RESUMO
Characterized as a neglected disease, Chagas disease is an infection that, in the current scenario, affects about 8 million people per year, with a higher incidence in underdeveloped countries, Chagas is responsible for physiological disabilities that result in impacts that are slightly reflected in world socioeconomic stability. Although treatments are based on drugs such as Benznidazole, the pathology lacks a continuous treatment method with low toxicological incidence. The present study estimates the anti-chagasic activity of the synthetic chalcone CPN2F based on the alignment between in vitro tests and structural classification in silico studies, molecular docking and ADMET studies. The in vitro tests showed a reduction in the protozoan metabolism in host cells (LLC-MK2). At the same time, the molecular docking models evaluate this growth inhibition through the synergistic effect associated with Benznida- zole against validated therapeutic target key stages (Cruzaine TcGAPDH and Trypanothione reductase) of the Trypanosoma cruzi development cycle. The in silico prediction results reveal an alignment between pharmacokinetic attributes, such as renal absorption and release, which allow the preparation of CPN2F as an antichagasic drug with a low incidence of organic toxicity.Communicated by Ramaswamy H. Sarma.
RESUMO
Objective: Identify the risk of patients with Chronic Chagas Cardiomyopathy (CCC) to prevent them from having Sudden Cardiac Death (SCD). Methods: We developed an SCD prediction system using a heterogeneous dataset of chagasic patients evaluated in 9 state-of-the-art machine learning algorithms to select the most critical clinical variables and predict SCD in chagasic patients even when the interval between the most recent exams and the SCD event is months or years. Results: 310 patients were analyzed, being 81 (14,7%) suffering from SCD. In the study, Balanced Random Forest showed the best performance, with AUC:80.03 and F1:75.12. Due to their high weights in the machine learning classifiers, we suggest Holter - Non-Sustained Ventricular Tachycardia, Total Ventricular Extrasystoles, Left Ventricular Systolic Diameter, Syncope, and Left Ventricular Diastolic Diameter as essential features to identify SCD. Conclusion: The high-risk pattern of SCD in patients with CCC can be identified and prevented based on clinical and laboratory variables.
Objetivo: Identificar o risco de pacientes com Cardiomiopatia Chagásica Crônica (CCC) para prevenir a Morte Súbita Cardíaca (MSC). Métodos: Desenvolvemos um sistema de MSC usando um conjunto de dados heterogêneo de pacientes chagásicos avaliados em 9 algoritmos de aprendizado de máquina de última geração para selecionar as variáveis clínicas mais críticas e prever MSC em pacientes chagásicos mesmo quando o intervalo mais recente entre os mais recentes exames e o evento MSC é meses ou anos. Resultados: Foram analisados 310 pacientes, sendo 81 (14,7%) portadores de CCC. No estudo, o algoritmo Balanced Random Forest apresentou o melhor desempenho, com AUC:80,03 e F1:75,12. Devido ao seu alto peso nos classificadores de aprendizado de máquina, sugerimos Holter - Taquicardia Ventricular Não Sustentada, Extrassístoles Ventriculares Totais, Diâmetro Sistólico do Ventrículo Esquerdo, Síncope e Diâmetro Diastólico do Ventrículo Esquerdo como características essenciais para identificar a CCC. Conclusão: O padrão de alto risco de MSC em pacientes com CCC pode ser identificado e prevenido com base em variáveis clínicas e laboratoriais.
Objetivo: Identificar el riesgo de los pacientes con Miocardiopatía Chagásica Crónica (MCC) para evitar que presenten Muerte Cardíaca Súbita (MCS). Métodos: Desarrollamos un sistema MCS utilizando un conjunto de datos heterogéneo de pacientes chagásicos evaluados en 9 algoritmos de aprendizaje automático de última generación para seleccionar las variables clínicas más críticas y predecir MCS en pacientes chagásicos incluso cuando el intervalo más reciente entre los más recientes exámenes y el evento MCS es meses o años. Resultados: Se analizaron 310 pacientes, siendo 81 (14,7%) con MSC. En el estudio, Balanced Random Forest mostró el mejor desempeño, con AUC:80.03 y F1:75.12. Debido a su alto peso en los clasificadores de aprendizaje automático, sugerimos Holter - Taquicardia ventricular no sostenida, Extrasístoles ventriculares totales, Diámetro sistólico del ventrículo izquierdo, Síncope y Diámetro diastólico del ventrículo izquierdo como características esenciales para identificar la MSC. Conclusión: El patrón de alto riesgo de MSC en pacientes con MCC se puede identificar y prevenir con base en variables clínicas y de laboratorio.
