RESUMEN
INTRODUCTION: Chronic kidney disease (CKD) and metabolic syndrome (MS) are recognized as public health problems which are related to overweight and cardiometabolic factors. The aim of this study was to develop a model to predict MS in people with CKD. METHODS: This was a prospective cross-sectional study of patients from a reference center in São Luís, MA, Brazil. The sample included adult volunteers classified according to the presence of mild or severe CKD. For MS tracking, the k-nearest neighbors (KNN) classifier algorithm was used with the following inputs: gender, smoking, neck circumference, and waist-to-hip ratio. Results were considered significant at p < 0.05. RESULTS: A total of 196 adult patients were evaluated with a mean age of 44.73 years, 71.9% female, 69.4% overweight, and 12.24% with CKD. Of the latter, 45.8% had MS, the majority had up to 3 altered metabolic components, and the group with CKD showed statistical significance in: waist circumference, systolic blood pressure, diastolic blood pressure, and fasting blood glucose. The KNN algorithm proved to be a good predictor for MS screening with 79% accuracy and sensitivity and 80% specificity (area under the ROC curve - AUC = 0.79). CONCLUSION: The KNN algorithm can be used as a low-cost screening method to evaluate the presence of MS in people with CKD.
Asunto(s)
Aprendizaje Automático , Síndrome Metabólico , Insuficiencia Renal Crónica , Humanos , Síndrome Metabólico/diagnóstico , Síndrome Metabólico/complicaciones , Síndrome Metabólico/epidemiología , Femenino , Masculino , Estudios Transversales , Insuficiencia Renal Crónica/complicaciones , Adulto , Persona de Mediana Edad , Estudios Prospectivos , Factores de Riesgo , Algoritmos , Brasil/epidemiologíaRESUMEN
BACKGROUND: Excess body fat has been growing alarmingly among adolescents, especially in low income and middle income countries where access to health services is scarce. Currently, the main method for assessing overweight in adolescents is the body mass index, but its use is criticized for its low sensitivity and high specificity, which may lead to a late diagnosis of comorbidities associated with excess body fat, such as cardiovascular diseases. Thus, the aim of this study was to develop a computational model using linear regression to predict obesity in adolescents and compare it with commonly used anthropometric methods. To improve the performance of our model, we estimated the percentage of fat and then classified the nutritional status of these adolescents. METHODS: The model was developed using easily measurable socio-demographic and clinical variables from a database of 772 adolescents of both genders, aged 10-19 years. The predictive performance was evaluated by the following metrics: accuracy, sensitivity, specificity, and area under ROC curve. The performance of the method was compared to the anthropometric parameters: body mass index and waist-to-height ratio. RESULTS: Our model showed a high correlation (R = 0.80) with the body fat percentage value obtained through bioimpedance. In addition, regarding discrimination, our model obtained better results compared to BMI and WHtR: AUROC = 0.80, 0.64, and 0.55, respectively. It also presented a high sensitivity of 92% and low false negative rate (6%), while BMI and WHtR showed low sensitivity (27% and 9.9%) and a high false negative rate (65% and 53%), respectively. CONCLUSIONS: The computational model of this study obtained a better performance in the evaluation of excess body fat in adolescents, compared to the usual anthropometric indicators presenting itself as a low cost alternative for screening obesity in adolescents living in Brazilian regions where financial resources are scarce.
Asunto(s)
Tejido Adiposo , Modelos Teóricos , Sobrepeso/diagnóstico , Adolescente , Adulto , Índice de Masa Corporal , Brasil , Niño , Costos y Análisis de Costo , Femenino , Humanos , Modelos Lineales , Masculino , Tamizaje Masivo/economía , Estado Nutricional , Curva ROC , Reproducibilidad de los Resultados , Relación Cintura-Estatura , Adulto JovenRESUMEN
Hypsarrhythmia is an electroencephalographic pattern specific to some epileptic syndromes that affect children under one year of age. The identification of this pattern, in some cases, causes disagreements between experts, which is worrisome since an inaccurate diagnosis can bring complications to the infant. Despite the difficulties in visually identifying hypsarrhythmia, options of computerized assistance are scarce. Aiming to collaborate with the recognition of this electropathological pattern, we propose in this paper a mathematical index that can help electroencephalography experts to identify hypsarrhythmia. We performed hypothesis tests that indicated significant differences in the groups under analysis, where the p-values were found to be extremely small.