Data quality in trauma transfusion studies and the impact of missing data on predicting massive transfusion

Maximizing data quality may be especially difficult in trauma-related clinical research. Strategies are needed to improve data quality and assess the impact of data quality on clinical predictive models. This study had two objectives. The first was to compare missing data between two multi-center trauma transfusion studies: a retrospective study (RS) using medical chart data with minimal data quality review and the PRospective Observational Multi-center Major Trauma Transfusion (PROMMTT) study with standardized quality assurance. The second objective was to assess the impact of missing data on clinical prediction algorithms by evaluating blood transfusion prediction models using PROMMTT data. RS (2005-06) and PROMMTT (2009-10) investigated trauma patients receiving ≥ 1 unit of red blood cells (RBC) from ten Level I trauma centers. Missing data were compared for 33 variables collected in both studies using mixed effects logistic regression (including random intercepts for study site). Massive transfusion (MT) patients received ≥ 10 RBC units within 24h of admission. Correct classification percentages for three MT prediction models were evaluated using complete case analysis and multiple imputation based on the multivariate normal distribution. A sensitivity analysis for missing data was conducted to estimate the upper and lower bounds of correct classification using assumptions about missing data under best and worst case scenarios. Most variables (17/33=52%) had <1% missing data in RS and PROMMTT. Of the remaining variables, 50% demonstrated less missingness in PROMMTT, 25% had less missingness in RS, and 25% were similar between studies. Missing percentages for MT prediction variables in PROMMTT ranged from 2.2% (heart rate) to 45% (respiratory rate). For variables missing >1%, study site was associated with missingness (all p≤0.021). Survival time predicted missingness for 50% of RS and 60% of PROMMTT variables. MT models complete case proportions ranged from 41% to 88%. Complete case analysis and multiple imputation demonstrated similar correct classification results. Sensitivity analysis upper-lower bound ranges for the three MT models were 59-63%, 36-46%, and 46-58%. Prospective collection of ten-fold more variables with data quality assurance reduced overall missing data. Study site and patient survival were associated with missingness, suggesting that data were not missing completely at random, and complete case analysis may lead to biased results. Evaluating clinical prediction model accuracy may be misleading in the presence of missing data, especially with many predictor variables. The proposed sensitivity analysis estimating correct classification under upper (best case scenario)/lower (worst case scenario) bounds may be more informative than multiple imputation, which provided results similar to complete case analysis.^

Developing the follow-up schedules for women with breast cancer

Background: The follow-up care for women with breast cancer requires an understanding of disease recurrence patterns and the follow-up visit schedule should be determined according to the times when the recurrence are most likely to occur, so that preventive measure can be taken to avoid or minimize the recurrence. Objective: To model breast cancer recurrence through stochastic process with an aim to generate a hazard function for determining a follow-up schedule. Methods: We modeled the process of disease progression as the time transformed Weiner process and the first-hitting-time was used as an approximation of the true failure time. The women's "recurrence-free survival time" or a "not having the recurrence event" is modeled by the time it takes Weiner process to cross a threshold value which represents a woman experiences breast cancer recurrence event. We explored threshold regression model which takes account of covariates that contributed to the prognosis of breast cancer following development of the first-hitting time model. Using real data from SEER-Medicare, we proposed models of follow-up visits schedule on the basis of constant probability of disease recurrence between consecutive visits. Results: We demonstrated that the threshold regression based on first-hitting-time modeling approach can provide useful predictive information about breast cancer recurrence. Our results suggest the surveillance and follow-up schedule can be determined for women based on their prognostic factors such as tumor stage and others. Women with early stage of disease may be seen less frequently for follow-up visits than those women with locally advanced stages. Our results from SEER-Medicare data support the idea of risk-controlled follow-up strategies for groups of women. Conclusion: The methodology we proposed in this study allows one to determine individual follow-up scheduling based on a parametric hazard function that incorporates known prognostic factors.^

Instrumental variable method for the causal relationship between soluble receptor for advanced glycation end-products (sRAGE) and risk of pancreatic cancer

This thesis project is motivated by the potential problem of using observational data to draw inferences about a causal relationship in observational epidemiology research when controlled randomization is not applicable. Instrumental variable (IV) method is one of the statistical tools to overcome this problem. Mendelian randomization study uses genetic variants as IVs in genetic association study. In this thesis, the IV method, as well as standard logistic and linear regression models, is used to investigate the causal association between risk of pancreatic cancer and the circulating levels of soluble receptor for advanced glycation end-products (sRAGE). Higher levels of serum sRAGE were found to be associated with a lower risk of pancreatic cancer in a previous observational study (255 cases and 485 controls). However, such a novel association may be biased by unknown confounding factors. In a case-control study, we aimed to use the IV approach to confirm or refute this observation in a subset of study subjects for whom the genotyping data were available (178 cases and 177 controls). Two-stage IV method using generalized method of moments-structural mean models (GMM-SMM) was conducted and the relative risk (RR) was calculated. In the first stage analysis, we found that the single nucleotide polymorphism (SNP) rs2070600 of the receptor for advanced glycation end-products (AGER) gene meets all three general assumptions for a genetic IV in examining the causal association between sRAGE and risk of pancreatic cancer. The variant allele of SNP rs2070600 of the AGER gene was associated with lower levels of sRAGE, and it was neither associated with risk of pancreatic cancer, nor with the confounding factors. It was a potential strong IV (F statistic = 29.2). However, in the second stage analysis, the GMM-SMM model failed to converge due to non- concaveness probably because of the small sample size. Therefore, the IV analysis could not support the causality of the association between serum sRAGE levels and risk of pancreatic cancer. Nevertheless, these analyses suggest that rs2070600 was a potentially good genetic IV for testing the causality between the risk of pancreatic cancer and sRAGE levels. A larger sample size is required to conduct a credible IV analysis.^

Prevalence of Staphylococcus aureus colonization among high-risk HIV populations

Staphylococcus aureus is a common microorganism in humans, typically colonizing the nasopharynx, skin and other mucosal surfaces. It is among the most frequent causes of clinically-significant bacterial infections accounting for increased morbidity and mortality among individuals with HIV/AIDS. Evidence of higher colonization rates among high-risk HIV populations have been observed however, prevalence estimates have varied. Additionally, behavioral, biological, and/or environmental factors that may account for these high colonization rates are not understood. Previous literature on clinic-based surveys were subject to considerable biases. Additionally, representative samples of high-risk HIV populations were difficult to obtain due in part to an underrepresentation of individuals who may not regularly obtain health care. ^ The main objective of this project is to determine the prevalence of methicillin-sensitive S. aureus (MSSA) and methicillin-resistant (MRSA) nasal colonization in two populations: 1) men who have sex with men (MSM) and 2) injection drug users (IDU). Both of these populations are included in the third round of the National HIV Behavioral Surveillance System (NHBS) in Houston, Texas. ^ In the NHBS-MSM3 study, logistic regression was used to report odds ratios and 95% confidence intervals (CI). For the NHBS-IDU3 study, to account for the lack of independence between samples, the method of generalized estimating equations was utilized to report adjusted odds ratios and 95% CI. The NHBS-MSM3 study enrolled 202 participants with a MSSA colonization rate of 26.7% and MRSA rate of 3%. In the NHBS-IDU3 study, 18.4% were nasally colonized with MSSA and 5.7% were nasally colonized with MRSA. Among the NHBS-MSM3 population, high-risk sexual practices were associated with colonization. For the NHBS-IDU3 population, age, marital status, employment status, and the presence of scabs, were associated with colonization status when controlling for size of recruitment network. In multivariate GEE analyses, the use of antiretroviral medications and age remained significantly associated with S. aureus nasal colonization when controlling for size of recruitment network and gender. In both studies, a significantly higher than expected S. aureus and MRSA colonization rate was observed as compared to colonization rates described for the general population. However, these estimates were moderate in comparison to reported clinic-based MSM and IDU S. aureus colonization findings. This study validates substantial prevalence differences and biases that may exist with data collected from clinic-based MSM and IDU. The prevalence of MSSA and MRSA nasal colonization did not differ significantly with respect to HIV status among NHBS-MSM3/NHBS-IDU3 participants. Continued examination on the effects of S. aureus colonization and infection should be examined longitudinally to confirm additional community-based determinants in populations that are disproportionately affected.^

Assessing the patterns of colorectal cancer treatment, adherence to treatment guidelines and survival in Texas

Colorectal cancer (CRC) is the third leading cancer in both incidence and mortality in Texas. This study investigated the adherence of CRC treatment to standard treatment guidelines and the association between standard treatment and CRC survival in Texas. The author used Texas Cancer Registry (TCR) and Medicare linked data to study the CRC treatment patterns and factors associated with standard treatment in patients who were more than 65 years old and were diagnosed in 2001 through 2007. We also determined whether adherence to standard treatment affect patients' survival. Multiple logistic regression and Cox regression analysis were used to analyze our data. Both regression models are adjusted for demographic characteristics and tumor characteristics. We found that for the 3977 regional colon cancer patients 80 years old or younger, 60.2% of them received chemotherapy, in adherence to the recommended treatment guidelines. People with younger age, female gender, higher education and lower comorbidity score are more likely adherent to this surgery guideline. Patients' adherence to chemotherapy in this cohort have better survival compared to those who are not (HR: 0.76, 95% CI: 0.68-0.84). For the 12709 colon cancer patients treated with surgery, 49.3% have more than 12 lymph nodes removed, in adherence to the treatment guidelines. People with younger age, female gender, higher education, regional stage, lager tumor size and lower comorbidity score are more likely to adherent to this surgery guideline. Patients with more than 12 lymph nodes removed in this cohort have better survival (HR: 0.86, 95% CI: 0.82-0.91). For the 1211 regional rectal cancer patients 80 years old or younger, 63.2% of them were adherent to radiation treatment. People with smaller tumor size and lower comorbidity score are more likely to adherent to this radiation guideline. There is no significant survival difference between radiation adherent patients and non-adherent patients (HR: 1.03, 95% CI: 0.82-1.29). For the 1122 regional rectal cancer patients 80 years old or younger who were treated with surgery, 76.0% of them received postoperative chemotherapy, in adherence to the treatment guidelines. People with younger age and smaller comorbidity score are related with higher adherence rate. Patients adherent with adjuvant chemotherapy in this cohort have better survival than those were not adherent (HR: 0.60, 95% CI: 0.45-0.79).^

Robust effect sizes and their confidence intervals for group difference between trajectories in hierarchical linear growth model

Hierarchical linear growth model (HLGM), as a flexible and powerful analytic method, has played an increased important role in psychology, public health and medical sciences in recent decades. Mostly, researchers who conduct HLGM are interested in the treatment effect on individual trajectories, which can be indicated by the cross-level interaction effects. However, the statistical hypothesis test for the effect of cross-level interaction in HLGM only show us whether there is a significant group difference in the average rate of change, rate of acceleration or higher polynomial effect; it fails to convey information about the magnitude of the difference between the group trajectories at specific time point. Thus, reporting and interpreting effect sizes have been increased emphases in HLGM in recent years, due to the limitations and increased criticisms for statistical hypothesis testing. However, most researchers fail to report these model-implied effect sizes for group trajectories comparison and their corresponding confidence intervals in HLGM analysis, since lack of appropriate and standard functions to estimate effect sizes associated with the model-implied difference between grouping trajectories in HLGM, and also lack of computing packages in the popular statistical software to automatically calculate them. ^ The present project is the first to establish the appropriate computing functions to assess the standard difference between grouping trajectories in HLGM. We proposed the two functions to estimate effect sizes on model-based grouping trajectories difference at specific time, we also suggested the robust effect sizes to reduce the bias of estimated effect sizes. Then, we applied the proposed functions to estimate the population effect sizes (d ) and robust effect sizes (du) on the cross-level interaction in HLGM by using the three simulated datasets, and also we compared the three methods of constructing confidence intervals around d and du recommended the best one for application. At the end, we constructed 95% confidence intervals with the suitable method for the effect sizes what we obtained with the three simulated datasets. ^ The effect sizes between grouping trajectories for the three simulated longitudinal datasets indicated that even though the statistical hypothesis test shows no significant difference between grouping trajectories, effect sizes between these grouping trajectories can still be large at some time points. Therefore, effect sizes between grouping trajectories in HLGM analysis provide us additional and meaningful information to assess group effect on individual trajectories. In addition, we also compared the three methods to construct 95% confident intervals around corresponding effect sizes in this project, which handled with the uncertainty of effect sizes to population parameter. We suggested the noncentral t-distribution based method when the assumptions held, and the bootstrap bias-corrected and accelerated method when the assumptions are not met.^

Exploring parental factors and their influence on early adolescent sexual health

Black and Hispanic youth experience the largest burden of sexually transmitted infections, teen pregnancy, and childbirth (Hamilton, Martin, & Ventura, 2011). Minority youth are disporportionately more likely to sexually debut at every age and debut before the age of 13 compared to whites (Centers for Disease Control and Prevention, 2011). However, there is little known about pre-coital sexual activity or protective parental factors in early adolscent minority youth. Parental factors such as parent-child communication and parental monitoring influence adolescent sexual behaviors and pre-coital sexual behaviors in early adolescence. Three distinct methods were used in this dissertation. Study one used qualitative methods, semi-structured, in-depth, individual interviews, to explore parent-child communication in African American mother-early adolescent son dyads. Study two used quantitative methods, secondary data analysis of a cross sectional study, to conduct a moderation analysis. For study three, I conducted a systematic review of parent-based adolescent sexual health interventions. Study one found that mothers feel comfortable talking about sex with adolescents, provide a two-prong sexual health message, and want their sons to tell their when they are thinking of having sex. Study found that parental monitoring moderates the relation between parent-child communication and pre-coital sexual behaviors. Study three found that interventions use a variety of theory, methods, and strategies and that no parent-based programs target faith-based organizations, mother-son or father-daughter dyads, or parents of LGBTQ youth. Adolescent sexual health interventions should consider addressing youth-to-parent disclosure of sexual activity or intentions to debut, addressing both parent-child sexual health communication and parental monitoring, and using a theoretical framework.^

Behavioral decision making and the levels of change: An application of the transtheoretical model to prenatal smoking in low -income women

Despite continued research and public health efforts to reduce smoking during pregnancy, prenatal cessation rates in the United States have decreased and the incidence of low birth weight has increased from 1985 to 1991. Lower socioeconomic status women who are at increased risk for poor pregnancy outcomes may be resistant to current intervention efforts during pregnancy. The purpose of this dissertation was to investigate the determinants of continued smoking and quitting among low-income pregnant women.^ Using data from cross-sectional surveys of 323 low-income pregnant smokers, the first study developed and tested measures of the pros and cons of smoking during pregnancy. The original decisional balance measure for smoking was compared with a new measure that added items thought to be more salient to the target population. Confirmatory factor analysis using structural equation modeling showed neither the original nor new measure fit the data adequately. Using behavioral science theory, content from interviews with the population, and statistical evidence, two 7-item scales representing the pros and cons were developed from a portion (n = 215) of the sample and successfully cross-validated on the remainder of the sample (n = 108). Logistic regression found only pros were significantly associated with continued smoking. In a discriminant function analysis, stage of change was significantly associated with pros and cons of smoking.^ The second study examined the structural relationships between psychosocial constructs representing some of the levels of and the pros and cons of smoking. The cross-sectional design mandates that statements made regarding prediction do not prove causation or directionality from the data or methods analysis. Structural equation modeling found the following: more stressors and family criticism were significantly more predictive of negative affect than social support; a bi-directional relationship was found between negative affect and current nicotine addiction; and negative affect, addiction, stressors, and family criticism were significant predictors of pros of smoking.^ The findings imply reversing the trend of decreasing smoking cessation during pregnancy may require supplementing current interventions for this population of pregnant smokers with programs addressing nicotine addiction, negative affect, and other psychosocial factors such as family functioning and stressors. ^

Skills training and social influences for violence prevention in middle schools: A curriculum evaluation

This pilot study evaluated the effect of skills training and of social influences on self-reported aggressive behavior in a sample of 239 sixth-grade students. The effect of two intervention groups and one control group were compared. In the first intervention group, a 15-session, violence-prevention curriculum was taught by the teacher. In the second intervention group, the same curriculum was taught by the teacher with the assistance of peer leaders trained to modify social norms about violence. The control group was evaluated but did not receive any training. The design included four schools. In two schools, three classes were assigned to one of the two interventions or to the control group. In the other two schools, two classes were assigned to either intervention (teacher only) or control. Students were evaluated before and after the implementation of the curriculum using a standardized questionnaire.^ The primary outcome was the effect of the curriculum and peer leaders on self-reported aggressive behaviors. The secondary outcome was their impact on intervening variables: knowledge about violence, conflict-resolution skills, self-efficacy, and attitudes.^ The intervention had a moderate effect on reducing self-reported aggressive behaviors among boys in two of the six classes that received the curriculum. Both classes with peer leaders reduced their aggressive behavior, but this reduction was significant in only one. A peer leader selection problem could probably explain this lack of effect.^ In three of the four schools, both interventions had an overall significant effect on increasing knowledge about violence and skills to reduce violence. Students also developed a more negative attitude toward violence after the intervention. As hypothesized, attitude change was stronger among students from the teacher plus peer leader group. No intervention effect was observed on self-efficacy nor on attitudes toward skills to reduce violence. Limitations of the study and implications for violence prevention in schools are discussed. ^

The epidemiology of chronic fatigue in San Francisco

Chronic fatigue syndrome (CFS) is a recently defined condition characterized by severe disabling fatigue that persists for a minimum of six months, and a host of somatic and neurocognitive symptoms. Although conditions similar to CFS have been described in the medical literature for over 100 years, little is known about the epidemiology of CFS or of chronic fatigue generally. The San Francisco Fatigue Study was undertaken to describe the prevalence and characteristics of self-reported chronic fatigue and associated conditions in a diverse urban community. The study utilized a cross-sectional telephone survey of a random sample of households in San Francisco, followed by case/control interviews of fatigued and nonfatigued subjects. Respondents were classified as chronically fatigued (CF) if they reported severe fatigue lasting six months or longer, then further classified as having CFS-like illness if, based on self-reported information, their condition appeared to meet CFS case definition criteria. Subjects who reported idiopathic chronic fatigue that did not meet CFS criteria were classified as having ICF-like illness.^ 8004 households were screened, yielding fatigue and demographic information on 16970 residents. CF was reported by 635 persons, 3.7% of the study population. CFS-like illness was identified in 34 subjects (0.2%), and ICF-like illness in 259 subjects (1.6%). Logistic regression analysis indicated that prevalence odds ratios for CFS-like illness were significantly elevated for females compared to males (OR = 2.9), and in Blacks (OR = 2.9) and Native Americans (OR = 13.2) relative to Whites, but significantly lower in Asians (OR = 0.12). Above-average household income was protective for all categories of CF. CFS-like subjects reported more symptoms and were more severely disabled than ICF-like subjects, but the pattern of symptoms experienced by both groups was similar. In conclusion, unexplained chronic fatigue, including CFS-like illness, occurs in all sociodemographic groups, but may be most prevalent among persons with lower incomes and in some racial minorities. Future studies that include clinical evaluation of incident cases of CFS and ICF are required to further clarify the epidemiology of unexplained chronic fatigue in the population. ^

The role of substance abuse treatment in preventing human immunodeficiency virus transmission among injecting drug users

This exploratory study assesses the utility of substance abuse treatment as a strategy for preventing human immunodeficiency virus (HIV) transmission among injecting drug users (IDUs). Data analyzed in this study were collected in San Antonio, TX, 1989 through 1995 using both qualitative and quantitative methods. Qualitative data included ethnographic interviews with 234 active IDUs; quantitative data included baseline risk assessments and HIV screening plus interviews follow-up interviews administered approximately six months later to 823 IDUs participating in a Federally-funded AIDS community outreach demonstration project.^ Findings that have particularly important implications for substance abuse treatment as an HIV prevention strategy for IDUs are listed below. (1) IDUs who wanted treatment were significantly more likely to be daily heroin users. (2) IDUs who want treatment were significantly more likely to have been to treatment previously. (3) IDUs who wanted treatment at baseline reported significantly higher levels of HIV risk than IDUs who did not want treatment. (4) IDUs who went to treatment between their baseline and follow-up interviews reported significantly higher levels of HIV risk at baseline than IDUs who did not go to treatment. (5) IDUs who went to treatment between their baseline and follow-up interviews reported significantly greater decreases in injection-related HIV risk behaviors. (6) IDUs who went to treatment reported significantly greater decreases in sexual HIV risk behaviors than IDUs who did not go to treatment.^ This study also noted a number of factors that may limit the effectiveness of substance abuse treatment in reducing HIV risk among IDUs. Findings suggest that the impact of methadone maintenance on HIV risk behaviors among opioid dependent IDUs may be limited by the negative manner in which it is perceived by IDUs as well as other elements of society. One consequence of the negative perception of methadone maintenance held by many elements of society may be an unwillingness to provide public funding for an adequate number of methadone maintenance slots. Thus many IDUs who would be willing to enter methadone maintenance are unable to enter it and many IDUs who do enter it are forced to drop out prematurely. ^

Structural equation modeling of the medical outcome study: Short Form 36 (SF-36)

The factorial validity of the SF-36 was evaluated using confirmatory factor analysis (CFA) methods, structural equation modeling (SEM), and multigroup structural equation modeling (MSEM). First, the measurement and structural model of the hypothesized SF-36 was explicated. Second, the model was tested for the validity of a second-order factorial structure, upon evidence of model misfit, determined the best-fitting model, and tested the validity of the best-fitting model on a second random sample from the same population. Third, the best-fitting model was tested for invariance of the factorial structure across race, age, and educational subgroups using MSEM.^ The findings support the second-order factorial structure of the SF-36 as proposed by Ware and Sherbourne (1992). However, the results suggest that: (a) Mental Health and Physical Health covary; (b) general mental health cross-loads onto Physical Health; (c) general health perception loads onto Mental Health instead of Physical Health; (d) many of the error terms are correlated; and (e) the physical function scale is not reliable across these two samples. This hierarchical factor pattern was replicated across both samples of health care workers, suggesting that the post hoc model fitting was not data specific. Subgroup analysis suggests that the physical function scale is not reliable across the "age" or "education" subgroups and that the general mental health scale path from Mental Health is not reliable across the "white/nonwhite" or "education" subgroups.^ The importance of this study is in the use of SEM and MSEM in evaluating sample data from the use of the SF-36. These methods are uniquely suited to the analysis of latent variable structures and are widely used in other fields. The use of latent variable models for self reported outcome measures has become widespread, and should now be applied to medical outcomes research. Invariance testing is superior to mean scores or summary scores when evaluating differences between groups. From a practical, as well as, psychometric perspective, it seems imperative that construct validity research related to the SF-36 establish whether this same hierarchical structure and invariance holds for other populations.^ This project is presented as three articles to be submitted for publication. ^

A study of the impact of cigarette advertising on adolescent susceptibility to smoking among 5th-, 8th-, and 12th-grade students in Hempstead and Hitchcock Independent School Districts

This study assessed the impact of cigarette advertising on adolescent susceptibility to smoking in the Hempstead and Hitchcock Independent School Districts. A convenience sample of 217 youths, 10-19 years of age was recruited in the study. Students completed both a paper-and-pencil and a computer-aided questionnaire in April 1996. Adolescents were defined as susceptible to smoking if they could not definitely rule out the possibility of future smoking. For the analysis, an index was devised: a 5-point index of an individual's receptivity to cigarette advertising. The index is determined by the number of positive responses to five survey items (recognizing cigarette brand logos, recognizing cigarette advertisement's pictures, recognizing cigarette brand slogans, evaluating adolescent attitudes toward cigarette advertising, and the degree to which adolescents were exposed to cigarette advertisements). Using logistic regression, we assessed the independent importance of the index in predicting susceptibility to smoking and ever smoking after adjusting for sociodemographic variables, perceived school performance and family composition. Of students surveyed, 54.4% of students appeared to have started the smoking uptake process as measured by susceptibility to smoking. Camel was recognized by the majority of students (88%), followed by Marlboro (41.5%) and Newport (40.1%). The pattern for recognition of the cigarette advertisements was the same as the pattern of market for cigarette. Advertisement featuring the cartoon character Joe Camel was significantly more appealing to adolescents than were advertisements with human models, with animal models, and with text only (p $<$ 0.001). Text only advertisement was significantly less appealing than other types of advertisements. The cigarette advertisement with White models (Marlboro) had significantly higher appeal to White students than to African-American students (p $<$ 0.001). The cigarette advertisement featuring African-American models (Virginia Slims) was significantly more appealing to African-American students than other ethnic groups (p $<$ 0.001). Receptivity to cigarette advertising was to be an important concurrent predictor of past smoking experience and intention to smoke in the future. Adolescents who scored in the fourth quartile of the Index of Receptivity to Cigarette Advertising were 7.54 (95% confidence interval (CI) = 1.92-29.56) times as likely to be susceptible to smoking, and were 4.56 (95% CI = 1.55-13.38) times as likely to have tried smoking, as those who scored in the first quartile of the Index. The findings confirmed the hypothesis that cigarette advertising may be a strong current influence in encouraging adolescents to initiate the smoking uptake process than sociodemographic variables, perceived school performance and family composition. ^

Statistical characterization and development of summary measures of non-normal distributions of nuclear morphometry data from prostate cancer cells for use as prognostic indicators

Nuclear morphometry (NM) uses image analysis to measure features of the cell nucleus which are classified as: bulk properties, shape or form, and DNA distribution. Studies have used these measurements as diagnostic and prognostic indicators of disease with inconclusive results. The distributional properties of these variables have not been systematically investigated although much of the medical data exhibit nonnormal distributions. Measurements are done on several hundred cells per patient so summary measurements reflecting the underlying distribution are needed.^ Distributional characteristics of 34 NM variables from prostate cancer cells were investigated using graphical and analytical techniques. Cells per sample ranged from 52 to 458. A small sample of patients with benign prostatic hyperplasia (BPH), representing non-cancer cells, was used for general comparison with the cancer cells.^ Data transformations such as log, square root and 1/x did not yield normality as measured by the Shapiro-Wilks test for normality. A modulus transformation, used for distributions having abnormal kurtosis values, also did not produce normality.^ Kernel density histograms of the 34 variables exhibited non-normality and 18 variables also exhibited bimodality. A bimodality coefficient was calculated and 3 variables: DNA concentration, shape and elongation, showed the strongest evidence of bimodality and were studied further.^ Two analytical approaches were used to obtain a summary measure for each variable for each patient: cluster analysis to determine significant clusters and a mixture model analysis using a two component model having a Gaussian distribution with equal variances. The mixture component parameters were used to bootstrap the log likelihood ratio to determine the significant number of components, 1 or 2. These summary measures were used as predictors of disease severity in several proportional odds logistic regression models. The disease severity scale had 5 levels and was constructed of 3 components: extracapsulary penetration (ECP), lymph node involvement (LN+) and seminal vesicle involvement (SV+) which represent surrogate measures of prognosis. The summary measures were not strong predictors of disease severity. There was some indication from the mixture model results that there were changes in mean levels and proportions of the components in the lower severity levels. ^

A comparison of Markov and generalized linear models of hospital mortality

This paper reports a comparison of three modeling strategies for the analysis of hospital mortality in a sample of general medicine inpatients in a Department of Veterans Affairs medical center. Logistic regression, a Markov chain model, and longitudinal logistic regression were evaluated on predictive performance as measured by the c-index and on accuracy of expected numbers of deaths compared to observed. The logistic regression used patient information collected at admission; the Markov model was comprised of two absorbing states for discharge and death and three transient states reflecting increasing severity of illness as measured by laboratory data collected during the hospital stay; longitudinal regression employed Generalized Estimating Equations (GEE) to model covariance structure for the repeated binary outcome. Results showed that the logistic regression predicted hospital mortality as well as the alternative methods but was limited in scope of application. The Markov chain provides insights into how day to day changes of illness severity lead to discharge or death. The longitudinal logistic regression showed that increasing illness trajectory is associated with hospital mortality. The conclusion is reached that for standard applications in modeling hospital mortality, logistic regression is adequate, but for new challenges facing health services research today, alternative methods are equally predictive, practical, and can provide new insights. ^