Prediction of septic and hypovolemic shock in intensive care unit patients using machine learning. / Predição de choque séptico e hipovolêmico em pacientes de unidade de terapia intensiva com o uso de machine learning.

OBJECTIVE: To create and validate a model for predicting septic or hypovolemic shock from easily obtainable variables collected from patients at admission to an intensive care unit. METHODS: A predictive modeling study with concurrent cohort data was conducted in a hospital in the interior of northeastern Brazil. Patients aged 18 years or older who were not using vasoactive drugs on the day of admission and were hospitalized from November 2020 to July 2021 were included. The Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost classification algorithms were tested for use in building the model. The validation method used was k-fold cross validation. The evaluation metrics used were recall, precision and area under the Receiver Operating Characteristic curve. RESULTS: A total of 720 patients were used to create and validate the model. The models showed high predictive capacity with areas under the Receiver Operating Characteristic curve of 0.979; 0.999; 0.980; 0.998 and 1.00 for the Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost algorithms, respectively. CONCLUSION: The predictive model created and validated showed a high ability to predict septic and hypovolemic shock from the time of admission of patients to the intensive care unit.

OBJETIVO: Criar e validar um modelo de predição de choque séptico ou hipovolêmico a partir de variáveis de fácil obtenção coletadas na admissão de pacientes internados em uma unidade de terapia intensiva. MÉTODOS: Estudo de modelagem preditiva com dados de coorte concorrente realizada em um hospital do interior do nordeste brasileiro. Foram incluídos pacientes com 18 anos ou mais sem uso de droga vasoativa no dia da admissão e que foram internados entre novembro de 2020 e julho de 2021. Foram testados os algoritmos de classificação do tipo Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost para a construção do modelo. O método de validação utilizado foi o k-fold cross validation. As métricas de avaliação utilizadas foram recall, precisão e área sob a curva Receiver Operating Characteristic. RESULTADOS: Foram utilizados 720 pacientes para criação e validação do modelo. Os modelos apresentaram alta capacidade preditiva com área sob a curva Receiver Operating Characteristic de 0,979; 0,999; 0,980; 0,998 e 1,00 para os algoritmos de Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost, respectivamente. CONCLUSÃO: O modelo preditivo criado e validado apresentou elevada capacidade de predição do choque séptico e hipovolêmico desde o momento da admissão de pacientes na unidade de terapia intensiva.

Anticariogenic activities of Libidibia ferrea, gallic acid and ethyl gallate against Streptococcus mutans in biofilm model.

ETHNOPHARMACOLOGICAL RELEVANCE: In Brazil, ethnopharmacological studies show that Libidibia ferrea (Mart. ex Tul.) L. P. Queiroz is commonly used in folk medicine as an antifungal, antimicrobial and anti-inflammatory. In the Amazon region, the dried fruit powder of L. ferrea are widely used empirically by the population in an alcoholic tincture as an antimicrobial mouthwash in oral infections and the infusion is also recommended for healing oral wounds. However, there are few articles that have evaluated the antimicrobial activity against oral pathogens in a biofilm model, identifying active compounds and mechanisms of action. AIM OF THE STUDY: The aim of this study was to evaluate the antimicrobial and anti-adherence activities of the ethanolic extract, fractions and isolated compounds (gallic acid and ethyl gallate) of the fruit and seed of L. ferrea against Streptococcus mutans. The inhibition of acidicity/acidogenicity and the expression of the S. mutans GTF genes in biofilms were also evaluated. MATERIALS AND METHODS: Minimal Inhibitory Concentration (MIC), Minimum Bactericidal Concentration (MBC) and Minimum Inhibitory Concentration of Cell Adhesion (MICA) were evaluated with ethanolic extract (EELF), fractions, gallic acid (GA) and ethyl gallate (EG) against S. mutans. Inhibition of biofilm formation, pH drop and proton permeability tests were conducted with EELF, GA and EG, and also evaluated the expression of the GTF genes in biofilms. The compounds of dichloromethane fraction were identified by GC-MS. RESULTS: This is the first report of shikimic, pyroglutamic, malic and protocatechuic acids identified in L. ferrea. EELF, GA and EG showed MIC at 250 µg/mL, and MBC at 1000 µg/mL by EELF. EELF biofilms showed reduced dry weight and acidogenicity of S. mutans in biofilms. GA and EG reduced viable cells, glucans soluble in alkali, acidogenicity, aciduricity and downregulated expression of gtfB, gtfC and gtfD genes in biofilms. SEM images of GA and EG biofilms showed a reduction of biomass, exopolysaccharide and microcolonies of S. mutans. CONCLUSIONS: The ethanolic extract of fruit and seed of L. ferrea, gallic acid and ethyl gallate showed great antimicrobial activity and inhibition of adhesion, reduction of acidogenicity and aciduricity in S. mutans biofilms. The results obtained in vitro validate the use of this plant in ethnopharmacology, and open opportunities for the development of new oral anticariogenic agents, originated by plants that can inhibit pathogenic biofilm that leads to the development of caries.

Predição de choque séptico e hipovolêmico em pacientes de unidade de terapia intensiva com o uso de machine learning / Prediction of septic and hypovolemic shock in intensive care unit patients using machine learning

RESUMO Objetivo: Criar e validar um modelo de predição de choque séptico ou hipovolêmico a partir de variáveis de fácil obtenção coletadas na admissão de pacientes internados em uma unidade de terapia intensiva. Métodos: Estudo de modelagem preditiva com dados de coorte concorrente realizada em um hospital do interior do nordeste brasileiro. Foram incluídos pacientes com 18 anos ou mais sem uso de droga vasoativa no dia da admissão e que foram internados entre novembro de 2020 e julho de 2021. Foram testados os algoritmos de classificação do tipo Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost para a construção do modelo. O método de validação utilizado foi o k-fold cross validation. As métricas de avaliação utilizadas foram recall, precisão e área sob a curva Receiver Operating Characteristic. Resultados: Foram utilizados 720 pacientes para criação e validação do modelo. Os modelos apresentaram alta capacidade preditiva com área sob a curva Receiver Operating Characteristic de 0,979; 0,999; 0,980; 0,998 e 1,00 para os algoritmos de Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost, respectivamente. Conclusão: O modelo preditivo criado e validado apresentou elevada capacidade de predição do choque séptico e hipovolêmico desde o momento da admissão de pacientes na unidade de terapia intensiva.

ABSTRACT Objective: To create and validate a model for predicting septic or hypovolemic shock from easily obtainable variables collected from patients at admission to an intensive care unit. Methods: A predictive modeling study with concurrent cohort data was conducted in a hospital in the interior of northeastern Brazil. Patients aged 18 years or older who were not using vasoactive drugs on the day of admission and were hospitalized from November 2020 to July 2021 were included. The Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost classification algorithms were tested for use in building the model. The validation method used was k-fold cross validation. The evaluation metrics used were recall, precision and area under the Receiver Operating Characteristic curve. Results: A total of 720 patients were used to create and validate the model. The models showed high predictive capacity with areas under the Receiver Operating Characteristic curve of 0.979; 0.999; 0.980; 0.998 and 1.00 for the Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost algorithms, respectively. Conclusion: The predictive model created and validated showed a high ability to predict septic and hypovolemic shock from the time of admission of patients to the intensive care unit.