Fusing data mining, machine learning and traditional statistics to detect biomarkers associated with depression

BACKGROUND: Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study.

METHODS: The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009-2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators.

RESULTS: After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (p<0.001).

CONCLUSION: The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling methodology and was demonstrated to be a useful tool for detecting three biomarkers associated with depression for future hypothesis generation: red cell distribution width, serum glucose and total bilirubin.

Poverty, hunger and food security in Central America and Panama

Includes bibliography

Vilas rurais no processo de transformação do espaço rural no município de Paranavaí

Pós-graduação em Geografia - FCT

A reprodução sócio-econômica e produtiva do campesinato no Sudeste paraense: o Assentamento Palmares II, Parauapebas/PA

O Sudeste Paraense foi palco de um dos maiores e mais incisivos processos de ocupação e colonização da região amazônica em sua totalidade. O elevado contingente migrante camponês ao longo de todo século XX, em especial, nas décadas dos anos de 1970, 1980 e 1990, concorreu diretamente com outras estratégias postas e pensadas para a colonização da região, como a agropecuária de grande porte e extensiva, mineração e projetos de geração de energia. Diante de uma complexidade ímpar no agrário regional, esse cenário é marcado até a atualidade por elevada conflitividade, posicionando claramente a região no debate acadêmico como sendo uma fronteira. A partir de meados dos anos 1990, os conflitos e disputas ganham novos contornos com a criação de Projetos de Assentamentos e a implementação de uma série de políticas voltadas ao atendimento da agricultura familiar, o que possibilita de certa forma pensar em novos tipos de conflitos e possibilidades de reprodução social e econômica dos camponeses assentados. O presente trabalho, dentro desse novo contexto, trata especificamente das possibilidades atuais de reprodução social e econômica do campesinato no assentamento Palmares II, município de Parauapebas/PA, buscando compreender os possíveis fatores que vem permitindo ou não a ruptura com a tese do ciclo e fronteira e em contraposição permitindo certa estabilização aos camponeses assentados. Para além de evidenciar e comprovar a existência de novas trajetórias dos sistemas de produção postas em prática pelos agricultores do assentamento em questão, o trabalho pretende indicar quais fatores econômicos, políticos, sociais têm sido importantes para a continuidade e possibilidade das estratégias de reprodução camponesa.

Educação e trabalho em movimentos sociais: princípios educativos transcendentes e comuns ao Movimento dos Trabalhadores Rurais Sem Terra (MST), aos socialistas utópicos owenistas e aos cartistas britânicos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Efficiency and soil contamination during underground application of insecticides: control of leaf-cutting ants with thermal foggers

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A precarização do trabalho: migrantes nordestinos no município de Leme-SP : caminhos, estradas e sonhos

This paper aims to examine the genesis of migration to the city of Leme-SP, as well as the influence of the social matrix northeastern expansion and redevelopment through the territorialization of the migrant population, particularly workers from the state of Ceará, migration from the 1970s. This process is evidenced by the territorial division of labor, through the economic, political and cultural insecurity through the work of cutting sugar cane, the territoriality of culture and northeastern faith in the city, and becomes another object before the materiality in which occurs. In this aspect, through dialogue between the sciences and arts, it was possible to show the historical importance of the phenomenon of migration in the country, in different scales and relationship that encompasses everything and everyone

"Dar voce a una voce": diversità e rappresentazione nella letteratura young adult. Proposta di traduzione di Gabi, a Girl in Pieces di Isabel Quintero.

In this dissertation, I will present my translation into Italian of several excerpts from Gabi, A Girl in Pieces, a young adult (YA) novel by Mexican-American author Isabel Quintero, along with examining the issues of diversity and representation in YA literature. This study aims to demonstrate the benefits of multicultural literature for young readers and the importance of publishing stories that reflect the diversity of the world we inhabit. The translation of the novel is accompanied by an analysis of its social, cultural, and literary context. The first chapter provides an overview of Chican@ history, literature, and culture, focusing on the concepts of identity and hybridity. The second chapter describes YA literature and its characteristics, outlines its history, and discusses the value of diverse books in the lives of teenage readers. Additionally, it cites relevant studies and statistics proving the dearth of diverse literature for young readers in the United States. The third chapter focuses specifically on the representation of Latin@s and Chican@s in literature for young readers, examining the main stereotypes that have plagued the depiction of this community and the new perspectives offered by Mexican-American YA authors. In the fourth chapter, I introduce Isabel Quintero and her novel Gabi, A Girl in Pieces, analyzing its plot, style, format, and main themes. In the fifth chapter, I provide my translation, which is then analyzed in the sixth and final chapter. The translation commentary details some of the problems I encountered and the strategies I applied. The sixth chapter also includes some observations on the translation of teenage speech, of multilingual texts, and of children’s and YA literature.

Genetics and epidemiology of gallbladder disease in New World native peoples.

Native peoples of the New World, including Amerindians and admixed Latin Americans such as Mexican-Americans, are highly susceptible to diseases of the gallbladder. These include cholesterol cholelithiasis (gallstones) and its complications, as well as cancer of the gallbladder. Although there is clearly some necessary dietary or other environmental risk factor involved, the pattern of disease prevalence is geographically associated with the distribution of genes of aboriginal Amerindian origin, and levels of risk generally correspond to the degree of Amerindian admixture. This pattern differs from that generally associated with Westernization, which suggests a gene-environment interaction, and that within an admixed population there is a subset whose risk is underestimated when admixture is ignored. The risk that an individual of a susceptible New World genotype will undergo a cholecystectomy by age 85 can approach 40% in Mexican-American females, and their risk of gallbladder cancer can reach several percent. These are heretofore unrecognized levels of risk, especially of the latter, because previous studies have not accounted for admixture or for the loss of at-risk individuals due to cholecystectomy. A genetic susceptibility may, thus, be as "carcinogenic" in New World peoples as any known major environmental exposure; yet, while the risk has a genetic basis, its expression as gallbladder cancer is so delayed as to lead only very rarely to multiply-affected families. Estimates in this paper are derived in part from two studies of Mexican-Americans in Starr County and Laredo, Texas.

Physical activity and survival after a first myocardial infarction: The Corpus Christi Heart Project

Previous studies have demonstrated that habitual physical activity is associated with a reduced risk of incident coronary heart disease (CHD). However, the role of physical activity in lowering the risk of all-cause mortality, CHD mortality, reinfarction, or receipt of a revascularization procedure after a first myocardial infarction (MI) remains unresolved, particularly in minority populations. To investigate the associations between physical activity and risk of all-cause mortality, CHD mortality, reinfarction, and receipt of a revascularization procedure, this study was conducted among Mexican-American and non-Hispanic white women and men who survived a first MI. The Corpus Christi Heart Project, a population-based cardiovascular surveillance study, provide data which included vital status, survival time, medical history, CHD risk factor information, including level of physical activity among Mexican-American and non-Hispanic white adults who had experienced a first MI between May, 1988 and April, 1990. MI patients were interviewed at baseline and annually thereafter until their death or through May, 1995. A categorical variable was created to reflect change in level of physical activity following the first MI; categories included (1) sedentary with no change, (2) decreased activity, (3) increased activity, and (4) moderate activity with no change (the referent group). Proportional hazards regression analyses were used to assess the relationship of level of physical activity and risk of death, reinfarction, or receipt of a revascularization procedure adjusting for age, sex, ethnicity, severity of MI, and CHD risk factor status. Over a 7-year follow-up period, the relative risk (95% confidence intervals) of all-cause mortality was 4.67 (2.27, 9.60) for the sedentary-no change group, 2.33 (0.96, 5.67) for the decreased activity group, and 0.52 (0.11, 2.41) for the increased activity group. The relative risk of CHD mortality was 6.92 (2.05, 23.34) for the sedentary-no change group, 2.40 (0.55, 10.51) for the decreased activity group, and 1.58 (0.26, 9.65) for the increased activity group. The relative risk for reinfarction was 2.50 (1.52, 4.10) for the sedentary-no change group, 2.26 (1.24, 4.12) for the decreased activity group, and 0.52 (0.21, 1.32) for the increased activity group. Finally, the relative risk for receipt of a revascularization procedure was 0.65 (0.39, 1.07) for the sedentary-no change group, 0.45 (0.22, 0.92) for the decreased activity group, and 1.01 (0.51, 2.02) for the increased activity group. No interactions were observed for ethnicity or severity of first MI. These results are consistent with the hypothesis that moderate physical activity is independently associated with a lower risk of all-cause mortality, CHD mortality, and reinfarction, but not revascularization, among Mexican-American and non-Hispanic white, female and male, first MI patients. These results also support the current recommendation that physical activity plays an important role in the secondary prevention of CHD. ^

Exploring the role of viral infection in type 2 diabetes

Viral infection is known to play a role in type I diabetes, but there is a paucity of information on the role of viruses in type 2 diabetes. This research examined the seroprevalence of selected viruses in a group of predominantly Mexican-American patients with End Stage Renal Disease (ESRD). Using a case control design, patients with type 2 diabetes were compared with a group of non-diabetic controls. ^ One hundred and thirteen patients, 83 with type 2 diabetes and 30 controls without diabetes, underwent hemodialysis at the same chronic dialysis facility in San Antonio, Texas. AD subjects were tested for IgG, IgM, and neutralizing antibodies against Coxsackie B viruses (CBV), and IgG and IgM antibodies against cytomegalovirus (CMV) and parvovirus B19 (PVB19). Hepatitis B virus antigen (HBVAg), Hepatitis B virus antibody (HBVAb), Hepatitis C virus antibody (HCVAb), and Rubella (IgG) were also measured. A subset of 91 patients, 66 with diabetes and 25 controls, were tested bimonthly for six months. There was a significant difference (P = 0.04) in the seroprevalence of IgG antibodies to CMV between patients with type 2 diabetes (98%) and non-diabetic controls (87%) in the initial sample (OR = 6.2, 95% CI:1.1–36.0). A greater seroprevalence of CMV IgG antibodies was observed over the six month period among patients with type 2 diabetes (M) compared to controls (84%). This difference was also statistically (P < 0.03), with a greater odds ratio (OR = 12.4, 95% CI: 1.3–116.9), but with larger confidence interval related to the small number of subjects. However, when adjusted for age by logistic regression analysis there was no difference between the groups (OR = 1). ^ After one sample, there was a greater seroprevalence of HCVAb in the group without diabetes (28%), compared to those with type 2 diabetes (10%) (P = 0.04). This difference was no longer significant when adjusted for patient age. The prevalence of antibodies to PVB19, HBSAg, HBV, and Rubella was not significantly different in patients with type 2 diabetes and controls. There were significantly more vascular complications (P < 0.02) among patients with diabetes. ^ These results indicate that the significant associations observed in this population between viral infection with CMV, HCV, and type 2 diabetes are confounded by age. Accelerated atherosclerosis has been associated with age, diabetes, as well as CMV. Latent infection may be a factor that links these processes. ^

A STUDY OF THE ATTITUDES OF ELDERLY CONSUMERS TOWARD DENTAL CARE AND ORAL HEALTH

This paper describes a study of the attitudes of elderly consumers toward dental care and oral health. Four hundred and two respondents ages 60-97 were interviewed with a 62 item questionnaire. Attitudes were measured regarding: quality of care, sufficient utilization of care, priority of oral health, patient-provider interaction, individual control over health, powerful others control of health, and chance as the locus of control over health. Analysis of variance was performed on the sample of males and females separately. Fifty-four hypotheses were tested on each sex. Race and self-concept were excellent predictors of attitude for both sexes and SES (socioeconomic status) and self-reported health were good predictors for females. There was no statistically significant relationship between the frequency with which the elderly utilize dental care and their attitudes toward the quality of care they receive. Foremost reason for non-utilization was that of no felt need. Those selecting this reason were likely to be Anglo females, wearers of dentures, in good health. Those selecting cost as the foremost reason for non-utilization were Black, in fair health, of either sex, missing some teeth, but with no dentures. Overall attitudes toward quality of dental care were positive, despite the fact that this group was exposed to dental care in its infancy. This may suggest that the elderly recognize the importance of technological advances in dentistry. Women with low income and education levels were more likely to have positive attitudes about quality of care than other females. Attitudes about interaction between patient and provider were overall negative. The sample scored high on individual control over health, and scored lower, but nonetheless positively, on feelings that persons other than themselves are most essential to maintaining health. Overall these elderly persons did not agree that they relied on chance in matters of health. Those who did choose this locus were female, with lower SES and health status. Though males scored high on internal control of health, those with lowest scores were Mexican-American or had never been married. Sex and ethnicity were the best predictors of attitude across all measures in the study.^

Analysis of recurrent failure times: A time-dependent Yule process approach

Analysis of recurrent events has been widely discussed in medical, health services, insurance, and engineering areas in recent years. This research proposes to use a nonhomogeneous Yule process with the proportional intensity assumption to model the hazard function on recurrent events data and the associated risk factors. This method assumes that repeated events occur for each individual, with given covariates, according to a nonhomogeneous Yule process with intensity function λx(t) = λ 0(t) · exp( x′β). One of the advantages of using a non-homogeneous Yule process for recurrent events is that it assumes that the recurrent rate is proportional to the number of events that occur up to time t. Maximum likelihood estimation is used to provide estimates of the parameters in the model, and a generalized scoring iterative procedure is applied in numerical computation. ^ Model comparisons between the proposed method and other existing recurrent models are addressed by simulation. One example concerning recurrent myocardial infarction events compared between two distinct populations, Mexican-American and Non-Hispanic Whites in the Corpus Christi Heart Project is examined. ^

Case-control study of association of maternal recall of diarrhea or use of antimicrobials in the periconceptional period and neural tube defects

In June 1995 a case-control study was initiated by the Texas Department of Health among Mexican American women residing in the fourteen counties of the Texas-Mexico border. Case-women had carried infants with neural tube defect. Control-women had given birth to infants without neural tube defects. The case-control protocol included a general questionnaire which elicited information regarding illnesses experienced and antibiotics taken from three months prior to conception to three months after conception. An assessment of the associations between periconceptional diarrhea and the risk of neural tube defects indicated that the unadjusted association of diarrhea and risk of neural tube defect was significant (OR = 3.3, CI = 1.4–7.6). The unadjusted association of use of oral antimicrobials and risk of neural tube defect was also significant (OR = 3.4, CI = 1.6–7.3). These associations persisted among women who had no fever during the periconceptional period and were present irrespective of folate intake. Diarrhea was associated with an increased risk of NTD independent of use of antimicrobials. The converse was also true; antimicrobials were associated with an increased risk of NTD independent of diarrhea. Further research regarding these potentially modifiable risk factors is warranted. Replication of these findings could result in interventions in addition to folate supplementation. ^