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.^

Identification and characterization of distinct classes of cAMP-pulse-induced genes in Dictyostelium discoideum development

The unicellular amoeba Dictyostelium discoideum embarks on a developmental program upon starvation. During development, extracellular oscillatory cAMP signaling orchestrates the chemotaxis-mediated aggregation of ∼105 amoebae and is required for optimal induction of so-called pulse-induced genes. This requirement for pulsatile CAMP reflects adaptation of the cAMP-receptor-mediated pathways that regulate these genes. Through examination of a collection of pulse-induced genes, we defined two distinct gene classes based on their induction kinetics and the impact of mutations that impair PKA signaling. The first class (represented by D2 and prtA) is highly dependent on PKA signaling, whereas the second class (represented by carA, gpaB, and acaA) is not. Analysis of expression kinetics revealed that these classes are sequentially expressed with the PKA-independent genes peaking in expression before the PKA-dependent class. Experiments with cycloheximide, an inhibitor of translation, demonstrated that the pulse induction of both classes depends on new protein synthesis early in development. carA and gpaB also exhibit pulse-independent, starvation-induced expression which, unlike their pulse induction, was found to be insensitive to cycloheximide added at the outset of starvation. This result indicates that the mechanism of starvation induction pre-exists in growing cells and is distinct from the pulse induction mechanism for these genes. In order to identify cis-acting elements that are critical for induction of carA, we constructed a GFP reporter controlled by a 914-base-pair portion of its promoter and verified that its expression was PKA-independent, pulse-inducible, and developmentally regulated like the endogenous carA gene. By a combination of truncation, internal deletion, and site-directed mutation, we defined several distinct functional elements within the carA promoter, including a 39-bp region required for pulse induction between base pairs -321 and -282 (relative to the transcription start site), a 131-bp region proximal to the start site that is sufficient for starvation induction, and two separate enhancer domains. Identification of factors that interact with these promoter elements and genetic approaches exploiting the GFP reporter described here should help complete our understanding of the mechanisms regulating these genes, including adaptation mechanisms that likely also govern chemotaxis of Dictyostelium and mammalian cells. ^

Mistreatment and self-neglect in community dwelling older adults: Studies of construct validity, measurement invariance and latent classes

Mistreatment and self-neglect significantly increase the risk of dying in older adults. It is estimated that 1 to 2 million older adults experience elder mistreatment and self-neglect every year in the United States. Currently, there are no elder mistreatment and self-neglect assessment tools with construct validity and measurement invariance testing and no studies have sought to identify underlying latent classes of elder self-neglect that may have differential mortality rates. Using data from 11,280 adults with Texas APS substantiated elder mistreatment and self-neglect 3 studies were conducted to: (1) test the construct validity and (2) the measurement invariance across gender and ethnicity of the Texas Adult Protective Services (APS) Client Assessment and Risk Evaluation (CARE) tool and (3) identify latent classes associated with elder self-neglect. Study 1 confirmed the construct validity of the CARE tool following adjustments to the initial hypothesized CARE tool. This resulted in the deletion of 14 assessment items and a final assessment with 5 original factors and 43 items. Cross-validation for this model was achieved. Study 2 provided empirical evidence for factor loading and item-threshold invariance of the CARE tool across gender and between African-Americans and Caucasians. The financial status domain of the CARE tool did not function properly for Hispanics and thus, had to be deleted. Subsequent analyses showed factor loading and item-threshold invariance across all 3 ethnic groups with the exception of some residual errors. Study 3 identified 4-latent classes associated with elder self-neglect behaviors which included individuals with evidence of problems in the areas of (1) their environment, (2) physical and medical status, (3) multiple domains and (4) finances. Overall, these studies provide evidence supporting the use of APS CARE tool for providing unbiased and valid investigations of mistreatment and neglect in older adults with different demographic characteristics. Furthermore, the findings support the underlying notion that elder self-neglect may not only occur along a continuum, but that differential types may exist. All of which, have very important potential implications for social and health services distributed to vulnerable mistreated and neglected older adults.^