Mathematical and empirical examinations of some epidemiological procedures

In epidemiology literature, it is often required to investigate the relationships between means where the levels of experiment are actually monotone sets forming a partition on the range of sampling values. With this need, the analysis of these group means is generally performed using classical analysis of variance (ANOVA). However, this method has never been challenged. In this dissertation, we will formulate and present our examination of its validity. First, the classical assumptions of normality and constant variance are not always true. Second, under the null hypothesis of equal means, the test statistic for the classical ANOVA technique is still valid. Third, when the hypothesis of equal means is rejected, the classical analysis techniques for hypotheses of contrasts are not valid. Fourth, under the alternative hypothesis, we can show that the monotone property of levels leads to the conclusion that the means are monotone. Fifth, we propose an appropriate method for handing the data in this situation. ^

Determining appropriate measurement methods for etiological research of computing-related musculoskeletal symptoms and disorders

Two studies among college students were conducted to evaluate appropriate measurement methods for etiological research on computing-related upper extremity musculoskeletal disorders (UEMSDs). ^ A cross-sectional study among 100 graduate students evaluated the utility of symptoms surveys (a VAS scale and 5-point Likert scale) compared with two UEMSD clinical classification systems (Gerr and Moore protocols). The two symptom measures were highly concordant (Lin's rho = 0.54; Spearman's r = 0.72); the two clinical protocols were moderately concordant (Cohen's kappa = 0.50). Sensitivity and specificity, endorsed by Youden's J statistic, did not reveal much agreement between the symptoms surveys and clinical examinations. It cannot be concluded self-report symptoms surveys can be used as surrogate for clinical examinations. ^ A pilot repeated measures study conducted among 30 undergraduate students evaluated computing exposure measurement methods. Key findings are: temporal variations in symptoms, the odds of experiencing symptoms increased with every hour of computer use (adjOR = 1.1, p < .10) and every stretch break taken (adjOR = 1.3, p < .10). When measuring posture using the Computer Use Checklist, a positive association with symptoms was observed (adjOR = 1.3, p < 0.10), while measuring posture using a modified Rapid Upper Limb Assessment produced unexpected and inconsistent associations. The findings were inconclusive in identifying an appropriate posture assessment or superior conceptualization of computer use exposure. ^ A cross-sectional study of 166 graduate students evaluated the comparability of graduate students to College Computing & Health surveys administered to undergraduate students. Fifty-five percent reported computing-related pain and functional limitations. Years of computer use in graduate school and number of years in school where weekly computer use was ≥ 10 hours were associated with pain within an hour of computing in logistic regression analyses. The findings are consistent with current literature on both undergraduate and graduate students. ^

Genome-wide gene-gene interaction analysis for cardiovascular disease

Numerous studies have been carried out to try to better understand the genetic predisposition for cardiovascular disease. Although it is widely believed that multifactorial diseases such as cardiovascular disease is the result from effects of many genes which working alone or interact with other genes, most genetic studies have been focused on identifying of cardiovascular disease susceptibility genes and usually ignore the effects of gene-gene interactions in the analysis. The current study applies a novel linkage disequilibrium based statistic for testing interactions between two linked loci using data from a genome-wide study of cardiovascular disease. A total of 53,394 single nucleotide polymorphisms (SNPs) are tested for pair-wise interactions, and 8,644 interactions are found to be significant with p-values less than 3.5×10-11. Results indicate that known cardiovascular disease susceptibility genes tend not to have many significantly interactions. One SNP in the CACNG1 (calcium channel, voltage-dependent, gamma subunit 1) gene and one SNP in the IL3RA (interleukin 3 receptor, alpha) gene are found to have the most significant pair-wise interactions. Findings from the current study should be replicated in other independent cohort to eliminate potential false positive results.^

Validating the dietary intake questions from the Tu Salud, ¡Si Cuenta! questionnaire

Background. Poor nutrition is an important factor in the onset of obesity which is a growing problem in the United States that disproportionately affects Mexican-Americans. In order to form recommendations and effectively target nutrition in interventions it is necessary to have valid epidemiological tools to better understand dietary trends. Purpose. The purpose of this study is to evaluate the validity of the nutritional intake questions from the Tu Salud, ¡Sí Cuenta! Questionnaire in an adult Mexican-American population. Methods. Fifty participants in the Cameron County Hispanic Cohort were recruited into the validity study, which consisted of completing the Tu Salud, ¡Sí Cuenta! questionnaire and the 24-hour recall with a 2 hour time period between administrations. Responses were analyzed to determine the percent agreement, kappa statistic and Spearman rank order correlation. Results: Five items had good validity (>0.6), three items had fair validity (>0.4), and three items had poor validity (<0.4). In general, items that had low validity were those that were reported in low frequencies by study subjects. Overall, the Tu Salud, ¡Sí Cuenta! questionnaire showed good validity, making this questionnaire a valuable tool to assess the dietary intake patterns of this Mexican-American adult population. ^

Systematic review of genetic risk score in coronary heart disease and other diseases

In order to better take advantage of the abundant results from large-scale genomic association studies, investigators are turning to a genetic risk score (GRS) method in order to combine the information from common modest-effect risk alleles into an efficient risk assessment statistic. The statistical properties of these GRSs are poorly understood. As a first step toward a better understanding of GRSs, a systematic analysis of recent investigations using a GRS was undertaken. GRS studies were searched in the areas of coronary heart disease (CHD), cancer, and other common diseases using bibliographic databases and by hand-searching reference lists and journals. Twenty-one independent case-control studies, cohort studies, and simulation studies (12 in CHD, 9 in other diseases) were identified. The underlying statistical assumptions of the GRS using the experience of the Framingham risk score were investigated. Improvements in the construction of a GRS guided by the concept of composite indicators are discussed. The GRS will be a promising risk assessment tool to improve prediction and diagnosis of common diseases.^

A community-based assessment of the spatiotemporal distribution of influenza in a U.S.-Mexico border county during the spring 2009 novel H1N1 swine-origin influenza A pandemic

This study retrospectively evaluated the spatial and temporal disease patterns associated with influenza-like illness (ILI), positive rapid influenza antigen detection tests (RIDT), and confirmed H1N1 S-OIV cases reported to the Cameron County Department of Health and Human Services between April 26 and May 13, 2009 using the space-time permutation scan statistic software SaTScan in conjunction with geographical information system (GIS) software ArcGIS 9.3. The rate and age-adjusted relative risk of each influenza measure was calculated and a cluster analysis was conducted to determine the geographic regions with statistically higher incidence of disease. A Poisson distribution model was developed to identify the effect that socioeconomic status, population density, and certain population attributes of a census block-group had on that area's frequency of S-OIV confirmed cases over the entire outbreak. Predominant among the spatiotemporal analyses of ILI, RIDT and S-OIV cases in Cameron County is the consistent pattern of a high concentration of cases along the southern border with Mexico. These findings in conjunction with the slight northward space-time shifts of ILI and RIDT cluster centers highlight the southern border as the primary site for public health interventions. Finally, the community-based multiple regression model revealed that three factors—percentage of the population under age 15, average household size, and the number of high school graduates over age 25—were significantly associated with laboratory-confirmed S-OIV in the Lower Rio Grande Valley. Together, these findings underscore the need for community-based surveillance, improve our understanding of the distribution of the burden of influenza within the community, and have implications for vaccination and community outreach initiatives.^

Evaluation of the T-SPOT(RTM).TB test in the diagnosis of latent tuberculosis infection in HIV-infected children in Uganda

Background. About a third of the world’s population is infected with tuberculosis (TB) with sub-Saharan Africa being the worst hit. Uganda is ranked 16th among the countries with the biggest TB burden. The burden in children however has not been determined. The burden of TB has been worsened by the advent of HIV and TB is the leading cause of mortality in HIV infected individuals. Development of TB disease can be prevented if TB is diagnosed during its latent stage and treated with isoniazid. For over a century, latent TB infection (LTBI) was diagnosed using the Tuberculin Skin Test (TST). New interferon gamma release assays (IGRA) have been approved by FDA for the diagnosis of LTBI and adult studies have shown that IGRAs are superior to the TST but there have been few studies in children especially in areas of high TB and HIV endemicity. ^ Objective. The objective of this study was to examine whether the IGRAs had a role in LTBI diagnosis in HIV infected children in Uganda. ^ Methods. Three hundred and eighty one (381) children were recruited at the Baylor College of Medicine-Bristol Meyers Squibb Children’s Clinical Center of Excellence at Mulago Hospital, Kampala, Uganda between March and August 2010. All the children were subjected to a TST and T-SPOT ®.TB test which was the IGRA chosen for this study. Sputum examination and chest x-rays were also done to rule out active TB. ^ Results. There was no statistically significant difference between the tests. The agreement between the two assays was 95.9% and the kappa statistic was 0.7 (95% CI: 0.55–0.85, p-value<0.05) indicating a substantial or good agreement. The TST was associated with older age and higher weight for age z-scores but the T-SPOT®. TB was not. Both tests were associated with history of taking anti-retroviral therapy (ART). ^ Conclusion. Before promoting use of IGRAs in children living in HIV/TB endemic countries, more research needs to be done. ^

Treatment discontinuation among breast, colorectal, and prostate cancer patients in Alabama

Introduction. Cancer registries provide information about treatment initiation but not the full course of treatment. In an effort to identify patient reported reasons for discontinuing cancer treatment, patients with prostate, breast, and colorectal cancer were identified from Alabama State Cancer Registry (ASCR) -Alabama Medicare linked database for interview. This study has two specific aims: (1) determine whether the ASCR-Medicare database accurately reflects patients’ treatment experiences in terms of whether they started and completed treatment when compared to patient self-report and (2) determine which patient demographic and health care system factors are related to treatment completion as defined by patient self-report. ^ Methods. The ASCR-Medicare claims dataset supplemented patient interview responses to identify treatment initiation and completion among prostate, breast, and colorectal cancer patients in Alabama from 1999-2003. Kappa statistic was used to test for concordance of treatment initiation and completion between patient self-report and Medicare claims data. Patients who reported not completing treatment were asked questions to ascertain reasons for treatment discontinuation. Logistic regression models were constructed to explore the association of patient and tumor characteristics with discontinuation of radiation and chemotherapy. ^ Results. Overall, there was a fair agreement across all cancer sites about whether one had surgery (Kappa=.382). There was fair agreement between self-report and Medicare claims data for starting radiation treatment (Kappa=.278). For starting chemotherapy there was moderate agreement (Kappa=.414). There was no agreement for completing treatment for radiation and chemotherapy between the self-report and claims data. Patients most often reported doctor’s recommendation (40% for radiation treatment and 21.4% for chemotherapy) and side effects (30% for radiation treatment and 42.8% for chemotherapy) for discontinuing treatment. Females were less likely to complete radiation than males (OR=.24, 95% CI=.11–.50). Stage I patients were more likely to drop radiation treatment than stage III patients (OR=3.34, 95% CI=1.12–9.95). Younger patients were more likely to discontinue chemotherapy than older patients (OR=2.84 95%, CI=1.08–7.69) and breast cancer patients were less likely to discontinue chemotherapy than colorectal patients (OR=.13, 95% CI=.04–.46). ^ Conclusion. This study reveals that patients recall starting treatment more accurately than completing treatment and that there are several demographic and tumor characteristics that influence treatment discontinuation. Providing patients with treatment summaries and survivorship plans can help patients their follow-up care when there are gaps in treatment recall and discontinuation of treatment.^

Hypogonadism in male cancer patients: A cross-sectional study

Introduction. Cancer is the second most common cause of death in the USA (2). Studies have shown a coexistence of cancer and hypogonadism (9,31,13). The majority of patients with cancer develop cachexia, which cannot be solely explained by anorexia seen in these patients. Testosterone is a male sex hormone which is known to increase muscle mass and strength, maintain cancellous bone mass, and increase cortical bone mass, in addition to improving libido, sexual desire, and fantasy (14). If a high prevalence of hypogonadism is detected in male cancer patients, and a significant difference exists in testosterone levels in cancer patients with cachexia versus those without cachexia, testosterone may be administered in future randomized trials to help alleviate cachexia. Study group and design The study group consisted of male cancer patients and non-cancer controls aged between 40 and 70 years. The primary study design was cross-sectional with a sample size of 135. The present data analysis is done on a subset convenience sample of 72 patients recruited between November 2006 and January 2010. ^ Methods. Patients aged 40-70 years with or without a diagnosis of cancer were recruited into the study. All patients with a BMI over 35, significant edema, non-melanomatous skin cancer, current alcohol or illicit drug abuse, concomitant usage of medications interfering with gonadal axis, and anabolic agents, patients on tube feeds or parenteral nutrition within 3 months prior to enrollment were excluded from the study. The study was approved by the Institutional Review Board of Baylor College of Medicine and is being conducted at the Michael E. DeBakey Veterans Affairs Medical Center at Houston. My thesis is a pilot data analysis that employs a smaller subset convenience sample of 72 patients determined by using the data available for the 72 patients (of the intended sample of 135 patients) recruited between November 2006 and January 2010. The primary aim of this analysis is to compare the proportion of patients with hypogonadism in the male cancer and non-cancer control groups, and to evaluate if a significant difference exists with respect to testosterone levels in male cancer patients with cachexia versus those without cachexia. The procedures of the study relevant to the current data analysis included blood collection to measure levels of testosterone and measurement of body weight to categorize cancer patients into cancer cachexia and cancer non-cachexia sub-groups. ^ Results. After logarithmic transformation of data of cancer and control groups, the unpaired t test with unequal variances was done. The proportion of patients with hypogonadism in the male cancer and non-cancer control groups was 47.5% and 22.7% with a Pearson chi2 statistic of 1.6036 and a p value of 0.205. Comparing the mean calculated Bioavailable testosterone in male cancer patients and non-cancer controls resulted in a t statistic of 21.83 and a p value less than 0.001. When the cancer group alone was taken, the mean free testosterone, calculated bioavailable testosterone and total testosterone levels in the cancer non-cachexia sub-group were 3.93, 5.09, 103.51 respectively and in the cancer cachexia sub-group were 3.58, 4.17, 84.08 respectively. The unpaired t test with equal variances showed that the two sub-groups had p values of 0.2015, 0.1842, and 0.4894 with respect to calculated bioavailable testosterone, free testosterone, and total testosterone respectively. ^ Conclusions. The small sample size of this exploratory study, resulting in a small power, does not allow us to draw definitive conclusions. For the given sub-sample, the proportion of patients with hypogonadism in the cancer group was not significantly different from that of patients with hypogonadism in the control group. Inferences on prevalence of hypogonadism in male cancer patients could not be made in this paper as the sub-sample is small and therefore not representative of the general population. However, there was a statistically significant difference in calculated Bioavailable testosterone levels in male cancer patients versus non-cancer controls. Analysis of cachectic and non-cachectic patients within the male cancer group showed no significant difference in testosterone levels (total, free, and calculated bioavailable testosterone) between both sub-groups. However, to re-iterate, this study is exploratory and the results may change once the complete dataset is obtained and analyzed. It however serves as a good template to guide further research and analysis.^

A computerized statistical framework for coalescent analysis

Coalescent theory represents the most significant progress in theoretical population genetics in the past three decades. The coalescent theory states that all genes or alleles in a given population are ultimately inherited from a single ancestor shared by all members of the population, known as the most recent common ancestor. It is now widely recognized as a cornerstone for rigorous statistical analyses of molecular data from population [1]. The scientists have developed a large number of coalescent models and methods[2,3,4,5,6], which are not only applied in coalescent analysis and process, but also in today’s population genetics and genome studies, even public health. The thesis aims at completing a statistical framework based on computers for coalescent analysis. This framework provides a large number of coalescent models and statistic methods to assist students and researchers in coalescent analysis, whose results are presented in various formats as texts, graphics and printed pages. In particular, it also supports to create new coalescent models and statistical methods. ^

Selection bias and the cross-validation of regression models for prediction

Strategies are compared for the development of a linear regression model with stochastic (multivariate normal) regressor variables and the subsequent assessment of its predictive ability. Bias and mean squared error of four estimators of predictive performance are evaluated in simulated samples of 32 population correlation matrices. Models including all of the available predictors are compared with those obtained using selected subsets. The subset selection procedures investigated include two stopping rules, C$\sb{\rm p}$ and S$\sb{\rm p}$, each combined with an 'all possible subsets' or 'forward selection' of variables. The estimators of performance utilized include parametric (MSEP$\sb{\rm m}$) and non-parametric (PRESS) assessments in the entire sample, and two data splitting estimates restricted to a random or balanced (Snee's DUPLEX) 'validation' half sample. The simulations were performed as a designed experiment, with population correlation matrices representing a broad range of data structures.^ The techniques examined for subset selection do not generally result in improved predictions relative to the full model. Approaches using 'forward selection' result in slightly smaller prediction errors and less biased estimators of predictive accuracy than 'all possible subsets' approaches but no differences are detected between the performances of C$\sb{\rm p}$ and S$\sb{\rm p}$. In every case, prediction errors of models obtained by subset selection in either of the half splits exceed those obtained using all predictors and the entire sample.^ Only the random split estimator is conditionally (on $\\beta$) unbiased, however MSEP$\sb{\rm m}$ is unbiased on average and PRESS is nearly so in unselected (fixed form) models. When subset selection techniques are used, MSEP$\sb{\rm m}$ and PRESS always underestimate prediction errors, by as much as 27 percent (on average) in small samples. Despite their bias, the mean squared errors (MSE) of these estimators are at least 30 percent less than that of the unbiased random split estimator. The DUPLEX split estimator suffers from large MSE as well as bias, and seems of little value within the context of stochastic regressor variables.^ To maximize predictive accuracy while retaining a reliable estimate of that accuracy, it is recommended that the entire sample be used for model development, and a leave-one-out statistic (e.g. PRESS) be used for assessment. ^

Extension of k-ratio methods to rank-based analyses

An extension of k-ratio multiple comparison methods to rank-based analyses is described. The new method is analogous to the Duncan-Godbold approximate k-ratio procedure for unequal sample sizes or correlated means. The close parallel of the new methods to the Duncan-Godbold approach is shown by demonstrating that they are based upon different parameterizations as starting points.^ A semi-parametric basis for the new methods is shown by starting from the Cox proportional hazards model, using Wald statistics. From there the log-rank and Gehan-Breslow-Wilcoxon methods may be seen as score statistic based methods.^ Simulations and analysis of a published data set are used to show the performance of the new methods. ^

Patterns of homicide Houston: Texas, 1987

The situational and interpersonal characteristics of homicides occurring in Houston, Texas, during 1987 were investigated. A total of 328 cases were ascertained from the linking of police computer data, medical examiner's records, and death certificate information. The medical examiner's records contained all of the ascertained cases. The comparability ratio between the medical examiner's records and police and vital statistic data was 1.03 and 0.966, respectively. Data inconsistencies were found between the three information sources on Spanish surname, age, race/ethnicity, external cause of death coding, alcohol and drug involvement, weapon/method used, and Hispanic immigration status. Recommendations for improving the quality of homicide information gathered and for linking homicide surveillance systems were made.^ Males constituted 82% of all victims. The age-adjusted homicide rate for Blacks was 31.1 per 100,000 population, for Hispanics 19.2, and for Anglos 5.4. Among males, Blacks had an age-adjusted rate of 54.5, Hispanics, 31.0, and Anglos 7.5. Among females, Blacks had an age-adjusted rate of 9.3, Hispanics 6.1, and Anglos 3.1. Black males, ages 25-34, had the highest homicide rate, at 96.5.^ Half of all homicides occurred in a residence. Among Hispanic males, homicides occurred most often in the street. Firearms were used to commit 64% of the homicides. Arguments preceded 58% of all cases. Nearly two-thirds of the victims knew their assailant. Only 15% of males compared to 62% of females were killed by a spouse, an intimate acquaintance, or a family member. Blacks (93%) and Hispanics (88%) were more likely than Anglos (70%) to have been killed by persons of the same race/ethnicity. Nearly three-fourths of all Houston Hispanic homicide victims were foreign born.^ Alcohol was detected in 47% of the victims tested. Nearly one-third of those tested had blood alcohol concentrations (BACs) greater than 100 mg%. Males (53%) were more likely than females (20%) to have positive BACs. Hispanic males (64%) were more likely to have detectable BACs than either Black (51%) or Anglo (44%) males.^ Illegal drugs were detected in 20% of the victims tested. One-fourth of the victims who tested positive for drugs had more than one drug in their system at death. The stimulant cocaine was the most commonly detected drug, comprising 53% of all illegal drugs identified.^ Recommendations for the primary, secondary, and tertiary prevention of homicide and for future homicide research are made. ^

FACTORS INFLUENCING THE PATTERNS OF PHYSICIAN VISITS TO NURSING HOME RESIDENTS

This study was designed to identify some of the factors related to patterns of physician visits to nursing home residents. The relationship of ten resident and organizational characteristics to patterns of physician visits was investigated through secondary analysis of data abstracted from the 1973-74 National Nursing Home Survey of the National Center for Health Statistics. The study sample was composed of 11,135 of the 19,013 nursing home residents who participated in the survey.^ The analytic results revealed that all ten variables had a statistically significant relationship to patterns of physician visits, mainly due to the large sample size. The degrees of association between the variables, measured by the Cramer's V statistic, ranged from moderate to very weak.^ Certification status of the nursing home under Medicare and/or Medicaid was shown to be most strongly related to patterns of physician visits, followed by primary source of payment for nursing home care, and residence prior to nursing home admission. Several variables thought to be related to patterns of physician visits were found to have a very weak relationship: age of the resident, marital status, length of stay, primary diagnosis, number of chronic conditions, activities of daily living status, and levels of care.^ In order to get a more precise picture of the relative influence of certification status and primary source of payment when the other variables were statistically controlled, these two variables were combined into a single variable. The results revealed that the combined effects of certification status and primary source of payment were sustained, regardless of differences in the residents' personal, utilization, and health status characteristics, and the levels of care that they received. The results also indicated that the five groups created by combining the two variables differed in patterns of physician visits. For example, private pay residents in intermediate care facilities (ICF's) and non-certified facilities were more likely to receive unscheduled visits than private pay residents in skilled nursing homes (SNH's), residents in SNH's supported by Medicare or Medicaid, and residents in ICF's supported by Medicaid. ^

Motivational interviewing and feedback for college drinkers: Handling missing values with complete case analysis and multiple imputation

Objective: In this secondary data analysis, three statistical methodologies were implemented to handle cases with missing data in a motivational interviewing and feedback study. The aim was to evaluate the impact that these methodologies have on the data analysis. ^ Methods: We first evaluated whether the assumption of missing completely at random held for this study. We then proceeded to conduct a secondary data analysis using a mixed linear model to handle missing data with three methodologies (a) complete case analysis, (b) multiple imputation with explicit model containing outcome variables, time, and the interaction of time and treatment, and (c) multiple imputation with explicit model containing outcome variables, time, the interaction of time and treatment, and additional covariates (e.g., age, gender, smoke, years in school, marital status, housing, race/ethnicity, and if participants play on athletic team). Several comparisons were conducted including the following ones: 1) the motivation interviewing with feedback group (MIF) vs. the assessment only group (AO), the motivation interviewing group (MIO) vs. AO, and the intervention of the feedback only group (FBO) vs. AO, 2) MIF vs. FBO, and 3) MIF vs. MIO.^ Results: We first evaluated the patterns of missingness in this study, which indicated that about 13% of participants showed monotone missing patterns, and about 3.5% showed non-monotone missing patterns. Then we evaluated the assumption of missing completely at random by Little's missing completely at random (MCAR) test, in which the Chi-Square test statistic was 167.8 with 125 degrees of freedom, and its associated p-value was p=0.006, which indicated that the data could not be assumed to be missing completely at random. After that, we compared if the three different strategies reached the same results. For the comparison between MIF and AO as well as the comparison between MIF and FBO, only the multiple imputation with additional covariates by uncongenial and congenial models reached different results. For the comparison between MIF and MIO, all the methodologies for handling missing values obtained different results. ^ Discussions: The study indicated that, first, missingness was crucial in this study. Second, to understand the assumptions of the model was important since we could not identify if the data were missing at random or missing not at random. Therefore, future researches should focus on exploring more sensitivity analyses under missing not at random assumption.^