Polianna Delfino-Pereira, Magda Carvalho Pires, Virginia Mara Reis Gomes, Matheus Carvalho Alves Nogueira, Maria Clara Pontello Barbosa Lima, Alexandre Vargas Schwarzbold, Amanda de Oliveira Maurílio, Ana Luiza Bahia Alves Scotton, André Soares de Moura Costa, Barbara Lopes Farace, Bruno Mateus de Castro, Christiane Corrêa Rodrigues Cimini, Daniel Vitório Silveira, Daniela Ponce, Elayne Crestani Pereira, Eliane Würdig Roesch, Euler Roberto Fernandes Manenti, Evelin Paola de Almeida Cenci, Fernanda Costa dos Santos, Fernando Anschau, Fernando Graça Aranha, Frederico Bartolazzi, Guilherme Fagundes Nascimento, Heloisa Reniers Vianna, Joanna d'Arc Lyra Batista, Joice Coutinho de Alvarenga, Juliana da Silva Nogueira Carvalho, Juliana Machado-Rugolo, Karen Brasil Ruschel, Luanna Silva Monteiro Menezes, Luís César de Castro, Luiz Antônio Nasi, Maiara Anschau Floriani, Maíra Dias Souza, Maíra Viana Rego Souza-Silva, Marcelo Carneiro, Maria Aparecida Camargos Bicalho, Mariana Frizzo de Godoy, Milton Henriques Guimarães-Júnior, Patricia Klarmann Ziegelmann, Pedro Ledic Assaf, Petrônio José de Lima Martelli, Renan Goulart Finger, Saionara Cristina Francisco, Silvia Ferreira Araújo, Talita Fischer Oliveira, Thainara Conceição de Oliveira, Thalita Martins Lage, Vanessa Muller, Yuri Carlotto Ramires, Teresa Cristina de Abreu Ferrari, and Milena Soriano Marcolino

Subjects
COVID-19, Hospital-manifested infection, Clinical characteristics, Outcomes, Risk factors, In-hospital mortality, Infectious and parasitic diseases, RC109-216
Abstract

ABSTRACT: Objectives: To analyze the clinical characteristics and outcomes of admitted patients with the hospital- versus community-manifested COVID-19 and to evaluate the risk factors related to mortality in the first population. Methods: This retrospective cohort included consecutive adult patients with COVID-19, hospitalized between March and September 2020. The demographic data, clinical characteristics, and outcomes were extracted from medical records. Patients with hospital-manifested COVID-19 (study group) and those with community-manifested COVID-19 (control group) were matched by the propensity score model. Logistic regression models were used to verify the risk factors for mortality in the study group. Results: Among 7,710 hospitalized patients who had COVID-19, 7.2% developed symptoms while admitted for other reasons. Patients with hospital-manifested COVID-19 had a higher prevalence of cancer (19.2% vs 10.8%) and alcoholism (8.8% vs 2.8%) than patients with community-manifested COVID-19 and also had a higher rate of intensive care unit requirement (45.1% vs 35.2%), sepsis (23.8% vs 14.5%), and death (35.8% vs 22.5%) (P

Published
2023
Full Text
View/download PDF

3. Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset

Author

Bruno Barbosa Miranda de Paiva, Polianna Delfino Pereira, Claudio Moisés Valiense de Andrade, Virginia Mara Reis Gomes, Maira Viana Rego Souza-Silva, Karina Paula Medeiros Prado Martins, Thaís Lorenna Souza Sales, Rafael Lima Rodrigues de Carvalho, Magda Carvalho Pires, Lucas Emanuel Ferreira Ramos, Rafael Tavares Silva, Alessandra de Freitas Martins Vieira, Aline Gabrielle Sousa Nunes, Alzira de Oliveira Jorge, Amanda de Oliveira Maurílio, Ana Luiza Bahia Alves Scotton, Carla Thais Candida Alves da Silva, Christiane Corrêa Rodrigues Cimini, Daniela Ponce, Elayne Crestani Pereira, Euler Roberto Fernandes Manenti, Fernanda d’Athayde Rodrigues, Fernando Anschau, Fernando Antônio Botoni, Frederico Bartolazzi, Genna Maira Santos Grizende, Helena Carolina Noal, Helena Duani, Isabela Moraes Gomes, Jamille Hemétrio Salles Martins Costa, Júlia di Sabatino Santos Guimarães, Julia Teixeira Tupinambás, Juliana Machado Rugolo, Joanna d’Arc Lyra Batista, Joice Coutinho de Alvarenga, José Miguel Chatkin, Karen Brasil Ruschel, Liege Barella Zandoná, Lílian Santos Pinheiro, Luanna Silva Monteiro Menezes, Lucas Moyses Carvalho de Oliveira, Luciane Kopittke, Luisa Argolo Assis, Luiza Margoto Marques, Magda Cesar Raposo, Maiara Anschau Floriani, Maria Aparecida Camargos Bicalho, Matheus Carvalho Alves Nogueira, Neimy Ramos de Oliveira, Patricia Klarmann Ziegelmann, Pedro Gibson Paraiso, Petrônio José de Lima Martelli, Roberta Senger, Rochele Mosmann Menezes, Saionara Cristina Francisco, Silvia Ferreira Araújo, Tatiana Kurtz, Tatiani Oliveira Fereguetti, Thainara Conceição de Oliveira, Yara Cristina Neves Marques Barbosa Ribeiro, Yuri Carlotto Ramires, Maria Clara Pontello Barbosa Lima, Marcelo Carneiro, Adriana Falangola Benjamin Bezerra, Alexandre Vargas Schwarzbold, André Soares de Moura Costa, Barbara Lopes Farace, Daniel Vitorio Silveira, Evelin Paola de Almeida Cenci, Fernanda Barbosa Lucas, Fernando Graça Aranha, Gisele Alsina Nader Bastos, Giovanna Grunewald Vietta, Guilherme Fagundes Nascimento, Heloisa Reniers Vianna, Henrique Cerqueira Guimarães, Julia Drumond Parreiras de Morais, Leila Beltrami Moreira, Leonardo Seixas de Oliveira, Lucas de Deus Sousa, Luciano de Souza Viana, Máderson Alvares de Souza Cabral, Maria Angélica Pires Ferreira, Mariana Frizzo de Godoy, Meire Pereira de Figueiredo, Milton Henriques Guimarães-Junior, Mônica Aparecida de Paula de Sordi, Natália da Cunha Severino Sampaio, Pedro Ledic Assaf, Raquel Lutkmeier, Reginaldo Aparecido Valacio, Renan Goulart Finger, Rufino de Freitas, Silvana Mangeon Meirelles Guimarães, Talita Fischer Oliveira, Thulio Henrique Oliveira Diniz, Marcos André Gonçalves, and Milena Soriano Marcolino

Subjects
Medicine, Science
Abstract

Abstract The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48–71), 46% women]. We also proposed new original population-based meta-features that have not been devised in the literature. Stacking has shown to achieve the best results reported in the literature for the death prediction task, improving over previous state-of-the-art by more than 46% in Recall for predicting death, with AUROC 0.826 and MacroF1 of 65.4%. The newly proposed meta-features were highly discriminative of death, but fell short in producing large improvements in final prediction performance, demonstrating that we are possibly on the limits of the prediction capabilities that can be achieved with the current set of ML techniques and (meta-)features. Finally, we investigated how the trained models perform on different hospitals, showing that there are indeed large differences in classifier performance between different hospitals, further making the case that errors are produced by factors that cannot be modeled with the current predictors.

Published
2023
Full Text
View/download PDF

4. Hypothyroidism does not lead to worse prognosis in COVID-19: findings from the Brazilian COVID-19 registry

Author

Daniella Nunes Pereira, Leticia Ferreira Gontijo Silveira, MD, PhD, Milena Maria Moreira Guimarães, Carísi Anne Polanczyk, Aline Gabrielle Sousa Nunes, André Soares de Moura Costa, Barbara Lopes Farace, Christiane Corrêa Rodrigues Cimini, Cíntia Alcantara de Carvalho, Daniela Ponce, Eliane Würdig Roesch, Euler Roberto Fernandes Manenti, Fernanda Barbosa Lucas, Fernanda d'Athayde Rodrigues, Fernando Anschau, Fernando Graça Aranha, Frederico Bartolazzi, Giovanna Grunewald Vietta, Guilherme Fagundes Nascimento, Helena Duani, Heloisa Reniers Vianna, Henrique Cerqueira Guimarães, Jamille Hemétrio Salles Martins Costa, Joanna d'Arc Lyra Batista, Joice Coutinho de Alvarenga, José Miguel Chatkin, Júlia Drumond Parreiras de Morais, Juliana Machado-Rugolo, Karen Brasil Ruschel, Lílian Santos Pinheiro, Luanna Silva Monteiro Menezes, Luciana Siuves Ferreira Couto, Luciane Kopittke, Luís César de Castro, Luiz Antônio Nasi, Máderson Alvares de Souza Cabral, Maiara Anschau Floriani, Maíra Dias Souza, Marcelo Carneiro, Maria Aparecida Camargos Bicalho, Mariana Frizzo de Godoy, Matheus Carvalho Alves Nogueira, Milton Henriques Guimarães Júnior, Natália da Cunha Severino Sampaio, Neimy Ramos de Oliveira, Pedro Ledic Assaf, Renan Goulart Finger, Roberta Xavier Campos, Rochele Mosmann Menezes, Saionara Cristina Francisco, Samuel Penchel Alvarenga, Silvana Mangeon Mereilles Guimarães, Silvia Ferreira Araújo, Talita Fischer Oliveira, Thulio Henrique Oliveira Diniz, Yuri Carlotto Ramires, Evelin Paola de Almeida Cenci, Thainara Conceição de Oliveira, Alexandre Vargas Schwarzbold, Patricia Klarmann Ziegelmann, Roberta Pozza, Caroline Scherer Carvalho, Magda Carvalho Pires, and Milena Soriano Marcolino

Subjects
Hypothyroidism, COVID-19, Mortality, Prognosis, Epidemiology, Infectious and parasitic diseases, RC109-216
Abstract

Background: It is not clear whether previous thyroid diseases influence the course and outcomes of COVID-19. Methods: The study is a part of a multicentric cohort of patients with confirmed COVID-19 diagnosis from 37 hospitals. Matching for age, sex, number of comorbidities, and hospital was performed for the paired analysis. Results: Of 7,762 patients with COVID-19, 526 had previously diagnosed hypothyroidism and 526 were matched controls. The median age was 70 years, and 68.3% were females. The prevalence of comorbidities was similar, except for coronary and chronic kidney diseases that were higher in the hypothyroidism group (p=0.015 and p=0.001). D-dimer levels were lower in patients with hypothyroid (p=0.037). In-hospital management was similar, but hospital length-of-stay (p=0.029) and mechanical ventilation requirement (p=0.006) were lower for patients with hypothyroidism. There was a trend of lower in-hospital mortality in patients with hypothyroidism (22.1% vs 27.0%; p=0.062). Conclusion: Patients with hypothyroidism had a lower requirement of mechanical ventilation and showed a trend of lower in-hospital mortality. Therefore, hypothyroidism does not seem to be associated with a worse prognosis.

Published
2022
Full Text
View/download PDF

5. Lesão Miocárdica e Prognóstico em Pacientes Hospitalizados com COVID-19 no Brasil: Resultados do Registro Nacional de COVID-19

Author

Hannah Cardoso Barbosa, Maria Auxiliadora Parreiras Martins, Jordana Cristina de Jesus, Karina Cardoso Meira, Luiz Guilherme Passaglia, Manuela Furtado Sacioto, Adriana Falangola Benjamin Bezerra, Alexandre Vargas Schwarzbold, Amanda de Oliveira Maurílio, Barbara Lopes Farace, Carla Thais Cândida Alves da Silva, Christiane Corrêa Rodrigues Cimini, Daniel Vitorio Silveira, Daniela do Reis Carazai, Daniela Ponce, Emanuel Victor Alves Costa, Euler Roberto Fernandes Manenti, Evelin Paola de Almeida Cenci, Frederico Bartolazzi, Glícia Cristina de Castro Madeira, Guilherme Fagundes Nascimento, Isabela Vasconcellos Pires Velloso, Joanna d’Arc Lyra Batista, Júlia Drumond Parreiras de Morais, Juliana da Silva Nogueira Carvalho, Karen Brasil Ruschel, Karina Paula Medeiros Prado Martins, Liege Barella Zandoná, Luanna Silva Monteiro Menezes, Luciane Kopittke, Luís César de Castro, Luiz Antônio Nasi, Maiara Anschau Floriani, Maíra Dias Souza, Marcelo Carneiro, Maria Aparecida Camargos Bicalho, Maria Clara Pontello Barbosa Lima, Mariana Frizzo de Godoy, Milton Henriques Guimarães-Júnior, Paulo Mascarenhas Mendes, Polianna Delfino-Pereira, Raquel Jaqueline Eder Ribeiro, Renan Goulart Finger, Rochele Mosmann Menezes, Saionara Cristina Francisco, Silvia Ferreira Araújo, Talita Fischer Oliveira, Thainara Conceição de Oliveira, Carisi Anne Polanczyk, and Milena Soriano Marcolino

Subjects
COVID-19, Infecções por Coronavírus, Troponina, Respiração artificial, Mortalidade, Diseases of the circulatory (Cardiovascular) system, RC666-701
Abstract

Resumo Fundamento As complicações cardiovasculares da COVID-19 são aspectos importantes da patogênese e do prognóstico da doença. Evidências do papel prognóstico da troponina e da lesão miocárdica em pacientes hospitalizados com COVID-19 na América Latina são ainda escassos. Objetivos Avaliar a lesão miocárdica como preditor independente de mortalidade hospitalar e suporte ventilatório mecânico em pacientes hospitalizados, do registro brasileiro de COVID-19. Métodos Este estudo coorte é um subestudo do registro brasileiro de COVID-19, conduzido em 31 hospitais brasileiros de 17 cidades, de março a setembro de 2020. Os desfechos primários incluíram mortalidade hospitalar e suporte ventilatório mecânico invasivo. Os modelos para os desfechos primários foram estimados por regressão de Poisson com variância robusta, com significância estatística de p

Published
2023
Full Text
View/download PDF

6. ABC2-SPH risk score for in-hospital mortality in COVID-19 patients: development, external validation and comparison with other available scores

Author

Mariana Frizzo de Godoy, Luana Martins Oliveira, Christiane Correa Rodrigues cimini, Fernando Antônio Botoni, Raquel Lutkmeier, Neimy Ramos de Oliveira, Andre Pinheiro Weber, Roberta Xavier Campos, Andressa Barreto Glaeser, Cintia Alcantara de Carvalho, Renan Goulart Finger, Israel Júnior Borges do Nascimento, Yuri Carlotto Ramires, Carolina Marques Ramos, Angelinda Rezende Bhering, Karina Paula Medeiros Prado Martins, Julia Drumond Parreiras de Morais, Rufino de Freitas Silva, Heloisa Reniers Vianna, Amanda de Oliveira Maurilio, Luis Cesar Souto de Moura, Giovanna Grunewald Vietta, Alexandre Vargas Schwarzbold, Daniel Taiar Marinho Oliveira Ferrara, Maíra Viana Rego Souza-Silva, Milton Henriques Guimarães-Júnior, Luís César de Castro, Thaiza Simonia Marinho Albino de Araujo, Silvia Ferreira Araujo, Caroline Danubia Gomes, Marilia Mastrocolla de Almeida Cardoso, Berta Raventós, Milena Soriano Marcolino, Saionara Cristina Francisco, Rafael Guimarães Tavares da Silva, José Miguel Chatkin, Carisi Anne Polanczyk, Raphael Castro Martins, Lucas de Deus Sousa, Susany Anastacia Pereira, Eric Boersma, Pedro Ledic Assaf, Patricia Klarmann Ziegelmann, Karen Cristina Jung Rech Pontes, Tatiana Kurtz, Roger Mendes de Abreu, Petrônio José de Lima Martelli, Angelica Aparecida Coelho Madureira, Carla Thais Candida Alves da Silva, Lilian Santos Pinheiro, Luanna da Silva Monteiro, Frederico Bartolazzi, Kauane Aline Maciel dos Santos, Natalia Lima Rangel, Marcela Goncalves Trindade Tofani, Maria Aparecida Camargos Bicalho, Natalia da Cunha Severino Sampaio, Virginia Mara Reis Gomes, Maria Angelica Pires Ferreira, Luisa Elem Almeida Santos, Bruno Mateus de Castro, Thaís Lorenna Souza Sales, Ana Luiza Bahia Alves Scotton, Joanna d'Arc L. Batista, Fernando Graca Aranha, Thainara Conceicao de Oliveira, Fernando Anschau, Felipe Barbosa Vallt, Thulio Henrique Oliveira Diniz, Rafael Lima Rodrigues de Carvalho, Guilherme Fagundes Nascimento, Roberta Pozza, Elayne Crestani Pereira, Máderson Alvares de Souza Cabral, Rodolfo Lucas Silva Mourato, Isabela Moraes Gomes, Julia Di Sabatino Santos Guimaraes, Ana Paula Beck da Silva Etges, Luciana Siuves Ferreira Couto, Gisele Alsina Nader Bastos, Juliana Machado Rugolo, Rochele Mosmann Menezes, L. E. F. Ramos, Liliane Souto Pacheco, Helena Carolina Noal, Veridiana Baldon dos Santos Santos, Henrique Cerqueira Guimaraes, Matheus Carvalho Alves Nogueira, Ricardo Bertoglio Cardoso, Glicia Cristina de Castro Madeira, Daniela Ponce, Helena Duani, Vitor Augusto Lima do Vale, Marcelo Carneiro, Leonardo Seixas de Oliveira, Talita Fischer Oliveira, Emanuele Marianne Souza Kroger, Israel Molina, Natalia Trifiletti Crespo, Edilson Cezar, Karen Brasil Ruschel, Tatiani Oliveira Fereguetti, Rafaela dos Santos Charao de Almeida, Joice Coutinho de Alvarenga, Maiara Anschau Floriani, Maira Dias Souza, Adrián Sánchez-Montalvá, Barbara Lopes Farace, Maria Clara Pontello Barbosa Lima, Meire Pereira de Figueiredo, Luciane Kopittke, Gabriela Petry Crestani, Andre Soares de Moura Costa, Silvana Mangeon Meirelles Guimarães, Fernanda Barbosa Lucas, Reginaldo Aparecido Valacio, Daniel Vitorio Silveira, Magda Carvalho Pires, Cardiology, Universidade Federal de Minas Gerais (UFMG), Institute for Health Technology Assessment IATS/ CNPq)., Universidade Federal de São João del-Rei, Universitat Autònoma de Barcelona, Grupo Hospitalar Conceição, Pontifícia Universidade Católica do Rio Grande do Sul RGS), Hospital São Lucas PUCRS, Rede Mater Dei de Saúde, Hospital Márcio Cunha, Universidade do Sul de Santa Catarina UNISUL, Dissertare Scientific Advice, SOS Cardio Hospital, Universidade Estadual Paulista (UNESP), Universidade Federal do Rio Grande do Sul, Hospital Bruno Born, Research Center of Vale do Taquari., Hospital Mãe de Deus, Hospital Universitário de Canoas, Universidade Federal de Viçosa (UFV), Hospital Santa Rosalia, Hospital Metropolitano Doutor Célio de Castro, Hospital Moinhos de Vento, Hospital Unimed BH, Hospital Risoleta Tolentino Neves, Hospital Metropolitano Odilon Behrens, Hospital Eduardo de Menezes, Universidade FUMEC, Hospital Julia Kubitschek, Hospital Universitário de Santa Maria, Universidade Federal de Santa Maria, Hospital São João de Deus, Hospital Regional Antônio Dias, Faculdade Ciências Médicas de Minas Gerais, Faculdade de Ciências Humanas de Curvelo, Av. Professor Alfredo Balena, Hospital Santo Antônio, Hospital Universitário Ciências Médicas, PROSICS Barcelona, Instituto René Rachou-FIOCRUZ Minas., Universidade Federal da Fronteira Sul, Hospital Regional do Oeste, Pontifícia Universidade Católica de Minas Gerais, Hospital Tacchini, Centro Universitário de Patos de Minas. RPatos de Minas, Hospital Semper, Hospital Santa Cruz, Universidade de Santa Cruz, Fundação Hospitalar do Estado de Minas Gerais – FHEMIG., Universidade Federal de Ouro Preto, Universidade Federal de Pernambuco (UFPE), Centro Universitário de Belo Horizonte UniBH), University Medical Center Rotterdam, Institut Català de la Salut, [Marcolino MS] Department of Internal Medicine, Medical School, Universidade Federal de Minas Gerais. Belo Horizonte, Brazil. Telehealth Center, University Hospital, Universidade Federal de Minas Gerais. Belo Horizonte, Brazil. Institute for Health Technology Assessment (IATS/ CNPq). Rua Ramiro Barcelos, 2359. Prédio 21 | Sala 507, Porto Alegre, Brazil. [Pires MC] Institute for Health Technology Assessment (IATS/ CNPq). Rua Ramiro Barcelos, 2359. Prédio 21 | Sala 507, Porto Alegre, Brazil. Department of Statistics, Universidade Federal de Minas Gerais. Belo Horizonte, Brazil. [Ramos LEF, Silva RT] Department of Statistics, Universidade Federal de Minas Gerais. Belo Horizonte, Brazil. [Oliveira LM] Institute for Health Technology Assessment (IATS/ CNPq). Rua Ramiro Barcelos, 2359. Prédio 21 | Sala 507, Porto Alegre, Brazil. Center for Research and Graduate Studies in Business Administration, Universidade Federal de Minas Gerais. Belo Horizonte, Brazil. [Carvalho RLR] Institute for Health Technology Assessment (IATS/ CNPq). Rua Ramiro Barcelos, 2359. Prédio 21 | Sala 507, Porto Alegre, Brazil. [Sánchez-Montalvá A, Raventós B] Servei de Malalties Infeccioses, Vall d’Hebron Hospital Universitari, Barcelona, Spain. Universitat Autònoma de Barcelona, Bellaterra, Spain. PROSICS, Barcelona, Spain. [Molina I] Vall d’Hebron Hospital Universitari, Barcelona, Spain. PROSICS Barcelona. Barcelona, Spain. Instituto René Rachou-FIOCRUZ Minas. Belo Horizonte, Brazil, and Vall d'Hebron Barcelona Hospital Campus

Subjects
Microbiology (medical), Percentile, medicine.medical_specialty, Coronavirus disease 2019 (COVID-19), COVID-19 (Malaltia) - Mortalitat, Infectious and parasitic diseases, RC109-216, Logistic regression, Article, SDG 3 - Good Health and Well-being, Mortalitat - Estadístiques, Other subheadings::Other subheadings::Other subheadings::/mortality [Other subheadings], Internal medicine, Heart rate, virosis::infecciones por virus ARN::infecciones por Nidovirales::infecciones por Coronaviridae::infecciones por Coronavirus [ENFERMEDADES], técnicas de investigación::métodos epidemiológicos::recopilación de datos::estadísticas vitales::mortalidad::mortalidad hospitalaria [TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS], medicine, score, Humans, Hospital Mortality, Mortality, Diagnosis::Prognosis [ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT], Investigative Techniques::Epidemiologic Methods::Data Collection::Vital Statistics::Mortality::Hospital Mortality [ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT], diagnóstico::pronóstico [TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS], Blood urea nitrogen, Aged, Retrospective Studies, Hospitalizations, COVID-19 (Malaltia) - Prognosi, Otros calificadores::Otros calificadores::Otros calificadores::/mortalidad [Otros calificadores], Framingham Risk Score, SARS-CoV-2, business.industry, Score, COVID-19, Virus Diseases::RNA Virus Infections::Nidovirales Infections::Coronaviridae Infections::Coronavirus Infections [DISEASES], General Medicine, Emergency department, Middle Aged, Prognosis, Hospitalization, Infectious Diseases, Risk factors, Cohort, business
Abstract

Made available in DSpace on 2022-04-29T08:31:56Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-09-01 Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Objectives: The majority of available scores to assess mortality risk of coronavirus disease 2019 (COVID-19) patients in the emergency department have high risk of bias. Therefore, this cohort aimed to develop and validate a score at hospital admission for predicting in-hospital mortality in COVID-19 patients and to compare this score with other existing ones. Methods: Consecutive patients (≥ 18 years) with confirmed COVID-19 admitted to the participating hospitals were included. Logistic regression analysis was performed to develop a prediction model for in-hospital mortality, based on the 3978 patients admitted between March–July, 2020. The model was validated in the 1054 patients admitted during August–September, as well as in an external cohort of 474 Spanish patients. Results: Median (25–75th percentile) age of the model-derivation cohort was 60 (48–72) years, and in-hospital mortality was 20.3%. The validation cohorts had similar age distribution and in-hospital mortality. Seven significant variables were included in the risk score: age, blood urea nitrogen, number of comorbidities, C-reactive protein, SpO2/FiO2 ratio, platelet count, and heart rate. The model had high discriminatory value (AUROC 0.844, 95% CI 0.829–0.859), which was confirmed in the Brazilian (0.859 [95% CI 0.833–0.885]) and Spanish (0.894 [95% CI 0.870–0.919]) validation cohorts, and displayed better discrimination ability than other existing scores. It is implemented in a freely available online risk calculator (https://abc2sph.com/). Conclusions: An easy-to-use rapid scoring system based on characteristics of COVID-19 patients commonly available at hospital presentation was designed and validated for early stratification of in-hospital mortality risk of patients with COVID-19. Department of Internal Medicine Medical School Universidade Federal de Minas Gerais Telehealth Center University Hospital Universidade Federal de Minas Gerais Institute for Health Technology Assessment IATS/ CNPq)., Rua Ramiro Barcelos, 2359. Prédio 21 | Sala 507 Department of Statistics Universidade Federal de Minas Gerais Center for Research and Graduate Studies in Business Administration Universidade Federal de Minas Gerais Universidade Federal de São João del-Rei Infectious Diseases Department Vall d'Hebron University Hospita Universitat Autònoma de Barcelona Hospital Nossa Senhora da Conceição and Hospital Cristo Redentor Grupo Hospitalar Conceição Pontifícia Universidade Católica do Rio Grande do Sul RGS) Hospital São Lucas PUCRS Rede Mater Dei de Saúde Hospital Márcio Cunha Universidade do Sul de Santa Catarina UNISUL Dissertare Scientific Advice SOS Cardio Hospital Internal Medicine Department University Hospital Universidade Federal de Minas Gerais Faculdade de Medicina de Botucatu Universidade Estadual Paulista Júlio de Mesquita Filho Hospital das Clínicas da Faculdade de Medicina de Botucatu Universidade Federal do Rio Grande do Sul Hospital Bruno Born Research Center of Vale do Taquari. Hospital Mãe de Deus Hospital Universitário de Canoas Mucuri Medical School FAMMUC Universidade Federal dos Vales do Jequitinhonha e Mucuri – UFVJM Hospital Santa Rosalia Hospital Metropolitano Doutor Célio de Castro Hospital Moinhos de Vento Hospital Unimed BH Hospital Risoleta Tolentino Neves Post-graduation Center Medical School Universidade Federal de Minas Gerais Hospital Metropolitano Odilon Behrens Hospital Eduardo de Menezes Universidade FUMEC Hospital Julia Kubitschek Hospital Universitário de Santa Maria Departamento de Medicina Interna Universidade Federal de Santa Maria Hospital São João de Deus Hospital Regional Antônio Dias Faculdade Ciências Médicas de Minas Gerais Hospital de Clínicas de Porto Alegre Universidade Federal do Rio Grande do Sul Faculdade de Ciências Humanas de Curvelo Hospital João XXIII Av. Professor Alfredo Balena Hospital Santo Antônio Hospital Universitário Ciências Médicas Vall d'Hebron University Hospital PROSICS Barcelona Instituto René Rachou-FIOCRUZ Minas. Universidade Federal da Fronteira Sul Hospital Regional do Oeste Pontifícia Universidade Católica de Minas Gerais Hospital Tacchini Centro Universitário de Patos de Minas. RPatos de Minas Hospital Semper Hospital Santa Cruz Universidade de Santa Cruz Fundação Hospitalar do Estado de Minas Gerais – FHEMIG. Universidade Federal de Ouro Preto Hospital das Clínicas da Universidade Federal de Pernambuco Universidade Federal de Pernambuco Centro de Ciências Médicas Centro Universitário de Belo Horizonte UniBH) Erasmus MC University Medical Center Rotterdam Department of Cardiology Faculdade de Medicina de Botucatu Universidade Estadual Paulista Júlio de Mesquita Filho Hospital das Clínicas da Faculdade de Medicina de Botucatu

Published
2021
Full Text
View/download PDF

7. Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry

Author

Polianna Delfino-Pereira, Cláudio Moisés Valiense De Andrade, Virginia Mara Reis Gomes, Maria Clara Pontello Barbosa Lima, Maira Viana Rego Souza-Silva, Marcelo Carneiro, Karina Paula Medeiros Prado Martins, Thaís Lorenna Souza Sales, Rafael Lima Rodrigues De Carvalho, Magda Carvalho Pires, Lucas Emanuel Ferreira Ramos, Rafael T Silva, Adriana Falangola Benjamin Bezerra, Alexandre Vargas Schwarzbold, Aline Gabrielle Sousa Nunes, Amanda de Oliveira Maurilio, Ana Luiza Bahia Alves Scotton, André Soares de Moura Costa, Andriele Abreu Castro, Bárbara Lopes Farace, Christiane Corrêa Rodrigues Cimini, Cíntia Alcântara De Carvalho, Daniel Vitorio Silveira, Daniela Ponce, Elayne Crestani Pereira, Euler Roberto Fernandes Manenti, Evelin Paola de Almeida Cenci, Fernanda Barbosa Lucas, Fernanda d’Athayde Rodrigues, Fernando Anschau, Fernando Antônio Botoni, Fernando Graça Aranha, Frederico Bartolazzi, Gisele Alsina Nader Bastos, Giovanna Grunewald Vietta, Guilherme Fagundes Nascimento, Helena Carolina Noal, Helena Duani, Heloísa Reniers Vianna, Henrique Cerqueira Guimarães, Isabela Moraes Gomes, Jamille Hemerito Salles Martins Costa, Jessica Rayane Corrêa Silva Da Fonseca, Júlia Di Sabatino Santos Guimarães, Júlia Drumond Parreiras De Morais, Juliana Machado Rugolo, Joanna d’Arc Lyra Batista, Joice Coutinho De Alvarenga, José Miguel Chatkin, Karen Brasil Ruschel, Leila Beltrami Moreira, Leonardo Seixas De Oliveira, Liege Barella Zandona, Lilian Santos Pinheiro, Luanna da Silva Monteiro, Lucas de Deus Sousa, Luciane Kopittke, Luciano de Souza Viana, Luís César De Castro, Luísa Argolo Assis, Luísa Elem Almeida Santos, Maderson Álvares de Souza Cabral, Magda Cesar Raposo, Maiara Anschau Floriani, Maria Angélica Pires Ferreira, Maria Aparecida Camargos Bicalho, Mariana Frizzo De Godoy, Matheus Carvalho Alves Nogueira, Meire Pereira De Figueiredo, Milton Henriques Guimarães Júnior, Monica Aparecida de Paula De Sordi, Natália da Cunha Severino Sampaio, Neimy Ramos De Oliveira, Pedro Ledic Assaf, Raquel Lutkmeier, Reginaldo Aparecido Valacio, Renan Goulart Finger, Rochele Mosmann Menezes, Rufino de Freitas Silva, Saionara Cristina Francisco, Silvana Mangeon Meireles Guimaraes, Silvia Ferreira Araujo, Talita Fischer Oliveira, Tatiana Kurtz, Tatiana Oliveira Fereguetti, Thainara Conceição De Oliveira, Túlio Henrique Oliveira Diniz, Yara Cristina Neves Marques Barbosa Ribeiro, Yuri Carlotto Ramires, Marcos André Gonçalves, Milena Soriano Marcolino, and Bruno Barbosa Miranda de Paiva

Abstract

The majority prognostic scores proposed for early assessment of coronavirus disease 19 (COVID-19) patients are bounded by methodological flaws. Our group recently developed a new risk score - ABC2SPH - using traditional statistical methods (least absolute shrinkage and selection operator logistic regression - LASSO). In this article, we provide a thorough comparative study between modern machine learning (ML) methods and state-of-the-art statistical methods, represented by ABC2SPH, in the task of predicting in-hospital mortality in COVID-19 patients using data upon hospital admission. We overcome methodological and technological issues found in previous similar studies, while exploring a large sample (5,032 patients). Additionally, we take advantage of a large and diverse set of methods and investigate the effectiveness of applying meta-learning, more specifically Stacking, in order to combine the methods' strengths and overcome their limitations. In our experiments, our Stacking solutions improved over previous state-of-the-art by more than 26% in predicting death, achieving 87.1% of AUROC and MacroF1 of 73.9%. We also investigated issues related to the interpretability and reliability of the predictions produced by the most effective ML methods. Finally, we discuss the adequacy of AUROC as an evaluation metric for highly imbalanced and skewed datasets commonly found in health-related problems.

Published
2022
Full Text
View/download PDF

8. Hospital-Manifested SARS-CoV-2 Infection in Brazil: Clinical Characteristics, Outcomes and Risk Factors for Mortality

Author

Polianna Delfino Pereira, Magda Carvalho Pires, Virginia Mara Reis Gomes, Matheus Carvalho Alves Nogueira, Maria Clara Pontello Barbosa Lima, Alexandre Vargas Schwarzbold, Amanda de Oliveira Maurílio, Ana Luiza Bahia Alves Scotton, André Soares de Moura Costa, Bárbara Lopes Farace, Bruno Mateus de Castro, Christiane Corrêa Rodrigues Cimini, Daniel Vitório Silveira, Daniela Ponce, Elayne Crestani Pereira, Eliane Würdig Roesch, Euler Roberto Fernandes Manenti, Evelin Paola de Almeida Cenci, Fernanda Costa dos Santos, Fernando Anschau, Fernando Graça Aranha, Frederico Bartolazzi, Guilherme Fagundes Nascimento, Heloisa Reniers Vianna, Joanna Batista, Joice Coutinho de Alvarenga, Juliana da Silva Nogueira Carvalho, Juliana Machado Rugolo, Karen Brasil Ruschel, Luanna da Silva Monteiro, Luis C. Castro, Luiz Antonio Nasi, Maiara Anschau Floriani, Maira Dias Souza, Maíra Viana Rego Souza-Silva, Marcelo Carneiro, Maria Aparecida Camargos Bicalho, Mariana Frizzo de Godoy, Milton Henriques Guimarães Júnior, Patricia K. Ziegelmann, Pedro Ledic Assaf, Petrônio José de Lima Martelli, Renan Goulart Finger, Saionara Cristina Francisco, Silvia Ferreira Araújo, Talita Fischer Oliveira, Thainara Conceição de Oliveira, Thalita Martins Lage, Vanessa Muller, Yuri Carlotto Ramires, Teresa Cristina de Abreu Ferrari, and Milena Soriano Marcolino

Published
2022
Full Text
View/download PDF

9. Hypothyroidism does not lead to worse prognosis in COVID-19: findings from the Brazilian COVID-19 registry

Author

Maiara Anschau Floriani, Maira Dias Souza, Máderson Alvares de Souza Cabral, Samuel Penchel Alvarenga, Mariana Frizzo de Godoy, Heloisa Reniers Vianna, Euler Roberto Fernandes Manenti, Giovanna Grunewald Vietta, Leticia Ferreira Gontijo Silveira, Luciane Kopittke, Evelin Paola de Almeida Cenci, Roberta Pozza, José Miguel Chatkin, Carisi Anne Polanczyk, Yuri Carlotto Ramires, Luciana Siuves Ferreira Couto, Rochele Mosmann Menezes, Marcelo Carneiro, Daniella Nunes Pereira, Luanna Silva Monteiro Menezes, Fernanda Barbosa Lucas, Joice Coutinho de Alvarenga, Magda Carvalho Pires, Daniela Ponce, Christiane Correa Rodrigues cimini, Maria Aparecida Camargos Bicalho, Renan Goulart Finger, Milena Maria Moreira Guimarães, Milena Soriano Marcolino, Saionara Cristina Francisco, Juliana Machado-Rugolo, Thulio Henrique Oliveira Diniz, Barbara Lopes Farace, Andre Soares de Moura Costa, Patricia Klarmann Ziegelmann, Natalia da Cunha Severino Sampaio, Silvia Ferreira Araujo, Roberta Xavier Campos, Karen Brasil Ruschel, Fernando Graca Aranha, Silvana Mangeon Mereilles Guimaraes, Lilian Santos Pinheiro, Milton Henriques Guimaraes Junior, Pedro Ledic Assaf, Talita Fischer Oliveira, Alexandre Vargas Schwarzbold, Guilherme Fagundes Nascimento, Thainara Conceicao de Oliveira, Helena Duani, Luiz Antonio Nasi, Jamille Hemetrio Salles Martins Costa, Cintia Alcantara de Carvalho, Aline Gabrielle Sousa Nunes, Frederico Bartolazzi, Fernanda D'Athayde Rodrigues, Joanna d'Arc Lyra Batista, Henrique Cerqueira Guimaraes, Matheus Carvalho Alves Nogueira, Neimy Ramos de Oliveira, Eliane Wurdig Roesch, Fernando Anschau, Julia Drumond Parreiras de Morais, and Luís César de Castro

Subjects
Mechanical ventilation, medicine.medical_specialty, Coronavirus disease 2019 (COVID-19), Respiratory rate, business.industry, medicine.medical_treatment, Thyroid, medicine.anatomical_structure, Interquartile range, Internal medicine, Cohort, Medicine, Risk factor, business, Lead (electronics)
Abstract

BackgroundIt is not clear whether previous thyroid diseases influence the course and outcomes of COVID-19. The study aims to compare clinical characteristics and outcomes of COVID-19 patients with and without hypothyroidism.MethodsThe study is a part of a multicentric cohort of patients with confirmed COVID-19 diagnosis, including data collected from 37 hospitals. Matching for age, sex, number of comorbidities and hospital was performed to select the patients without hypothyroidism for the paired analysis.ResultsFrom 7,762 COVID-19 patients, 526 had previously diagnosed hypothyroidism (50%) and 526 were selected as matched controls. The median age was 70 (interquartile range 59.0-80.0) years-old and 68.3% were females. The prevalence of underlying comorbidities were similar between groups, except for coronary and chronic kidney diseases, that had a higher prevalence in the hypothyroidism group (9.7% vs. 5.7%, p=0.015 and 9.9% vs. 4.8%, p=0.001, respectively). At hospital presentation, patients with hypothyroidism had a lower frequency of respiratory rate > 24 breaths per minute (36.1% vs 42.0%; p=0.050) and need of mechanical ventilation (4.0% vs 7.4%; p=0.016). D-dimer levels were slightly lower in hypothyroid patients (2.3 times higher than the reference value vs 2.9 times higher; p=0.037). In-hospital management was similar between groups, but hospital length-of-stay (8 vs 9 days; p=0.029) and mechanical ventilation requirement (25.4% vs. 33.1%; p=0.006) were lower for patients with hypothyroidism. There was a trend of lower in-hospital mortality in patients with hypothyroidism (22.1% vs. 27.0%; p=0.062).ConclusionIn this large Brazilian COVID-19 Registry, patients with hypothyroidism had a lower requirement of mechanical ventilation, and showed a trend of lower in-hospital mortality. Therefore, hypothyroidism does not seem to be associated with a worse prognosis, and should not be considered among the comorbidities that indicate a risk factor for COVID-19 severity.

Published
2021
Full Text
View/download PDF

10. Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry

Author

Daniela Ponce, Roberta Senger, Rufino de Freitas Silva, Elayne Crestani Pereira, Pedro Ledic Assaf, Maria Angelica Pires Ferreira, Adriana Falangola Benjamin Bezerra, Heloisa Reniers Vianna, Milena Soriano Marcolino, Saionara Cristina Francisco, Natalia da Cunha Severino Sampaio, Fernanda D'Athayde Rodrigues, Maiara Anschau Floriani, Ana Luiza Bahia Alves Scotton, Fernando Graca Aranha, Neimy Ramos de Oliveira, Yara Neves Marques Barbosa Ribeiro, Máderson Alvares de Souza Cabral, Maria Aparecida Camargos Bicalho, Giovanna Grunewald Vietta, José Miguel Chatkin, Maria Clara Pontello Barbosa Lima, Thaís Lorenna Souza Sales, Thainara Conceicao de Oliveira, Amanda de Oliveira Maurilio, Barbara Lopes Farace, Cláudio Moisés Valiense de Andrade, Rochele Mosmann Menezes, Milton Henriques Guimaraes Junior, Raquel Lutkmeier, Magda Cesar Raposo, Renan Goulart Finger, Marcelo Carneiro, Tatiana Kurtz, Andriele Abreu Castro, Fernando Anschau, Lucas de Deus Sousa, Mariana Frizzo de Godoy, Luisa Elem Almeida Santos, Meire Pereira de Figueiredo, Luciane Kopittke, Monica Aparecida de Paula De Sordi, Leonardo Seixas de Oliveira, Christiane Correa Rodrigues cimini, Luciano de Souza Viana, Talita Fischer Oliveira, Yuri Carlotto Ramires, Fernando Antônio Botoni, Luisa Argolo Assis, Polianna Delfino Pereira, Cintia Alcantara de Carvalho, Rafael Guimarães Tavares da Silva, Bruno Barbosa Miranda de Paiva, Andre Soares de Moura Costa, Guilherme Fagundes Nascimento, Joice Coutinho de Alvarenga, Gisele Alsina Nader Bastos, Rafael Lima Rodrigues de Carvalho, Karina Paula Medeiros Prado Martins, Julia Drumond Parreiras de Morais, Matheus Carvalho Alves Nogueira, Luís César de Castro, Helena Duani, Julia Di Sabatino Santos Guimaraes, Alexandre Vargas Schwarzbold, Helena Carolina Noal, Virginia Mara Reis Gomes, Thulio Henrique Oliveira Diniz, Evelin Paola de Almeida Cenci, Marcos André Gonçalves, Jamille Hemetrio Salles Martins Costa, Lilian Santos Pinheiro, Maíra Viana Rego Souza e Silva, Silvia Ferreira Araujo, Aline Gabrielle Sousa Nunes, Luanna da Silva Monteiro, Frederico Bartolazzi, Leila Beltrami Moreira, Fernanda Barbosa Lucas, Reginaldo Aparecido Valacio, Daniel Vitorio Silveira, Magda Carvalho Pires, L. E. F. Ramos, Joanna d'Arc Lyra Batista, Henrique Cerqueira Guimaraes, Euler Roberto Fernandes Manenti, Isabela Moraes Gomes, Karen Brasil Ruschel, Tatiani Oliveira Fereguetti, Silvana Mangeon Mereilles Guimaraes, Liege Barella Zandona, Jessica Rayane Correa Silva da Fonseca, and Juliana Machado Rugolo

Subjects
Ensemble forecasting, Meta learning (computer science), Computer science, business.industry, Machine learning, computer.software_genre, Class (biology), Outcome (probability), Cross-validation, Task (project management), Artificial intelligence, business, computer, Reliability (statistics), Interpretability
Abstract

ObjectiveTo provide a thorough comparative study among state-of-the-art machine learning methods and statistical methods for determining in-hospital mortality in COVID-19 patients using data upon hospital admission; to study the reliability of the predictions of the most effective methods by correlating the probability of the outcome and the accuracy of the methods; to investigate how explainable are the predictions produced by the most effective methods.Materials and MethodsDe-identified data were obtained from COVID-19 positive patients in 36 participating hospitals, from March 1 to September 30, 2020. Demographic, comorbidity, clinical presentation and laboratory data were used as training data to develop COVID-19 mortality prediction models. Multiple machine learning and traditional statistics models were trained on this prediction task using a folded cross-validation procedure, from which we assessed performance and interpretability metrics.ResultsThe Stacking of machine learning models improved over the previous state-of-the-art results by more than 26% in predicting the class of interest (death), achieving 87.1% of AUROC and macro F1 of 73.9%. We also show that some machine learning models can be very interpretable and reliable, yielding more accurate predictions while providing a good explanation for the ‘why’.ConclusionThe best results were obtained using the meta-learning ensemble model – Stacking. State-of the art explainability techniques such as SHAP-values can be used to draw useful insights into the patterns learned by machine-learning algorithms. Machine-learning models can be more explainable than traditional statistics models while also yielding highly reliable predictions.

Published
2021
Full Text
View/download PDF

11. ABC2-SPH risk score for in-hospital mortality in COVID-19 patients: development, external validation and comparison with other available scores

Author

Natalia Lima Rangel, Daniel Taiar Marinho Oliveira Ferrara, Natalia da Cunha Severino Sampaio, Máderson Alvares de Souza Cabral, Angelinda Rezende Bhering, Emanuele Marianne Souza Kroger, Rafael Lima Rodrigues de Carvalho, Lucas de Deus Sousa, Ana Luiza Bahia Alves Scotton, Roger Mendes de Abreu, Fernando Graca Aranha, Meire Pereira de Figueiredo, Guilherme Fagundes Nascimento, Luanna da Silva Monteiro, Frederico Bartolazzi, Juliana Machado Rugolo, Maria Aparecida Camargos Bicalho, Luciana Siuves Ferreira Couto, Rochele Mosmann Menezes, Luciane Kopittke, Natalia Trifiletti Crespo, Daniela Ponce, Eric Boersma, Patricia Klarmann Ziegelmann, Amanda de Oliveira Maurilio, Carisi Anne Polanczyk, Raquel Lutkmeier, Christiane Correa Rodrigues cimini, Bruno Mateus de Castro, Giovanna Grunewald Vietta, José Miguel Chatkin, Neimy Ramos de Oliveira, Thaís Lorenna Souza Sales, Lilian Santos Pinheiro, Angelica Aparecida Coelho Madureira, Gisele Alsina Nader Bastos, Elayne Crestani Pereira, Fernanda Barbosa Lucas, Karen Cristina Jung Rech Pontes, Maria Angelica Pires Ferreira, Liliane Souto Pacheco, Raphael Castro Martins, Andre Soares de Moura Costa, Helena Duani, Roberta Xavier Campos, Andre Pinheiro Weber, Matheus Carvalho Alves Nogueira, Rodolfo Lucas Silva Mourato, Silvia Ferreira Araujo, Renan Goulart Finger, Adrian Sanchez Montalva, Reginaldo Aparecido Valacio, Daniel Vitorio Silveira, Magda Carvalho Pires, Maíra Viana Rego Souza e Silva, Marcela Goncalves Trindade Tofani, Milena Soriano Marcolino, Saionara Cristina Francisco, Karen Brasil Ruschel, Tatiani Oliveira Fereguetti, L. E. F. Ramos, Israel Júnior Borges do Nascimento, Thaiza Simonia Marinho Albino de Araujo, Silvana Mangeon Mereilles Guimaraes, Rafaela dos Santos Charao de Almeida, Marcus Vinicius de Melo Andrade, Joanna d'Arc Lyra Batista, Andressa Barreto Glaeser, Veridiana Baldon dos Santos Santos, Henrique Cerqueira Guimaraes, Vitor Augusto Lima do Vale, Joice Coutinho de Alvarenga, Heloisa Reniers Vianna, Ricardo Bertoglio Cardoso, Petrônio José de Lima Martelli, Glicia Cristina de Castro Madeira, Fernando Anschau, Tatiana Kurtz, Milton Henriques Guimaraes Junior, Maria Clara Pontello Barbosa Lima, Mariana Frizzo de Godoy, Luana Martins Oliveira, Kauane Aline Maciel dos Santos, Gabriela Petry Crestani, Luisa Elem Almeida Santos, Fernando Antônio Botoni, Carla Thais Candida Alves da Silva, Felipe Barbosa Vallt, Rufino de Freitas Silva, Cintia Alcantara de Carvalho, Barbara Lopes Farace, Diego Henrique de Vasconcelos, Luis Cesar Souto de Moura, Alexandre Vargas Schwarbold, Karina Paula Medeiros Prado Martins, Julia Drumond Parreiras de Morais, Luís César de Castro, Pedro Ledic Assaf, Maiara Anschau Floriani, Roberta Pozza, Maira Dias Souza, Isabela Moraes Gomes, Susany Anastacia Pereira, Thainara Conceicao de Oliveira, Yuri Carlotto Ramires, Carolina Marques Ramos, Israel Molina Romero, Caroline Danubia Gomes, Rafael Guimarães Tavares da Silva, Marilia Mastrocolla de Almeida Cardoso, Berta Raventós, Leonardo Seixas de Oliveira, Virginia Mara Reis Gomes, Talita Fischer Oliveira, Thulio Henrique Oliveira Diniz, Julia Di Sabatino Santos Guimaraes, Ana Paula Beck da Silva Etges, Helena Carolina Noal, Marcelo Carneiro, and Edilson Cezar

Subjects
medicine.medical_specialty, Percentile, Framingham Risk Score, biology, business.industry, C-reactive protein, Emergency department, Logistic regression, Internal medicine, Cohort, Risk of mortality, biology.protein, Medicine, business, Blood urea nitrogen
Abstract

ObjectiveTo develop and validate a rapid scoring system at hospital admission for predicting in-hospital mortality in patients hospitalized with coronavirus disease 19 (COVID-19), and to compare this score with other existing ones.DesignCohort studySettingThe Brazilian COVID-19 Registry has been conducted in 36 Brazilian hospitals in 17 cities. Logistic regression analysis was performed to develop a prediction model for in-hospital mortality, based on the 3978 patients that were admitted between March-July, 2020. The model was then validated in the 1054 patients admitted during August-September, as well as in an external cohort of 474 Spanish patients.ParticipantsConsecutive symptomatic patients (≥18 years old) with laboratory confirmed COVID-19 admitted to participating hospitals. Patients who were transferred between hospitals and in whom admission data from the first hospital or the last hospital were not available were excluded, as well those who were admitted for other reasons and developed COVID-19 symptoms during their stay.Main outcome measuresIn-hospital mortalityResultsMedian (25th-75th percentile) age of the model-derivation cohort was 60 (48-72) years, 53.8% were men, in-hospital mortality was 20.3%. The validation cohorts had similar age distribution and in-hospital mortality. From 20 potential predictors, seven significant variables were included in the in-hospital mortality risk score: age, blood urea nitrogen, number of comorbidities, C-reactive protein, SpO2/FiO2ratio, platelet count and heart rate. The model had high discriminatory value (AUROC 0.844, 95% CI 0.829 to 0.859), which was confirmed in the Brazilian (0.859) and Spanish (0.899) validation cohorts. Our ABC2-SPH score showed good calibration in both Brazilian cohorts, but, in the Spanish cohort, mortality was somewhat underestimated in patients with very high (>25%) risk. The ABC2-SPH score is implemented in a freely available online risk calculator (https://abc2sph.com/).ConclusionsWe designed and validated an easy-to-use rapid scoring system based on characteristics of COVID-19 patients commonly available at hospital presentation, for early stratification for in-hospital mortality risk of patients with COVID-19.Summary boxesWhat is already known on this topic?Rapid scoring systems may be very useful for fast and effective assessment of COVID-19 patients in the emergency department.The majority of available scores have high risk of bias and lack benefit to clinical decision making.Derivation and validation studies in low- and middle-income countries, including Latin America, are scarce.What this study addsABC2-SPH employs seven well defined variables, routinely assessed upon hospital presentation: age, number of comorbidities, blood urea nitrogen, C reactive protein, Spo2/FiO2 ratio, platelets and heart rate.This easy-to-use risk score identified four categories at increasing risk of death with a high level of accuracy, and displayed better discrimination ability than other existing scores.A free web-based calculator is available and may help healthcare practitioners to estimate the expected risk of mortality for patients at hospital presentation.

Published
2021
Full Text
View/download PDF

12. BIS monitoring in sedated, mechanically ventilated patients: right tool in the wrong patients? A meta-analysis

Author

Cassio Mallmann, Renan Goulart Finger, and Wagner Luis Nedel

Subjects
medicine.medical_specialty, business.industry, Pain medicine, Treatment outcome, 030208 emergency & critical care medicine, Critical Care and Intensive Care Medicine, Respiration, Artificial, 03 medical and health sciences, Intensive Care Units, 0302 clinical medicine, Consciousness Monitors, Treatment Outcome, Anesthesiology, Meta-analysis, medicine, Humans, Hypnotics and Sedatives, 030212 general & internal medicine, Consciousness monitors, Deep Sedation, Intensive care medicine, business
Published
2016

Catalog

Books, media, physical & digital resources
See catalog results