Bayesian Hidden Markov Modeling of Array CGH Data

Genomic alterations have been linked to the development and progression of cancer. The technique of Comparative Genomic Hybridization (CGH) yields data consisting of fluorescence intensity ratios of test and reference DNA samples. The intensity ratios provide information about the number of copies in DNA. Practical issues such as the contamination of tumor cells in tissue specimens and normalization errors necessitate the use of statistics for learning about the genomic alterations from array-CGH data. As increasing amounts of array CGH data become available, there is a growing need for automated algorithms for characterizing genomic profiles. Specifically, there is a need for algorithms that can identify gains and losses in the number of copies based on statistical considerations, rather than merely detect trends in the data. We adopt a Bayesian approach, relying on the hidden Markov model to account for the inherent dependence in the intensity ratios. Posterior inferences are made about gains and losses in copy number. Localized amplifications (associated with oncogene mutations) and deletions (associated with mutations of tumor suppressors) are identified using posterior probabilities. Global trends such as extended regions of altered copy number are detected. Since the posterior distribution is analytically intractable, we implement a Metropolis-within-Gibbs algorithm for efficient simulation-based inference. Publicly available data on pancreatic adenocarcinoma, glioblastoma multiforme and breast cancer are analyzed, and comparisons are made with some widely-used algorithms to illustrate the reliability and success of the technique.

Semiparametric Normal Transformation Models for Spatially Correlated Survival Data

There is an emerging interest in modeling spatially correlated survival data in biomedical and epidemiological studies. In this paper, we propose a new class of semiparametric normal transformation models for right censored spatially correlated survival data. This class of models assumes that survival outcomes marginally follow a Cox proportional hazard model with unspecified baseline hazard, and their joint distribution is obtained by transforming survival outcomes to normal random variables, whose joint distribution is assumed to be multivariate normal with a spatial correlation structure. A key feature of the class of semiparametric normal transformation models is that it provides a rich class of spatial survival models where regression coefficients have population average interpretation and the spatial dependence of survival times is conveniently modeled using the transformed variables by flexible normal random fields. We study the relationship of the spatial correlation structure of the transformed normal variables and the dependence measures of the original survival times. Direct nonparametric maximum likelihood estimation in such models is practically prohibited due to the high dimensional intractable integration of the likelihood function and the infinite dimensional nuisance baseline hazard parameter. We hence develop a class of spatial semiparametric estimating equations, which conveniently estimate the population-level regression coefficients and the dependence parameters simultaneously. We study the asymptotic properties of the proposed estimators, and show that they are consistent and asymptotically normal. The proposed method is illustrated with an analysis of data from the East Boston Ashma Study and its performance is evaluated using simulations.

MODELING DIFFERENTIATED TREATMENT EFFECTS FOR MULTIPLE OUTCOMES DATA

Multiple outcomes data are commonly used to characterize treatment effects in medical research, for instance, multiple symptoms to characterize potential remission of a psychiatric disorder. Often either a global, i.e. symptom-invariant, treatment effect is evaluated. Such a treatment effect may over generalize the effect across the outcomes. On the other hand individual treatment effects, varying across all outcomes, are complicated to interpret, and their estimation may lose precision relative to a global summary. An effective compromise to summarize the treatment effect may be through patterns of the treatment effects, i.e. "differentiated effects." In this paper we propose a two-category model to differentiate treatment effects into two groups. A model fitting algorithm and simulation study are presented, and several methods are developed to analyze heterogeneity presenting in the treatment effects. The method is illustrated using an analysis of schizophrenia symptom data.

Studying Effects of Primary Care Physicians and Patients on the Trade-Off Between Charges for Primary Care and Specialty Care Using a Hierarchical Multivariate Two-Part Model

Objective. To examine effects of primary care physicians (PCPs) and patients on the association between charges for primary care and specialty care in a point-of-service (POS) health plan. Data Source. Claims from 1996 for 3,308 adult male POS plan members, each of whom was assigned to one of the 50 family practitioner-PCPs with the largest POS plan member-loads. Study Design. A hierarchical multivariate two-part model was fitted using a Gibbs sampler to estimate PCPs' effects on patients' annual charges for two types of services, primary care and specialty care, the associations among PCPs' effects, and within-patient associations between charges for the two services. Adjusted Clinical Groups (ACGs) were used to adjust for case-mix. Principal Findings. PCPs with higher case-mix adjusted rates of specialist use were less likely to see their patients at least once during the year (estimated correlation: –.40; 95% CI: –.71, –.008) and provided fewer services to patients that they saw (estimated correlation: –.53; 95% CI: –.77, –.21). Ten of 11 PCPs whose case-mix adjusted effects on primary care charges were significantly less than or greater than zero (p < .05) had estimated, case-mix adjusted effects on specialty care charges that were of opposite sign (but not significantly different than zero). After adjustment for ACG and PCP effects, the within-patient, estimated odds ratio for any use of primary care given any use of specialty care was .57 (95% CI: .45, .73). Conclusions. PCPs and patients contributed independently to a trade-off between utilization of primary care and specialty care. The trade-off appeared to partially offset significant differences in the amount of care provided by PCPs. These findings were possible because we employed a hierarchical multivariate model rather than separate univariate models.

Electronic medical record systems, data quality and loss to follow-up: survey of antiretroviral therapy programmes in resource-limited settings

OBJECTIVE: To describe the electronic medical databases used in antiretroviral therapy (ART) programmes in lower-income countries and assess the measures such programmes employ to maintain and improve data quality and reduce the loss of patients to follow-up. METHODS: In 15 countries of Africa, South America and Asia, a survey was conducted from December 2006 to February 2007 on the use of electronic medical record systems in ART programmes. Patients enrolled in the sites at the time of the survey but not seen during the previous 12 months were considered lost to follow-up. The quality of the data was assessed by computing the percentage of missing key variables (age, sex, clinical stage of HIV infection, CD4+ lymphocyte count and year of ART initiation). Associations between site characteristics (such as number of staff members dedicated to data management), measures to reduce loss to follow-up (such as the presence of staff dedicated to tracing patients) and data quality and loss to follow-up were analysed using multivariate logit models. FINDINGS: Twenty-one sites that together provided ART to 50 060 patients were included (median number of patients per site: 1000; interquartile range, IQR: 72-19 320). Eighteen sites (86%) used an electronic database for medical record-keeping; 15 (83%) such sites relied on software intended for personal or small business use. The median percentage of missing data for key variables per site was 10.9% (IQR: 2.0-18.9%) and declined with training in data management (odds ratio, OR: 0.58; 95% confidence interval, CI: 0.37-0.90) and weekly hours spent by a clerk on the database per 100 patients on ART (OR: 0.95; 95% CI: 0.90-0.99). About 10 weekly hours per 100 patients on ART were required to reduce missing data for key variables to below 10%. The median percentage of patients lost to follow-up 1 year after starting ART was 8.5% (IQR: 4.2-19.7%). Strategies to reduce loss to follow-up included outreach teams, community-based organizations and checking death registry data. Implementation of all three strategies substantially reduced losses to follow-up (OR: 0.17; 95% CI: 0.15-0.20). CONCLUSION: The quality of the data collected and the retention of patients in ART treatment programmes are unsatisfactory for many sites involved in the scale-up of ART in resource-limited settings, mainly because of insufficient staff trained to manage data and trace patients lost to follow-up.

Lipodystrophy and weight changes: data from the Swiss HIV Cohort Study, 2000-2006

BACKGROUND AND OBJECTIVES: Combination antiretroviral therapy (cART) is changing, and this may affect the type and occurrence of side effects. We examined the frequency of lipodystrophy (LD) and weight changes in relation to the use of specific drugs in the Swiss HIV Cohort Study (SHCS). METHODS: In the SHCS, patients are followed twice a year and scored by the treating physician as having 'fat accumulation', 'fat loss', or neither. Treatments, and reasons for change thereof, are recorded. Our study sample included all patients treated with cART between 2003 and 2006 and, in addition, all patients who started cART between 2000 and 2003. RESULTS: From 2003 to 2006, the percentage of patients taking stavudine, didanosine and nelfinavir decreased, the percentage taking lopinavir, nevirapine and efavirenz remained stable, and the percentage taking atazanavir and tenofovir increased by 18.7 and 22.2%, respectively. In life-table Kaplan-Meier analysis, patients starting cART in 2003-2006 were less likely to develop LD than those starting cART from 2000 to 2002 (P<0.02). LD was quoted as the reason for treatment change or discontinuation for 4% of patients on cART in 2003, and for 1% of patients treated in 2006 (P for trend <0.001). In univariate and multivariate regression analysis, patients with a weight gain of >or=5 kg were more likely to take lopinavir or atazanavir than patients without such a weight gain [odds ratio (OR) 2, 95% confidence interval (CI) 1.3-2.9, and OR 1.7, 95% CI 1.3-2.1, respectively]. CONCLUSIONS: LD has become less frequent in the SHCS from 2000 to 2006. A weight gain of more than 5 kg was associated with the use of atazanavir and lopinavir.

Graft coronary vasculopathy in cardiac transplantation--evaluation of risk factors by multivariate analysis

The development of coronary vasculopathy is the main determinant of long-term survival in cardiac transplantation. The identification of risk factors, therefore, seems necessary in order to identify possible treatment strategies. Ninety-five out of 397 patients, undergoing orthotopic cardiac transplantation from 10/1985 to 10/1992 were evaluated retrospectively on the basis of perioperative and postoperative variables including age, sex, diagnosis, previous operations, renal function, cholesterol levels, dosage of immunosuppressive drugs (cyclosporin A, azathioprine, steroids), incidence of rejection, treatment with calcium channel blockers at 3, 6, 12, and 18 months postoperatively. Coronary vasculopathy was assessed by annual angiography at 1 and 2 years postoperatively. After univariate analysis, data were evaluated by stepwise multiple logistic regression analysis. Coronary vasculopathy was assessed in 15 patients at 1 (16%), and in 23 patients (24%) at 2, years. On multivariate analysis, previous operations and the incidence of rejections were identified as significant risk factors (P < 0.05), whereas the underlying diagnosis had borderline significance (P = 0.058) for the development of graft coronary vasculopathy. In contrast, all other variables were not significant in our subset of patients investigated. We therefore conclude that the development of coronary vasculopathy in cardiac transplant patients mainly depends on the rejection process itself, aside from patient-dependent factors. Therapeutic measures, such as the administration of calcium channel blockers and regulation of lipid disorders, may therefore only reduce the progress of native atherosclerotic disease in the posttransplant setting.

Multivariate modelling of responses to conditional items: New possibilities for latent class analysis

Questionnaire data may contain missing values because certain questions do not apply to all respondents. For instance, questions addressing particular attributes of a symptom, such as frequency, triggers or seasonality, are only applicable to those who have experienced the symptom, while for those who have not, responses to these items will be missing. This missing information does not fall into the category 'missing by design', rather the features of interest do not exist and cannot be measured regardless of survey design. Analysis of responses to such conditional items is therefore typically restricted to the subpopulation in which they apply. This article is concerned with joint multivariate modelling of responses to both unconditional and conditional items without restricting the analysis to this subpopulation. Such an approach is of interest when the distributions of both types of responses are thought to be determined by common parameters affecting the whole population. By integrating the conditional item structure into the model, inference can be based both on unconditional data from the entire population and on conditional data from subjects for whom they exist. This approach opens new possibilities for multivariate analysis of such data. We apply this approach to latent class modelling and provide an example using data on respiratory symptoms (wheeze and cough) in children. Conditional data structures such as that considered here are common in medical research settings and, although our focus is on latent class models, the approach can be applied to other multivariate models.

SURVIVAL PREDICTION FOR BRAIN TUMOR PATIENTS USING GENE EXPRESSION DATA

Brain tumor is one of the most aggressive types of cancer in humans, with an estimated median survival time of 12 months and only 4% of the patients surviving more than 5 years after disease diagnosis. Until recently, brain tumor prognosis has been based only on clinical information such as tumor grade and patient age, but there are reports indicating that molecular profiling of gliomas can reveal subgroups of patients with distinct survival rates. We hypothesize that coupling molecular profiling of brain tumors with clinical information might improve predictions of patient survival time and, consequently, better guide future treatment decisions. In order to evaluate this hypothesis, the general goal of this research is to build models for survival prediction of glioma patients using DNA molecular profiles (U133 Affymetrix gene expression microarrays) along with clinical information. First, a predictive Random Forest model is built for binary outcomes (i.e. short vs. long-term survival) and a small subset of genes whose expression values can be used to predict survival time is selected. Following, a new statistical methodology is developed for predicting time-to-death outcomes using Bayesian ensemble trees. Due to a large heterogeneity observed within prognostic classes obtained by the Random Forest model, prediction can be improved by relating time-to-death with gene expression profile directly. We propose a Bayesian ensemble model for survival prediction which is appropriate for high-dimensional data such as gene expression data. Our approach is based on the ensemble "sum-of-trees" model which is flexible to incorporate additive and interaction effects between genes. We specify a fully Bayesian hierarchical approach and illustrate our methodology for the CPH, Weibull, and AFT survival models. We overcome the lack of conjugacy using a latent variable formulation to model the covariate effects which decreases computation time for model fitting. Also, our proposed models provides a model-free way to select important predictive prognostic markers based on controlling false discovery rates. We compare the performance of our methods with baseline reference survival methods and apply our methodology to an unpublished data set of brain tumor survival times and gene expression data, selecting genes potentially related to the development of the disease under study. A closing discussion compares results obtained by Random Forest and Bayesian ensemble methods under the biological/clinical perspectives and highlights the statistical advantages and disadvantages of the new methodology in the context of DNA microarray data analysis.

Time-Series Panel Analysis (TSPA): Multivariate Modeling of Temporal Associations in Psychotherapy Process.

Objective: Processes occurring in the course of psychotherapy are characterized by the simple fact that they unfold in time and that the multiple factors engaged in change processes vary highly between individuals (idiographic phenomena). Previous research, however, has neglected the temporal perspective by its traditional focus on static phenomena, which were mainly assessed at the group level (nomothetic phenomena). To support a temporal approach, the authors introduce time-series panel analysis (TSPA), a statistical methodology explicitly focusing on the quantification of temporal, session-to-session aspects of change in psychotherapy. TSPA-models are initially built at the level of individuals and are subsequently aggregated at the group level, thus allowing the exploration of prototypical models. Method: TSPA is based on vector auto-regression (VAR), an extension of univariate auto-regression models to multivariate time-series data. The application of TSPA is demonstrated in a sample of 87 outpatient psychotherapy patients who were monitored by postsession questionnaires. Prototypical mechanisms of change were derived from the aggregation of individual multivariate models of psychotherapy process. In a 2nd step, the associations between mechanisms of change (TSPA) and pre- to postsymptom change were explored. Results: TSPA allowed a prototypical process pattern to be identified, where patient's alliance and self-efficacy were linked by a temporal feedback-loop. Furthermore, therapist's stability over time in both mastery and clarification interventions was positively associated with better outcomes. Conclusions: TSPA is a statistical tool that sheds new light on temporal mechanisms of change. Through this approach, clinicians may gain insight into prototypical patterns of change in psychotherapy.

Survival with Newly Diagnosed Metastatic Prostate Cancer in the "Docetaxel Era": Data from 917 Patients in the Control Arm of the STAMPEDE Trial (MRC PR08, CRUK/06/019)

BACKGROUND Prostate cancer (PCa) is the second most common disease among men worldwide. It is important to know survival outcomes and prognostic factors for this disease. Recruitment for the largest therapeutic randomised controlled trial in PCa-the Systemic Therapy in Advancing or Metastatic Prostate Cancer: Evaluation of Drug Efficacy: A Multi-Stage Multi-Arm Randomised Controlled Trial (STAMPEDE)-includes men with newly diagnosed metastatic PCa who are commencing long-term androgen deprivation therapy (ADT); the control arm provides valuable data for a prospective cohort. OBJECTIVE Describe survival outcomes, along with current treatment standards and factors associated with prognosis, to inform future trial design in this patient group. DESIGN, SETTING, AND PARTICIPANTS STAMPEDE trial control arm comprising men newly diagnosed with M1 disease who were recruited between October 2005 and January 2014. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS Overall survival (OS) and failure-free survival (FFS) were reported by primary disease characteristics using Kaplan-Meier methods. Hazard ratios and 95% confidence intervals (CIs) were derived from multivariate Cox models. RESULTS AND LIMITATIONS A cohort of 917 men with newly diagnosed M1 disease was recruited to the control arm in the specified interval. Median follow-up was 20 mo. Median age at randomisation was 66 yr (interquartile range [IQR]: 61-71), and median prostate-specific antigen level was 112 ng/ml (IQR: 34-373). Most men (n=574; 62%) had bone-only metastases, whereas 237 (26%) had both bone and soft tissue metastases; soft tissue metastasis was found mainly in distant lymph nodes. There were 238 deaths, 202 (85%) from PCa. Median FFS was 11 mo; 2-yr FFS was 29% (95% CI, 25-33). Median OS was 42 mo; 2-yr OS was 72% (95% CI, 68-76). Survival time was influenced by performance status, age, Gleason score, and metastases distribution. Median survival after FFS event was 22 mo. Trial eligibility criteria meant men were younger and fitter than general PCa population. CONCLUSIONS Survival remains disappointing in men presenting with M1 disease who are started on only long-term ADT, despite active treatments being available at first failure of ADT. Importantly, men with M1 disease now spend the majority of their remaining life in a state of castration-resistant relapse. PATIENT SUMMARY Results from this control arm cohort found survival is relatively short and highly influenced by patient age, fitness, and where prostate cancer has spread in the body.

Electron and photon energy calibration with the ATLAS detector using LHC Run 1 data

This paper presents the electron and photon energy calibration achieved with the ATLAS detector using about 25 fb−1 of LHC proton–proton collision data taken at centre-of-mass energies of √s = 7 and 8 TeV. The reconstruction of electron and photon energies is optimised using multivariate algorithms. The response of the calorimeter layers is equalised in data and simulation, and the longitudinal profile of the electromagnetic showers is exploited to estimate the passive material in front of the calorimeter and reoptimise the detector simulation. After all corrections, the Z resonance is used to set the absolute energy scale. For electrons from Z decays, the achieved calibration is typically accurate to 0.05% in most of the detector acceptance, rising to 0.2% in regions with large amounts of passive material. The remaining inaccuracy is less than 0.2–1% for electrons with a transverse energy of 10 GeV, and is on average 0.3% for photons. The detector resolution is determined with a relative inaccuracy of less than 10% for electrons and photons up to 60 GeV transverse energy, rising to 40% for transverse energies above 500 GeV.