An investigation of the association between obesity, acanthosis nigricans, and fasting serum insulin level in 6--9 year old children living on the El Paso-Juarez U.S.-Mexico border

The objectives of this study were to investigate the relationship between fasting serum insulin levels and Acanthosis Nigricans (AN) (a dermatological condition characterized by hyperpigmentation and thickening of the skin in specific body areas such as the neck and knuckles) and obesity among 6 to 9 year old children. Children were selected at random from a pediatric clinic located on the U.S.-Mexico border. Because none of the children participants had a weight for height at or above the 97th percentile of the CDC growth charts, obesity was defined as weight for height at or above the 95th percentile and at risk of overweight between the 85 th and 95th percentiles of the CDC growth charts. Anthropometrics, blood samples for fasting serum insulin and blood glucose, and a picture of the neck were obtained at baseline (n = 85) and 6 months later (n = 49). None of the children partipating had high fasting serum insulin levels and only 2 children had AN degree 2 (moderately severe). At baseline children with a weight for height at or above the 95th, percentile had 15 units less of insulin than children who weighed less. However, 6 months later this was not confirmed, thus the baseline result is considered to be an anomaly. Eventhough statistical significance was not reached, results showed that children without AN had 5 percentiles lower weight for height than children with AN. The most important recommendation from this study is the need to monitor longitudinal growth in children to characterize the individual child's growth pattern. AN seems to be related to longitudinal growth changes. ^

Comparison of machine learning approaches and statistical methods for estimation of airborne chemical exposures

Accurate quantitative estimation of exposure using retrospective data has been one of the most challenging tasks in the exposure assessment field. To improve these estimates, some models have been developed using published exposure databases with their corresponding exposure determinants. These models are designed to be applied to reported exposure determinants obtained from study subjects or exposure levels assigned by an industrial hygienist, so quantitative exposure estimates can be obtained. ^ In an effort to improve the prediction accuracy and generalizability of these models, and taking into account that the limitations encountered in previous studies might be due to limitations in the applicability of traditional statistical methods and concepts, the use of computer science- derived data analysis methods, predominantly machine learning approaches, were proposed and explored in this study. ^ The goal of this study was to develop a set of models using decision trees/ensemble and neural networks methods to predict occupational outcomes based on literature-derived databases, and compare, using cross-validation and data splitting techniques, the resulting prediction capacity to that of traditional regression models. Two cases were addressed: the categorical case, where the exposure level was measured as an exposure rating following the American Industrial Hygiene Association guidelines and the continuous case, where the result of the exposure is expressed as a concentration value. Previously developed literature-based exposure databases for 1,1,1 trichloroethane, methylene dichloride and, trichloroethylene were used. ^ When compared to regression estimations, results showed better accuracy of decision trees/ensemble techniques for the categorical case while neural networks were better for estimation of continuous exposure values. Overrepresentation of classes and overfitting were the main causes for poor neural network performance and accuracy. Estimations based on literature-based databases using machine learning techniques might provide an advantage when they are applied to other methodologies that combine `expert inputs' with current exposure measurements, like the Bayesian Decision Analysis tool. The use of machine learning techniques to more accurately estimate exposures from literature-based exposure databases might represent the starting point for the independence from the expert judgment.^