RESUMO
This study aimed to determine the feasibility of applying machine-learning methods to assess the progression of chronic kidney disease (CKD) in patients with coronavirus disease (COVID-19) and acute renal injury (AKI). The study was conducted on patients aged 18 years or older who were diagnosed with COVID-19 and AKI between April 2020 and March 2021, and admitted to a second-level hospital in Mérida, Yucatán, México. Of the admitted patients, 47.92% died and 52.06% were discharged. Among the discharged patients, 176 developed AKI during hospitalization, and 131 agreed to participate in the study. The study's results indicated that the area under the receiver operating characteristic curve (AUC-ROC) for the four models was 0.826 for the support vector machine (SVM), 0.828 for the random forest, 0.840 for the logistic regression, and 0.841 for the boosting model. Variable selection methods were utilized to enhance the performance of the classifier, with the SVM model demonstrating the best overall performance, achieving a classification rate of 99.8% ± 0.1 in the training set and 98.43% ± 1.79 in the validation set in AUC-ROC values. These findings have the potential to aid in the early detection and management of CKD, a complication of AKI resulting from COVID-19. Further research is required to confirm these results.
RESUMO
A identificação de pacientes portadores de doença renal crônica (DRC) ou em risco para o seu desenvolvimento pode ser feita por meio de testes simplesna rotina clínica. A importância do diagnóstico precoce da DRC está na possibilidade de instituição de intervenções clínicas que contribuem para o retardo da progressão da doença, postergando o início da terapia renal substitutiva e, portanto, trazem ganhos para a qualidade de vida do paciente, contribuindo com redução de custos do sistema público de saúde. No entanto, uma parcela importante dos pacientes é encaminhada tardiamente ao nefrologista. Mesmo com o encaminhamento tardio, o tratamento da doença permite o controle da condição clínica do paciente. As diversas complicações que ocorremao longo da evolução da DRC chamam atenção para a importância do tratamento especializado e multifacetado, realizado por equipe interdisciplinar. A baixa adesão dos pacientes ao tratamento de doenças crônicas reforça a importância desse tipo de abordagem. Neste sentido, o presente trabalho tem como objetivos apresentar estratégias que possam envolver mais os pacientes no seu auto-cuidado, aumentar a adesão ao tratamento e otimizar o trabalhoda equipe interdisciplinar.
Simple and cost-effective laboratorial parameters can be used by the clinical practitioner for screening and diagnosing chronic kidney disease (CKD). The importance of diagnosing CKD, still in early stages, lies in the possibility of delaying progression of the disease, postponing the beginning of renal replacement therapy, and therefore, improving the patients quality of life and lowering costs of the public health care system. In addition, early detection of CKD allows for better control of the disturbances commonly developed as renal function decreases. However, an important proportion of patients are referred to the nephrologists only when the kidney function is markedly decreased. Even considering this late referral, treatment before the beginning of renal replacement therapy allows for better control of the patients overall clinical state. Such treatment can achieve better results when a multidisciplinary team is present. This is particularly important when considering multiple aspects of CKD and the low adherence of the patients to the treatment of chronic diseases in general. Accordingly, this study proposes a series of strategies to enhance the patients adherence to the treatment and, ultimately, improve the results and patient outcome.