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.^

A movement from traditional malarial chemoprophylaxis to the use of intermittent preventive treatment as a method of protection for children diagnosed with sickle-cell disease: A proposal for consideration based on a systematic review of the literature

Approximately 200,000 African children are born with sickle-cell anemia each year. Research has shown that individuals with hemoglobin disorders, particularly sickle-cell anemia, have increased susceptibility to contracting malaria. Currently it is recommended that patients diagnosed with sickle-cell anemia undergo malaria chemoprophylaxis in order to decrease their chances of malarial infection. However, studies have shown that routine administration of these drugs increases the risk of drug resistance and could possibly impair the development of naturally acquired immunity. Clinical trials have shown intermittent preventive treatment (IPT) to be an effective method of protection against malaria. The objective of this report was to review previously conducted clinical trials that study the effects of intermittent preventive treatment on malaria and anemia in infants and children. Based on the review, implications for its appropriateness as a protective measure against malaria for infants and children diagnosed with sickle-cell disease were provided.^ The 18 studies reviewed were randomized controlled trials that focused on IPT’s effect on malaria (7 studies), anemia (1 study), or both (8 studies). In addition to these 16, one study looks at IPT’s effect on molecular resistance to malaria, and another study is a follow-up to a study in order to review IPT’s potential to cause a rebound effect. The 18 th study in this review specifically looks at IPT’s protective efficacy in children with SCA. The studies in this report were restricted to randomized controlled trials that have been performed from 2000 to 2010. Reports on anemia were included to illustrate possible added benefits of the use of IPT specific to burdens associated with SCA other than malaria susceptibility. The outcomes of these studies address several issues of concern involving the administration of IPT: protective efficacy (in reference to age, seasonal versus perennial malaria regions, and overall effectiveness against malaria and anemia), drug resistance, drug rebound effect, drug side-effects, and long-term effects. Overall, these showed that IPT has a significant level of protective efficacy against malaria and/or anemia in children. More specifically, the IPT study evaluating children diagnosed with sickle-cell anemia proved IPT to be a more effective method of protection than traditional chemoprophylaxis. ^

Systematic literature review on internet-based interventions to prevent HIV transmission

Objective. To perform a systematic review of the internet based HIV prevention interventions.^ Data Source. Data resources including Ovid Medline, CINAHL (EBSCOhost and Psycinfo) were searched for the relevant articles. Study Selection: Studies were selected if the entire article was in English, Randomized control trial performed after 1998 till current, internet based aimed towards HIV/AIDS prevention. ^ Data Extraction. Each relevant article was coded using a code sheet which consisted of background information, study characteristics, study population information, program details, intervention and results. Data Synthesis: Total of seven relevant articles were coded and the information obtained was incorporated into the evidence tables for comparison.^ Conclusion. Overall the internet based HIV prevention studies have been very successful in recruiting large number of people but has not been able to show effective results due to high attrition. More research needs to be done in the area.^

Literature review of estimation of prevalence rate of HIV/AIDS in India using population survey and sentinel surveillance based data

HIV/AIDS is a treatable although incurable disease that presents immense challenges to those infected including physical, social and psychological effects. As of 2009, an estimated 2.4 million people were living with HIV or AIDS in India, 0.3% of the country's population. In India, it is difficult to not only treat but also to track because it is associated with socio-economic factors such as illiteracy, social biases, poor sanitation, malnutrition and social class. Nevertheless, it is important to know the prevalence of HIV/AIDS for several reasons. At the individual level, the quality of life of people living with HIV/AIDS is markedly lower than their counterparts without the disease and is associated with challenges. At the community level, it is important to identify high risk groups, monitor prevention efforts, and allocate appropriate resources to target programs for the reduction of transmission of HIV. ^