Emergency department use and Artificial Intelligence in Pelotas: design and baseline results.

OBJETIVO: To describe the initial baseline results of a population-based study, as well as a protocol in order to evaluate the performance of different machine learning algorithms with the objective of predicting the demand for urgent and emergency services in a representative sample of adults from the urban area of Pelotas, Southern Brazil. METHODS: The study is entitled "Emergency department use and Artificial Intelligence in PELOTAS (RS) (EAI PELOTAS)" (https://wp.ufpel.edu.br/eaipelotas/). Between September and December 2021, a baseline was carried out with participants. A follow-up was planned to be conducted after 12 months in order to assess the use of urgent and emergency services in the last year. Afterwards, machine learning algorithms will be tested to predict the use of urgent and emergency services over one year. RESULTS: In total, 5,722 participants answered the survey, mostly females (66.8%), with an average age of 50.3 years. The mean number of household people was 2.6. Most of the sample has white skin color and incomplete elementary school or less. Around 30% of the sample has obesity, 14% diabetes, and 39% hypertension. CONCLUSION: The present paper presented a protocol describing the steps that were and will be taken to produce a model capable of predicting the demand for urgent and emergency services in one year among residents of Pelotas, in Rio Grande do Sul state.

Emergency department use and Artificial Intelligence in Pelotas: design and baseline results / Uso serviços de serviços de urgência e emergência e Inteligência Artificial em Pelotas: protocolo e resultados iniciais

RESUMO Objetivo: To describe the initial baseline results of a population-based study, as well as a protocol in order to evaluate the performance of different machine learning algorithms with the objective of predicting the demand for urgent and emergency services in a representative sample of adults from the urban area of Pelotas, Southern Brazil. Methods: The study is entitled "Emergency department use and Artificial Intelligence in PELOTAS (RS) (EAI PELOTAS)" (https://wp.ufpel.edu.br/eaipelotas/). Between September and December 2021, a baseline was carried out with participants. A follow-up was planned to be conducted after 12 months in order to assess the use of urgent and emergency services in the last year. Afterwards, machine learning algorithms will be tested to predict the use of urgent and emergency services over one year. Results: In total, 5,722 participants answered the survey, mostly females (66.8%), with an average age of 50.3 years. The mean number of household people was 2.6. Most of the sample has white skin color and incomplete elementary school or less. Around 30% of the sample has obesity, 14% diabetes, and 39% hypertension. Conclusion: The present paper presented a protocol describing the steps that were and will be taken to produce a model capable of predicting the demand for urgent and emergency services in one year among residents of Pelotas, in Rio Grande do Sul state.

RESUMO Objetivo: Descrever os resultados iniciais da linha de base de um estudo de base populacional, bem como um protocolo para avaliar o desempenho de diferentes algoritmos de aprendizado de máquina, com o objetivo de predizer a demanda de serviços de urgência e emergência em uma amostra representativa de adultos da zona urbana de Pelotas, no Sul do Brasil. Métodos: O estudo intitula-se "Emergency department use and Artificial Intelligence in PELOTAS (RS) (EAI PELOTAS)" (https://wp.ufpel.edu.br/eaipelotas/). Entre setembro e dezembro de 2021, foi realizada uma linha de base com os participantes. Está previsto um acompanhamento após 12 meses para avaliar a utilização de serviços de urgência e emergência no último ano. Em seguida, serão testados algoritmos de machine learning para predizer a utilização de serviços de urgência e emergência no período de um ano. Resultados: No total, 5.722 participantes responderam à pesquisa, a maioria do sexo feminino (66,8%), com idade média de 50,3 anos. O número médio de pessoas no domicílio foi de 2,6. A maioria da amostra tem cor da pele branca e ensino fundamental incompleto ou menos. Cerca de 30% da amostra estava com obesidade, 14% com diabetes e 39% eram hipertensos. Conclusão: O presente trabalho apresentou um protocolo descrevendo as etapas que foram e serão tomadas para a produção de um modelo capaz de prever a demanda por serviços de urgência e emergência em um ano entre moradores de Pelotas, no estado do Rio Grande do Sul.

Does socioeconomic inequality occur in the multimorbidity among Brazilian adults?

OBJECTIVE: To assess the prevalence of multimorbidity among Brazilian adults and its association with socioeconomic indicators. METHODS: Cross-sectional study that used data from the Pesquisa Nacional Sobre Acesso, Utilização e Promoção do Uso Racional de Medicamentos no Brasil (PNAUM - Brazilian National Survey on Access, Use and Promotion of Rational Use of Medicines), carried out between 2013 and 2014. The definition of multimorbidity was the coexistence, in a single individual, of two or more chronic diseases, measured through a list of 14 morbidities (self-reported medical diagnosis throughout life). Economic status and educational level were the socioeconomic indicators used, being the inequalities assessed through the Slope Index of Inequality (SII) and the Concentration Index, stratified by gender. RESULTS: The study comprehended 23,329 adults (52.8% of which were women), with an average age of 37.9 years. Hypertension and high cholesterol levels were the most prevalent conditions. The prevalence of multimorbidity was of 10.9% (95%CI 10.1-11.7) representing nearly 11 million individuals in Brazil, of which 14.5% (95%CI 13.5-15.4) were women and 6.8% (95%CI 5.9-7.8) were men. The occurrence of multimorbidity was similar according to the socioeconomic indicators. In the inequality analysis, we observed absolute and relative differences in men with a higher purchasing power (SII = 3.7; 95%CI 0.3-7.0) and higher educational level (CIX = 7.1; 95%CI 0.9-14.7), respectively. CONCLUSIONS: The frequency of comorbidities in Brazilian adults is high, especially in absolute terms. We only observed socioeconomic inequalities in multimorbidities among men.

Does socioeconomic inequality occur in the multimorbidity among Brazilian adults? / Existe desigualdade socioeconômica na multimorbidade entre adultos brasileiros?

ABSTRACT OBJECTIVE: To assess the prevalence of multimorbidity among Brazilian adults and its association with socioeconomic indicators. METHODS: Cross-sectional study that used data from the Pesquisa Nacional Sobre Acesso, Utilização e Promoção do Uso Racional de Medicamentos no Brasil (PNAUM - Brazilian National Survey on Access, Use and Promotion of Rational Use of Medicines), carried out between 2013 and 2014. The definition of multimorbidity was the coexistence, in a single individual, of two or more chronic diseases, measured through a list of 14 morbidities (self-reported medical diagnosis throughout life). Economic status and educational level were the socioeconomic indicators used, being the inequalities assessed through the Slope Index of Inequality (SII) and the Concentration Index, stratified by gender. RESULTS: The study comprehended 23,329 adults (52.8% of which were women), with an average age of 37.9 years. Hypertension and high cholesterol levels were the most prevalent conditions. The prevalence of multimorbidity was of 10.9% (95%CI 10.1-11.7) representing nearly 11 million individuals in Brazil, of which 14.5% (95%CI 13.5-15.4) were women and 6.8% (95%CI 5.9-7.8) were men. The occurrence of multimorbidity was similar according to the socioeconomic indicators. In the inequality analysis, we observed absolute and relative differences in men with a higher purchasing power (SII = 3.7; 95%CI 0.3-7.0) and higher educational level (CIX = 7.1; 95%CI 0.9-14.7), respectively. CONCLUSIONS: The frequency of comorbidities in Brazilian adults is high, especially in absolute terms. We only observed socioeconomic inequalities in multimorbidities among men.

RESUMO OBJETIVO: Avaliar a prevalência de multimorbidade e a associação desta com indicadores socioeconômicos entre adultos brasileiros. MÉTODOS: Estudo transversal que utilizou dados oriundos da Pesquisa Nacional sobre Acesso, Utilização e Promoção do Uso Racional de Medicamentos no Brasil, realizada entre 2013 e 2014. Multimorbidade foi definida como a coexistência, no mesmo indivíduo, de duas ou mais doenças crônicas, e é mensurada a partir de uma lista de 14 morbidades (autorrelato de diagnóstico médico na vida). Classe econômica e escolaridade foram os indicadores socioeconômicos utilizados, sendo as desigualdades avaliadas pelo Slope Index of Inequality (SII) e pelo Concentration Index (CIX), estratificadas por sexo. RESULTADOS: O estudo considerou 23.329 mil adultos (52,8% de mulheres), com média de idade de 37,9 anos. Hipertensão e colesterol alto foram as condições mais prevalentes. A prevalência de multimorbidade foi de 10,9% (IC95% 10,1-11,7), representando, aproximadamente, 11 milhões de indivíduos no Brasil, sendo 14,5% (IC95% 13,5-15,4) entre mulheres e 6,8% (IC95% 5,9-7,8) entre homens. A ocorrência de multimorbidade foi similar segundo os indicadores socioeconômicos. Nas análises de desigualdade, observou-se diferença absoluta e relativa para homens com maior poder aquisitivo (SII = 3,7; IC95% 0,3-7,0) e maior escolaridade (CIX = 7,1; IC95% 0,9-14,7), respectivamente. CONCLUSÕES: A frequência de adultos brasileiros com multimorbidade é alta, principalmente em termos absolutos. Desigualdades socioeconômicas na multimorbidade foram observadas somente entre homens.