RESUMO
OBJECTIVE: To develop a scoring system to predict acute kidney injury in Asian patients after coronary artery bypass grafting. DESIGN: A retrospective analysis of data collected in an institutional cardiac database. SETTING: A tertiary academic hospital in a large metropolitan city. PARTICIPANTS: The study comprised 954 patients with coronary artery disease. INTERVENTIONS: All patients underwent coronary artery bypass surgery with cardiopulmonary bypass but did not undergo any other concomitant procedures. MEASUREMENTS AND MAIN RESULTS: The main outcome measured was acute kidney injury as defined by the Acute Kidney Injury Network criteria. The following 6 clinical variables were independent predictors of kidney injury: age>60 years, diabetes requiring insulin, estimated glomerular filtration rate<60 mL/min/1.73 m(2), ejection fraction<40%, cardiopulmonary bypass time>140 minutes, and aortic cross-clamp time>100 minutes. These variables were used to develop the Singapore Acute Kidney Injury score. CONCLUSION: The Singapore Acute Kidney Injury score is a simple way to predict, at the time of admission to the intensive care unit, an Asian patient's risk of developing acute kidney injury after coronary artery bypass surgery.
Assuntos
Injúria Renal Aguda/complicações , Injúria Renal Aguda/diagnóstico , Ponte de Artéria Coronária , Complicações Pós-Operatórias/diagnóstico , Injúria Renal Aguda/fisiopatologia , Fatores Etários , Povo Asiático , Bases de Dados Factuais , Complicações do Diabetes/fisiopatologia , Feminino , Taxa de Filtração Glomerular/fisiologia , Humanos , Masculino , Pessoa de Meia-Idade , Complicações Pós-Operatórias/fisiopatologia , Estudos Prospectivos , Estudos Retrospectivos , Fatores de Risco , Singapura , Fatores de TempoRESUMO
Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and the fourth most common cause of cancer-related death worldwide. Understanding the underlying gene mutations in HCC provides great prognostic value for treatment planning and targeted therapy. Radiogenomics has revealed an association between non-invasive imaging features and molecular genomics. However, imaging feature identification is laborious and error-prone. In this paper, we propose an end-to-end deep learning framework for mutation prediction in APOB, COL11A1 and ATRX genes using multiphasic CT scans. Considering intra-tumour heterogeneity (ITH) in HCC, multi-region sampling technology is implemented to generate the dataset for experiments. Experimental results demonstrate the effectiveness of the proposed model.