Blended Ensemble Learning Prediction Model for Strengthening Diagnosis and Treatment of Chronic Diabetes Disease.

Diabetes mellitus (DM), commonly known as diabetes, is a collection of metabolic illnesses characterized by persistently high blood sugar levels. The signs of elevated blood sugar include increased hunger, frequent urination, and increased thirst. If DM is not treated properly, it may lead to several complications. Diabetes is caused by either insufficient insulin production by the pancreas or an insufficient insulin response by the body's cells. Every year, 1.6 million individuals die from this disease. The objective of this research work is to use relevant features to construct a blended ensemble learning (EL)-based forecasting system and find the optimal classifier for comparing clinical outputs. The EL based on Bayesian networks and radial basis functions has been proposed in this article. The performances of five machine learning (ML) techniques, namely, logistic regression (LR), decision tree (DT) classifier, support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF), are compared with the proposed EL technique. Experiments reveal that the EL method performs better than the existing ML approaches in predicting diabetic illness, with the remarkable accuracy of 97.11%. The proposed ensemble learning could be useful in assisting specialists in accurately diagnosing diabetes and assisting patients in receiving the appropriate therapy.

Clinico-biochemical profile of sick children with severe acute malnutrition.

OBJECTIVE: Severe acute malnutrition (SAM) classified as edematous and marasmus, however, Kwashiorker represents the most severe phenotype of edematous malnutrition. The aim of this study was to describe the clinico-biochemical profile in sick children with severe acute malnutrition. MATERIALS AND METHODS: This is a descriptive cross-sectional study, which included children aged 6 to 60 months, fulfilling the World Health Organization (WHO) criteria of severe acute malnutrition. We collected data on demography, anthropometry, history, and clinical examination. Investigations included arterial blood gas analysis, serum electrolytes, calcium, serum albumin, and blood sugar. P value < 0.05 was considered significant. RESULTS: One hundred twenty-two children with SAM were recruited, out of which 65 (53.27%) had edematous malnutrition and 57 (46.7%) had nonedematous malnutrition. Out of total children, 90 (73.77%) were discharged from hospital, 18 (14.7%) died, and 14 (11.4%) were left against medical advice. Out of 122 children with SAM, edematous children were younger (25.7 vs. 34.5 months, P = 0.002). Children with edematous malnutrition were more likely to have pneumonia (P = 0.04), acute gastroenteritis (P < 0.001), hyponatremia (P = 0.04), metabolic acidosis (P = 0.005), and hypocalcemia (P = 0.006) when compared with nonedematous children. Edematous malnutrition has 1.3 and 1.4 times more risk of death and leave against medical advice (LAMA) respectively as compared to nonedematous malnutrition. Mortality was higher in edematous malnutrition (12, 66.6%) than nonedematous malnutrition (6, 33.3%). CONCLUSION: Edematous malnutrition was commonly prevalent in 1 to 3 years of children and clinical and biochemical abnormalities frequently co-exist with edematous malnutrition.

B-type Natriuretic peptide Levels and Outcome in Children With Severe Acute Malnutrition With Co-morbidity.

We studied the ability of B-type natriuretic peptide (BNP) in predicting mortality among 86 in-patients with severe acute malnutrition presenting with co-morbidity, and found that cut-off level of BNP ≥201 pg/mL in Receiver operating characteristics curve [AU-ROC 0.96 (95% CI 0.92,1.003, P<0.0001)] had high discriminative ability to distinguish between survivors and non-survivors.

Cardiac changes in children hospitalized with severe acute malnutrition: A prospective study at tertiary care center of northern India.

Severe acute malnutrition (SAM) may affect cardiac structure and function. Cardiac changes in sick children with SAM have received little attention in the literature. Children aged 6-60 months with SAM were cases, and age and sex matched children were controls. Cardiac biomarker levels were measured by the quantitative the Enzyme- linked immunosorbent assay (ELISA) method, and echocardiography was used to assess cardiac changes in all children. The study included 76 children in each group. Children with SAM had less left ventricular mass and increased myocardial performance index as compared with controls (p < 0.0001). Cardiac biomarker levels were increased in children with SAM (p < 0.0001). Cardiac changes and biomarker levels were comparable in children with edema and children without edema except creatine kinase-MB (p = 0.01).