RESUMO
OBJECTIVE: COVID-19 has brought emerging public health emergency and new challenges. It configures a complex panorama that has been requiring a set of coordinated actions and has innovation as one of its pillars. In particular, the use of digital tools plays an important role. In this context, this study presents a screening algorithm that uses a machine learning model to assess the probability of a diagnosis of COVID-19 based on clinical data. METHODS: This algorithm was made available for free on an online platform. The project was developed in three phases. First, an machine learning risk model was developed. Second, a system was developed that would allow the user to enter patient data. Finally, this platform was used in teleconsultations carried out during the pandemic period. RESULTS: The number of accesses during the period was 4,722. A total of 126 assistances were carried out from March 23, 2020, to June 16, 2020, and 107 satisfaction survey returns were received. The response rate to the questionnaires was 84.92%, and the ratings obtained regarding the satisfaction level were higher than 4.8 (on a 0-5 scale). The Net Promoter Score was 94.4. CONCLUSION: To the best of our knowledge, this is the first online application of its kind that presents a probabilistic assessment of COVID-19 using machine learning models exclusively based on the symptoms and clinical characteristics of users. The level of satisfaction was high. The integration of machine learning tools in telemedicine practice has great potential.
Assuntos
COVID-19 , Telemedicina , Humanos , COVID-19/diagnóstico , Aprendizado de Máquina , Algoritmos , Inquéritos e Questionários , Teste para COVID-19RESUMO
Depression is a widespread disease with a high economic burden and a complex pathophysiology disease that is still not wholly clarified, not to mention it usually is associated as a risk factor for absenteeism at work and suicide. Just 50% of patients with depression are diagnosed in primary care, and only 15% receive treatment. Stigmatization, the coexistence of somatic symptoms, and the need to remember signs in the past two weeks can contribute to explaining this situation. In this context, tools that can serve as diagnostic screening are of great value, as they can reduce the number of undiagnosed patients. Besides, Artificial Intelligence (AI) has enabled several fruitful applications in medicine, particularly in psychiatry. This study aims to evaluate the performance of Machine Learning (ML) algorithms in the detection of depressive patients from the clinical, laboratory, and sociodemographic data obtained from the Brazilian National Network for Research on Cardiovascular Diseases from June 2016 to July 2018. The results obtained are promising. In one of them, Random Forests, the accuracy, sensibility, and area under the receiver operating characteristic curve were, respectively, 0.89, 0.90, and 0.87.
Assuntos
Inteligência Artificial , Depressão , Algoritmos , Brasil/epidemiologia , Depressão/diagnóstico , Depressão/epidemiologia , Humanos , Aprendizado de Máquina , Atenção Primária à SaúdeRESUMO
BACKGROUND: Cardiovascular disease (CVD) mortality, after several decades of decrease, has shown a tendency towards the stabilization in some countries, including Brazil and Rio de Janeiro state. This new tendency was not further analyzed by gender, age group and region of the Rio de Janeiro state. OBJECTIVE: To analyze the trends of premature and late mortality from CVD, ischemic heart disease (IHD) and cerebrovascular disease (CBVD) by gender in the city of Rio de Janeiro (capital) and the health regions of Rio de Janeiro state (from 1996 to 2016. METHODS: Data on deaths and the population were obtained from DATASUS/MS. The rates were compensated by ill-defined codes, corrected by Ill-Defined Cardiovascular codes and gender and age-adjusted by the direct method (reference population - population of the state of Rio de Janeiro - 2000 census). The Joinpoint Trend Analysis Software was employed. RESULTS: IHD mortality stabilized or even increased for at least 50% of the analyzed areas (EAPC≥0). No change was observed. in the "North" and "Northwest" regions For CBVD, just one region showed stability regarding mortality (EAPC close to 0). For the other regions, the rate continued to decrease (APC<0) until 2016. CONCLUSION: These results observed in Rio de Janeiro are possibly appropriate to various Brazilian regions and demonstrate that a serious public health response is needed to address lifestyle behaviors. Primary care physicians should also be familiar with the unfavorable tendency in coronary heart disease among younger adults in recent years and actively screen for risk factors for cardiovascular disease, paying special attention to women.
FUNDAMENTO: A mortalidade por doenças cardiovasculares (DCV) vem mostrando tendência à estabilização em alguns países, incluindo o Brasil e o estado do Rio de Janeiro, após décadas de queda. Não encontramos análises detalhadas dessa tendência para o estado do Rio de Janeiro. OBJETIVO: Analisar as tendências da mortalidade prematura e tardia por doenças do aparelho circulatório (DAC), doença isquêmica do coração (DIC) e doença cerebrovascular (DCBV) por sexo nas regiões de saúde do estado do Rio de Janeiro e capital (1996-2016). MÉTODOS: Dados de óbitos e população foram obtidos no DATASUS/MS. Taxas foram compensadas por códigos mal definidos, corrigidos pelos códigos cardiovasculares mal definidos e ajustadas por sexo e idade pelo método direto. O Joinpoint Trend Analysis Software foi empregado para calcular a variação percentual anual (APC) e variação percentual anual média (AAPC). Foram consideradas para o estudo APC e AAPC significativamente diferentes de zero, calculadas por um teste de student com significância de 5%. RESULTADOS: A mortalidade por DIC estabilizou ou até aumentou em pelo menos 50% das localidades analisadas (EAPC ≥0). Nas regiões Norte e Noroeste, nenhuma mudança foi observada. Para DCBV, apenas uma região apresentou estabilidade na mortalidade (EAPC próximo a 0). Para as outras regiões, a taxa continuou a diminuir (APC <0) até 2016. CONCLUSÃO: Esses resultados observados no Rio de Janeiro devem se repetir em várias regiões brasileiras e apontam para a necessidade de uma resposta na abordagem dos comportamentos no estilo de vida. Os médicos da atenção primária devem estar familiarizados com a tendência desfavorável da doença isquêmica do coração entre os adultos mais jovens e rastrear ativamente os fatores de risco para DCV, com atenção especial às mulheres.
Assuntos
Doenças Cardiovasculares , Transtornos Cerebrovasculares , Isquemia Miocárdica , Adulto , Brasil/epidemiologia , Cidades , Feminino , HumanosRESUMO
BACKGROUND: In many cities around the world, the mortality rate from cancer (CA) has exceeded that from disease of the circulatory system (DCS). OBJECTIVES: To compare the mortality curves from DCS and CA in the most populous capital cities of the five regions of Brazil. METHODS: Data of mortality rates from DCS and CA between 2000 and 2015 were collected from the Mortality Information System of Manaus, Salvador, Goiania, Sao Paulo and Curitiba, and categorized by age range into early (30-69 years) and late (≥ 70 years), and by gender of the individuals. Chapters II and IX of the International Classification of Diseases-10 were used for the analysis of causes of deaths. The Joinpoint regression model was used to assess the tendency of the estimated annual percentage change of mortality rate, and the Monte Carlo permutation test was used to detect when changes occurred. Statistical significance was set at 5%. RESULTS: There was a consistent decrease in early and late mortality from DCS in both genders in the cities studied, except for late mortality in men in Manaus. There was a tendency of decrease of mortality rates from CA in São Paulo and Curitiba, and of increase in the rates from CA in Goiania. In Salvador, there was a decrease in early mortality from CA in men and women and an increase in late mortality in both genders. CONCLUSION: There was a progressive and marked decrease in the mortality rate from DCS and a maintenance or slight increase in CA mortality in the five capital cities studied. These phenomena may lead to the intersection of the curves, with predominance of mortality from CA (old and new cases).
Assuntos
Doenças Cardiovasculares/mortalidade , Mortalidade/tendências , Neoplasias/mortalidade , Adulto , Distribuição por Idade , Fatores Etários , Idoso , Brasil/epidemiologia , Causas de Morte/tendências , Cidades/epidemiologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Método de Monte Carlo , Distribuição por Sexo , Fatores Sexuais , Fatores de TempoRESUMO
The recent advances at hardware level and the increasing requirement of personalization of care associated with the urgent needs of value creation for the patients has helped Artificial Intelligence (AI) to promote a significant paradigm shift in the most diverse areas of medical knowledge, particularly in Cardiology, for its ability to support decision-making and improve diagnostic and prognostic performance. In this context, the present work does a non-systematic review of the main papers published on AI in Cardiology, focusing on its main applications, potential impacts and challenges.
Assuntos
Inteligência Artificial , Cardiologia , HumanosRESUMO
SUMMARY OBJECTIVE: COVID-19 has brought emerging public health emergency and new challenges. It configures a complex panorama that has been requiring a set of coordinated actions and has innovation as one of its pillars. In particular, the use of digital tools plays an important role. In this context, this study presents a screening algorithm that uses a machine learning model to assess the probability of a diagnosis of COVID-19 based on clinical data. METHODS: This algorithm was made available for free on an online platform. The project was developed in three phases. First, an machine learning risk model was developed. Second, a system was developed that would allow the user to enter patient data. Finally, this platform was used in teleconsultations carried out during the pandemic period. RESULTS: The number of accesses during the period was 4,722. A total of 126 assistances were carried out from March 23, 2020, to June 16, 2020, and 107 satisfaction survey returns were received. The response rate to the questionnaires was 84.92%, and the ratings obtained regarding the satisfaction level were higher than 4.8 (on a 0-5 scale). The Net Promoter Score was 94.4. CONCLUSION: To the best of our knowledge, this is the first online application of its kind that presents a probabilistic assessment of COVID-19 using machine learning models exclusively based on the symptoms and clinical characteristics of users. The level of satisfaction was high. The integration of machine learning tools in telemedicine practice has great potential.
RESUMO
Resumo Fundamento: A mortalidade por doenças cardiovasculares (DCV) vem mostrando tendência à estabilização em alguns países, incluindo o Brasil e o estado do Rio de Janeiro, após décadas de queda. Não encontramos análises detalhadas dessa tendência para o estado do Rio de Janeiro. Objetivo: Analisar as tendências da mortalidade prematura e tardia por doenças do aparelho circulatório (DAC), doença isquêmica do coração (DIC) e doença cerebrovascular (DCBV) por sexo nas regiões de saúde do estado do Rio de Janeiro e capital (1996-2016). Métodos: Dados de óbitos e população foram obtidos no DATASUS/MS. Taxas foram compensadas por códigos mal definidos, corrigidos pelos códigos cardiovasculares mal definidos e ajustadas por sexo e idade pelo método direto. O Joinpoint Trend Analysis Software foi empregado para calcular a variação percentual anual (APC) e variação percentual anual média (AAPC). Foram consideradas para o estudo APC e AAPC significativamente diferentes de zero, calculadas por um teste de student com significância de 5%. Resultados: A mortalidade por DIC estabilizou ou até aumentou em pelo menos 50% das localidades analisadas (EAPC ≥0). Nas regiões Norte e Noroeste, nenhuma mudança foi observada. Para DCBV, apenas uma região apresentou estabilidade na mortalidade (EAPC próximo a 0). Para as outras regiões, a taxa continuou a diminuir (APC <0) até 2016. Conclusão: Esses resultados observados no Rio de Janeiro devem se repetir em várias regiões brasileiras e apontam para a necessidade de uma resposta na abordagem dos comportamentos no estilo de vida. Os médicos da atenção primária devem estar familiarizados com a tendência desfavorável da doença isquêmica do coração entre os adultos mais jovens e rastrear ativamente os fatores de risco para DCV, com atenção especial às mulheres.
Abstract Background: Cardiovascular disease (CVD) mortality, after several decades of decrease, has shown a tendency towards the stabilization in some countries, including Brazil and Rio de Janeiro state. This new tendency was not further analyzed by gender, age group and region of the Rio de Janeiro state. Objective: To analyze the trends of premature and late mortality from CVD, ischemic heart disease (IHD) and cerebrovascular disease (CBVD) by gender in the city of Rio de Janeiro (capital) and the health regions of Rio de Janeiro state (from 1996 to 2016. Methods: Data on deaths and the population were obtained from DATASUS/MS. The rates were compensated by ill-defined codes, corrected by Ill-Defined Cardiovascular codes and gender and age-adjusted by the direct method (reference population - population of the state of Rio de Janeiro - 2000 census). The Joinpoint Trend Analysis Software was employed. Results: IHD mortality stabilized or even increased for at least 50% of the analyzed areas (EAPC≥0). No change was observed. in the "North" and "Northwest" regions For CBVD, just one region showed stability regarding mortality (EAPC close to 0). For the other regions, the rate continued to decrease (APC<0) until 2016. Conclusion: These results observed in Rio de Janeiro are possibly appropriate to various Brazilian regions and demonstrate that a serious public health response is needed to address lifestyle behaviors. Primary care physicians should also be familiar with the unfavorable tendency in coronary heart disease among younger adults in recent years and actively screen for risk factors for cardiovascular disease, paying special attention to women.
Assuntos
Humanos , Feminino , Adulto , Doenças Cardiovasculares , Transtornos Cerebrovasculares , Isquemia Miocárdica , Brasil/epidemiologia , CidadesRESUMO
Abstract Background: In many cities around the world, the mortality rate from cancer (CA) has exceeded that from disease of the circulatory system (DCS). Objectives: To compare the mortality curves from DCS and CA in the most populous capital cities of the five regions of Brazil. Methods: Data of mortality rates from DCS and CA between 2000 and 2015 were collected from the Mortality Information System of Manaus, Salvador, Goiania, Sao Paulo and Curitiba, and categorized by age range into early (30-69 years) and late (≥ 70 years), and by gender of the individuals. Chapters II and IX of the International Classification of Diseases-10 were used for the analysis of causes of deaths. The Joinpoint regression model was used to assess the tendency of the estimated annual percentage change of mortality rate, and the Monte Carlo permutation test was used to detect when changes occurred. Statistical significance was set at 5%. Results: There was a consistent decrease in early and late mortality from DCS in both genders in the cities studied, except for late mortality in men in Manaus. There was a tendency of decrease of mortality rates from CA in São Paulo and Curitiba, and of increase in the rates from CA in Goiania. In Salvador, there was a decrease in early mortality from CA in men and women and an increase in late mortality in both genders. Conclusion: There was a progressive and marked decrease in the mortality rate from DCS and a maintenance or slight increase in CA mortality in the five capital cities studied. These phenomena may lead to the intersection of the curves, with predominance of mortality from CA (old and new cases).
Resumo Fundamento: Em muitas cidades no mundo, a taxa de mortalidade por câncer (CA) ultrapassou aquela por doenças do aparelho circulatório (DAC). Objetivos: Comparar as curvas de mortalidade por DAC e CA nas capitais mais populosas das cinco regiões brasileiras. Métodos: Dados de mortalidade por DAC e CA entre 2000 e 2015 foram coletadas no Sistema de Informações sobre Mortalidade das capitais mais populosas das cinco regiões do Brasil: Manaus, Salvador, Goiânia, São Paulo e Curitiba. Os dados foram categorizados por faixas etárias dos indivíduos em precoce (30-69 anos) e tardia (≥70 anos), e por gênero. Foram considerados os capítulos II e IX da Classificação Internacional de Doenças-10 para análise das causas de óbito. A tendência na estimativa de mudança percentual foi calculada pelo modelo de regressão Joinpoint 4.6.0.0. e a detecção das mudanças das taxas pelo teste de permutação Monte Carlo. Nível de significância estatística de 5%. Resultados: Observou-se queda consistente das mortalidades precoce e tardia por DAC, em ambos os gêneros, nas capitais estudadas, com exceção da mortalidade tardia em homens em Manaus. Houve tendência de queda das taxas de mortalidade por CA em São Paulo e Curitiba, e de aumento da taxa de mortalidade por CA em Goiânia. Em Salvador, houve queda na mortalidade precoce por CA em homens e mulheres e incremento na mortalidade tardia em ambos os gêneros. Conclusão: Houve queda progressiva e expressiva da taxa de mortalidade por DAC nas cinco capitais em oposição à manutenção ou discreta elevação da mortalidade por CA. Tais fenômenos concorrem para o cruzamento das curvas com predomínio da mortalidade por CA (já ocorrido ou casos novos).
Assuntos
Humanos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Idoso , Doenças Cardiovasculares/mortalidade , Mortalidade/tendências , Neoplasias/mortalidade , Fatores de Tempo , Brasil/epidemiologia , Fatores Sexuais , Método de Monte Carlo , Causas de Morte/tendências , Fatores Etários , Cidades/epidemiologia , Distribuição por Sexo , Distribuição por IdadeRESUMO
Resumo Os recentes avanços ao nível de hardware e a crescente exigência de personalização dos cuidados associados às necessidades urgentes de criação de valor para os pacientes contribuíram para que a Inteligência Artificial (IA) promovesse uma mudança significativa de paradigma nas mais diversas áreas do conhecimento médico, em particular em Cardiologia, por sua capacidade de apoiar a tomada de decisões e melhorar o desempenho diagnóstico e prognóstico. Nesse contexto, o presente trabalho faz uma revisão não-sistemática dos principais trabalhos publicados sobre IA em Cardiologia, com foco em suas principais aplicações, possíveis impactos e desafios.
Abstract The recent advances at hardware level and the increasing requirement of personalization of care associated with the urgent needs of value creation for the patients has helped Artificial Intelligence (AI) to promote a significant paradigm shift in the most diverse areas of medical knowledge, particularly in Cardiology, for its ability to support decision-making and improve diagnostic and prognostic performance. In this context, the present work does a non-systematic review of the main papers published on AI in Cardiology, focusing on its main applications, potential impacts and challenges.