RESUMO
The COVID-19 pandemic is already considered one of the biggest global health crises. In Rio Grande do Norte, a Brazilian state, the RegulaRN platform was the health information system used to regulate beds for patients with COVID-19. This article explored machine learning and deep learning techniques with RegulaRN data in order to identify the best models and parameters to predict the outcome of a hospitalized patient. A total of 25,366 bed regulations for COVID-19 patients were analyzed. The data analyzed comes from the RegulaRN Platform database from April 2020 to August 2022. From these data, the nine most pertinent characteristics were selected from the twenty available, and blank or inconclusive data were excluded. This was followed by the following steps: data pre-processing, database balancing, training, and test. The results showed better performance in terms of accuracy (84.01%), precision (79.57%), and F1-score (81.00%) for the Multilayer Perceptron model with Stochastic Gradient Descent optimizer. The best results for recall (84.67%), specificity (84.67%), and ROC-AUC (91.6%) were achieved by Root Mean Squared Propagation. This study compared different computational methods of machine and deep learning whose objective was to classify bed regulation data for patients with COVID-19 from the RegulaRN Platform. The results have made it possible to identify the best model to help health professionals during the process of regulating beds for patients with COVID-19. The scientific findings of this article demonstrate that the computational methods used applied through a digital health solution, can assist in the decision-making of medical regulators and government institutions in situations of public health crisis.
RESUMO
Introdução: A colonoscopia é considerada o exame padrão ouro para diagnóstico do câncer de intestino. Porém o sucesso do exame depende do preparo colônico eficaz. Objetivo: Avaliar a eficácia do picossulfato de sódio (PS) comparativamente ao manitol (MN) no preparo intestinal precedente ao exame de colonoscopia. Material e Métodos: Revisão sistemática de ensaios clínicos randomizados controlados (ECRs). A busca por evidências na literatura científica foi conduzida nas bases de dados PubMed, Embase, Cochrane Library e Biblioteca Virtual da Saúde por meio da combinação dos seguintes indexadores e operadores booleanos: "colonoscopy" AND "picosulfate sodium" AND "mannitol". O risco de viés foi avaliado pela ferramenta RoB 2.0. Resultados: O efeito do PS sobre a limpeza colônica foi similar ou até mesmo inferior àquele demonstrado pelo MN. Entretanto, observou-se maior tolerabilidade e palatabilidade e menor frequência de efeitos colaterais associados ao PS em comparação ao MN. Ressalta-se a carência de rigor metodológico dos estudos incluídos, visto que 33% destes foram classificados com "alto risco" de viés, enquanto 66,7% apresentaram "alguma preocupação". Conclusão: Em comparação ao MN, o uso de PS não promove uma maior qualidade de limpeza colônica, embora esteja relacionado à menor ocorrência de efeitos colaterais, maior tolerabilidade e palatabilidade. Assim, sugere-se que a inclusão do PS seja considerada apenas em pacientes com intolerância importante ou surgimento de efeitos adversos que inviabilizem o preparo com MN.
Introduction: Colonoscopy is considered the gold standard test for diagnosing bowel cancer. The success of the exam, however, depends on effective colonic preparation. Objective: To evaluate the effectiveness of Sodium Picosulfate (PS) compared to Mannitol (MN) in intestinal preparation before colonoscopy examination. Material and Methods: Systematic review of randomized controlled clinical trials (RCTs). The search for evidence in the scientific literature was conducted in the PubMed, Embase, Cochrane Library and Virtual Health Library databases by combining the following indexers and Boolean operators: "colonoscopy" AND "picosulfate sodium" AND "Mannitol". The risk of bias was assessed using the RoB 2.0 tool. Results: The effect of PS on colonic cleansing was similar or even lower than that demonstrated by MN. However, greater tolerability and palatability and a lower frequency of side effects associated with PS were observed compared to MN. The lack of methodological rigor of the included studies is highlighted, as 33% of these were classified as "high risk" of bias, while 66.7% presented "some concern". Conclusion: Compared to MN, the use of PS does not promote a higher quality of colon cleansing, although it is related to the lower occurrence of side effects, greater tolerability and palatability. Therefore, it is suggested that the inclusion of PS must be considered only in patients with significant intolerance or the emergence of adverse effects that make preparation with MN unfeasible.