Logistic regression in survival analysis.

Preface. On the Entropies and Mutual Information of Some Bivariate Continuous Distributions Used in Reliability M. Ahsanullah, M. Habibullah. Initial Conditions Problem in Event History Analysis: An Indirect Inference Procedure M.Y. An. Analysis of Survival Data Under Competing Risks with Missing Cause of Death Information: Application and Implications for Study Design J.W. Andersen, et al. Conditional Proportional Hazards Models B.C. Arnold, Y.H. Kim. A Comparison of Conditional and Unconditional Inference Relating to Log-Gamma Distribution N. Balakrishnan, P.S. Chan. Universal Formulas for Treatment Effects from Noncompliance Data A.A. Balke, J. Pearl. Fundational Issues Concerning the Analysis of Censored Data R.E. Barlow, P. Tsai. Burn-in at the Component and System Level H.W. Block, et al. Identificationof Dependent Competing Risks Models K. Carling, T. Jacobson. Reliability Modelling for Optical Amplified Communication Systems M. Chown, G.A. Whitmore. A Parametric Approach to Measurement Errors in Receiver Operating Characteristic Studies M. Coffin, S. Sukhatme. Models for Degradation Processes and Event Times Based on Gaussian Processes K. Doksum, S.-L. Normand. A Non-Parametric Two-Sample Survival Test Based on a Single Occupancy Fermi-Dirac Model for the Discrete Range Distribution J.T. Efird, F. Pardo. Probability Approximations and Inequalities for Sequential Tests J. Glaz, J.R. Kenyon. Cure Mixture Models in Breast Cancer Survival Studies N.H. Gordon. A General Approach to Derive Chi-Square Type of Goodness-of-Fit Tests for Lifetime Data S. Hawala, J.-L. Wang. Prediction in Survival Analysis: Model or Medic? R. Henderson, M. Jones. Dynamic Reliability Models M. Hollander, E.A. Pena. Generalizations of Current Status Data with Applications N.P. Jewell, M. van der Laan. Trend Analysis of Multiple Counting Processes T. Kamakura. Historical Controls and Model Survival Analysis N. Keiding. A Random Effects Model for Multivariate Life Data A.C. Kimber. Statistical Challenges in Comparing Chemotherapy and Bone Marrow Transplantation as a Treatment for Leukemia J.P. Klein, M.-J. Zhang. Maximum Likelihood Estimation and the Multivariate Bernoulli Distribution: An Application to Reliability P.H. Kvam. Intermediate Clinical Events, Surrogate Markers and Survival M. Lefkopoulou, M. Zelen. A Semiparametric Bootstrap for Proportional Hazards Models T.M. Loughin, K.J. Koehler. Application of Cox Regression with a Change Point in Clinical Studies X. Luo, et al. Burn-in with Age Replacement A.W. Marshall. Fitting Cox's Proportional Hazards Model Using Grouped Survival Data I.W. McKeague, M.-J. Zhang. Statistical Methods for Dependent Competing Risks M.L. Moeschberger, J.P. Klein. Orthogonal Functions of Inverse Gaussian Disbrituions R. Nishii. Statistical Models for Quality of Life Measures Y. Palesch, A.J. Groos. Nonparametric Estimation of Regression Parameters from Censored Data with Two Discrete Covariates M.H. Rahbar. Locally Efficient Median Regressionwith Random Censoring and Surrogate Markers J.M. Robins. Survival Models for Heterogeneity Using the Non-Central Chi-Squared Distribution with Zero Degrees of Freedom C.S. Rocha. Efficiently Weighted Estimating Equations with Application to Proportional Excess Hazards P. Sasieni. Sequential Multi-Hypothesis Testing in Software Reliability J.S. Shieh, Y.L. Tong. Assessing Gamma Frailty Models for Clustered Failure Time Data J.H. Shih,

PM10 EFFECTS ON PRETERM BIRTH BY VARIOUS STATISTICAL MODELS

Great strides in the analysis of survival data using Bayesian methods have been made in the past ten years due to advances in Bayesian computation and the feasibility of such methods. In this chapter, we review Bayesian advances in survival analysis and discuss the various semiparametric modeling techniques that are now commonly used. We review parametric and semiparametric approaches to Bayesian survival analysis, with a focus on proportional hazards models. Reference to other types of models are also given.

For analysis of clustered survival data, the inferences of parameters in semi-parametricfrailty models have been widely studied. It is also important to investigate the potentialheterogeneity in event times among clusters (e.g. centers, patients). For purpose of thisanalysis, the interval estimation of frailty is useful. In this paper we propose a visual-izing method to present con dence intervals of individual frailties across clusters usingthe frailtyHL R-package, which is implemented from h-likelihood methods for frailtymodels. The proposed method is demonstrated using two practical examples.Keywords: frailtyHL R-package, h-likelihood, interval estimation, multilevel frailty, sharedfrailty. 1. Introduction The frailty models, Cox’s proportional hazards models (Park et al., 2012) allowing frailty(random e ect) terms, have been widely used for the analysis of clustered survival-time data.For the inference, the marginal likelihood often involves analytically intractable integrals,particularly when modelling multilevel or correlated frailties. However, the hierarchical-likelihood (h-likelihood; Lee and Nelder, 1996, 2001) obviates the need for intractable inte-gration over the frailty terms (Ha et al., 2001, 2011; Ha and Cho, 2012). It is also importantto investigate the potential heterogeneity in event times among clusters (e.g. centers, pa-tients) in order to understand and interpret the variability in the data (Vaida and Xu,2000). For example, despite the use of standardized protocols in multicenter randomizedclinical trials, outcome may vary between centers (Rondeau et al., 2008; Ha et al., 2011).Such heterogeneity may alter the interpretation and reporting of the treatment. For pur-pose of this analysis, the interval estimation of frailty is more useful than the inferenceof variance components of frailty (Vaida and Xu, 2000; Lee and Nelder, 2009; Ha et al.,

Background: The PROCLAIMSM registry (www.proclaimregistry.com), created in 2011, is the largest collection of IL-2 treated patients in the US and provides real-time insights into sequencing or combining IL-2 with new and old therapies and how this may affect patient outcomes. Previously, we reported a median overall survival (mOS) of 20 months with a median follow-up of 37 months in metastatic melanoma (mM) patients treated with high dose IL-2 (HD IL-2) between 2007 and 2012 from a retrospective cohort. These findings led to the hypothesis that improved mOS may have been a result of subsequent salvage therapies, including checkpoint inhibitors. Purpose: To report on the analysis of survival data from 26 sites. Methods: Patients must have received at least one dose of HD IL-2 for this analysis. Those that received checkpoint therapy prior to HD IL-2 were excluded. Statistics and survival analysis on prospectively entered patients were performed on datasets as of March 16th, 2015. Results: The median overall survival (mOS) for the 236 patients was 18.4 months with a median follow-up of 21.7 months. Patients were stratified into three groups; HD IL-2 only (n=123), HD IL-2 followed by ipilimumab (Post ipi, n=78), and HD IL-2 followed by PD-1 inhibitors (Post αPD-1, n=35). There were four patients in the Post αPD-1 group that received anti-PD-L1 treatment. Patients in the HD IL-2 only, Post ipi, and Post αPD-1 groups achieved a mOS of 14, 15.7, and 28.7 months, respectively. The estimated 12-month survival rates were 56%, 64%, and 97%, respectively. There were 10/78 (13%) and 3/35 (8.6%) post therapy treatment-related incidences of autoimmune events in the Post Ipi and Post αPD-1 groups, respectively. No treatment related deaths were reported. Conclusions: This is the first report of clinical data relating to HD IL-2 use followed by checkpoint blockade of the PD-1 pathway. Treatment with anti-PD-1 after initial therapy with HD IL-2 had significantly prolonged survival compared to patients treated with ipilimumab. Moreover, improved survival was not observed in patients treated with follow-on ipilimumab compared to patients treated only with HD IL-2. Anti-PD-1 therapy after HD IL-2, appears to be safe, is therapeutically active. These data support the concept of investigating IL-2 therapy in combination or sequence with newly developed immune checkpoint inhibitors. Citation Format: Michael K.K. Wong, Michael A. Morse, David F. McDermott, Joseph I. Clark, Howard L. Kaufman, Gregory A. Daniels, Hong Hua, Sandra Aung. Overall survival of metastatic melanoma patients treated with HD IL-2 followed by immune checkpoint blockade of the CTLA-4 or the PD-1 pathways: Analysis of data on the current use of HD IL-2. [abstract]. In: Proceedings of the CRI-CIMT-EATI-AACR Inaugural International Cancer Immunotherapy Conference: Translating Science into Survival; September 16-19, 2015; New York, NY. Philadelphia (PA): AACR; Cancer Immunol Res 2016;4(1 Suppl):Abstract nr B140.

Association Between Body Size and Colorectal Adenoma Recurrence

The Registry of the International Society for Heart and Lung Transplantation: Twenty-seventh official adult heart transplant report—2010

Many factors contribute to the development of clinical atherosclerotic disease in adults. Observational studies conducted from the late 1940s onward have helped us to identify cigarette smoking, cholesterol levels, diabetes, blood pressure, and other factors as important determinants of cardiovascular disease (CVD) outcomes.1,2 The effects are multiplicative. For example, smoking, hypertension, and diabetes each double the risk of a heart attack, and having all 3 factors can lead to a risk that was ≈8 times that of an adult of similar age and sex who did not have any of the factors.3 A major focus in the earlier population and clinical studies was identification of persons at increased risk before the clinical atherosclerotic event. Less attention has been directed toward other types of events, such as occurrence of a myocardial infarction in persons presenting with chest pain, recurrent CVD events, and long-term vascular disease complications such as cardiac failure. The determinants of these vascular events are likely to include some of the classical risk factors, but new factors will no doubt be important as well. Improvements in outpatient and inpatient care, diagnosis, and biomarker discovery have reshaped the landscape. It is possible to visualize subclinical CVD with modern atherosclerotic imaging techniques such as carotid intima-media thickness and arterial calcification assessments. Clinical chemists and geneticists identify new biomarkers that promise to help refine assessments of CVD risk, but it is not clear how such tests should be used for research or for clinical care. This article addresses several of the questions posed above and takes the perspective of research and care for clinical atherosclerotic disease, emphasizing the progress we have made from traditional risk factor assessment to the present time that includes newer assessment methods such as genomics, metabolomics, and predictive medicine. ### Traditional Risk Factors for Cardiovascular Disease The traditional risk factors include cholesterol, blood …

Clinical trials indicate that a sizable proportion of adults have multiple borderline coronary risk factors and may benefit from treatment. To estimate the relative and absolute contributions of borderline and elevated risk factors to the population burden of coronary heart disease (CHD) events. A prospective cohort study and a national cross-sectional survey. The Framingham Study and the Third National Health and Nutrition Examination Survey (NHANES III). White non-Hispanic persons in the Framingham Study and in NHANES III who were between 35 to 74 years of age and had no CHD. Occurrence of first CHD events according to 5 major CHD risk factors: blood pressure, low-density lipoprotein and high-density lipoprotein cholesterol levels, glucose intolerance, and smoking. Three categories-optimal, borderline, and elevated-were defined for each risk factor per national guidelines. Sex-specific 10-year CHD event rates from the Framingham Study were applied to numbers of at-risk individuals estimated from NHANES III and the 2000 U.S. Census. Twenty-six percent of men and 41% of women had at least 1 borderline risk factor in NHANES III. According to estimates, more than 90% of CHD events will occur in individuals with at least 1 elevated risk factor, and approximately 8% will occur in people with only borderline levels of multiple risk factors. Absolute 10-year CHD risk exceeded 10% in men older than age 45 years who had 1 elevated risk factor and 4 or more borderline risk factors and in those who had at least 2 elevated risk factors. In women, absolute CHD risk exceeded 10% only in those older than age 55 years who had at least 3 elevated risk factors. The generalizability of the findings to persons of other ethnic backgrounds is unknown. Borderline CHD risk factors alone account for a small proportion of CHD events.

2317 Uterine serous carcinoma is associated with a high risk of venous thromboembolism regardless of latency from surgical staging

Our study identified risk factors for the development of clinically identifiable catheter-associated thrombosis (CT). We performed a retrospective cohort study of neonates in whom a central catheter was present. A total of 1,475 catheters were identified in 766 patients during a 36-month study period. The odds ratio (OR) of thrombi formation in catheterized neonates was modeled using simple (single predictor) and multiple (multiple predictors) logistic regressions as well as simple and multiple Cox's proportional hazard models. The incidence of CT was 1.17 per 100 neonates. Unadjusted factors including age at insertion, history of surgery before or during line placement, cholestasis, femoral location, and line size significantly increased the OR or hazards ratio (HR) of developing thrombi formation. In multiple logistic and Cox's regression analyses, three factors continued to be significantly associated with OR or HR of thrombi formation: line size, femoral location, and cholestasis. We conclude that clinically identifiable CT is rare in the neonatal population. Furthermore, catheter-specific characteristics are predictive for CT and require further investigation.

Stroke ranks as the third leading cause of death in the United States. It is now estimated that there are more than 700 000 incident strokes annually and 4.4 million stroke survivors.1 2 The economic burden of stroke was estimated by the American Heart Association to be $51 billion (direct and indirect costs) in 1999.3 Despite the advent of treatment of selected patients with acute ischemic stroke with tissue plasminogen activator and the promise of other experimental therapies, the best approach to reducing the burden of stroke remains prevention.4 5 High-risk or stroke-prone individuals can be identified and targeted for specific interventions.6 This is important because epidemiological data suggest a substantial leveling off of prior declines in stroke-related mortality and a possible increase in stroke incidence.7 8 The Stroke Council of the American Heart Association formed an ad hoc writing group to provide a clear and concise overview of the evidence regarding various established and potential stroke risk factors. The writing group was chosen based on expertise in specific subject areas, and it used literature review, reference to previously published guidelines, and expert opinion to summarize existing evidence and formulate recommendations (Table 1⇓). View this table: Table 1. Levels of Evidence and Grading of Recommendations As given in Tables 2 through 4⇓⇓⇓, risk factors or risk markers for a first stroke were classified according to potential for modification (nonmodifiable, modifiable, or potentially modifiable) and strength of evidence (well documented, less well documented).5 The tables give the estimated prevalence, population attributable risk, relative risk, and risk reduction with treatment for each factor when known. Population attributable risk reflects the proportion of ischemic strokes in the population that can be attributed to a particular risk factor and is given by the formula 100×[prevalence(relative risk−1)/prevalence(relative risk−1)+1]). …

This paper presents a Bayesian approach using WinBUGS for analysing survival data in which observations have missing information on some covariates. Modelling the joint density of the survival time and the covariates allows for the missing covariate data to be missing at random (MAR), as opposed to the more restrictive assumptions imposed by a complete case analysis. Here, the survival times are modelled by the accelerated failure time model and the joint covariate density is factorized as a series of conditional densities, each modelled by logistic regression. We propose a class of models to examine MAR assumption by using Bayesian informative priors or auxiliary data. In the example considered, the complete case analysis underestimates the proportion of severely impaired cases. Furthermore, models evaluating sensitivity to the MAR assumption suggest that median life expectancies could be increased. Gains in precision are small in the application considered, possibly a reflection of extra uncertainty because of the inclusion of all cases, including those of unknown severity. Through simple Bayesian models, more realistic assumptions concerning the nature of the missing data can be made. Implementation in WinBUGS means that this model is accessible to practicing statisticians.

BackgroundCognitive resistance to Alzheimer’s disease (AD) refers to an individual’s capacity to avoid the appearance of Alzheimer’s dementia syndrome in the context of risk factors on pathologic processes. We sought to identify associations between potential modifiable risk factors for AD and cognitive resistance.Method2,318 participants from the Offspring and Omni cohorts in Framingham Heart Study without prevalent dementia and at high risk for AD were selected. High risk for AD was defined as having ≥2 of the following risk factors measured at baseline: (1) age >80 years; (2) diagnosis of cardiovascular disease or coronary heart failure; (3) carrier of ≥1 APOE ε4 allele; (4) plasma Aβ42/40 ≤0.1049 (Perez‐Grijalba et al.; 2019); (5) C‐reactive protein level ≥10 mg/L (Morley and Kushner; 1982); and (6) female sex. Cognitively resistant individuals were defined as those at high risk for AD that did not progress to a clinical diagnosis of dementia/AD. Standardized research criteria were used to ascertain all‐cause dementia and AD. Potential modifiable risk factors for AD measured at baseline included diabetes, hypertension, obesity, depression, smoking, and education. Logistic regression was used to examine associations between these factors and cognitive resistance to AD.ResultOver an average period of 36 years, absence of diabetes (OR = 3.63; 95% CI = 2.37 – 5.55; p <0.001) and absence of hypertension (OR = 1.60; 95% CI = 1.02 – 2.51; p = 0.038), as well as not smoking (OR = 2.10; 95% CI = 1.41 – 3.13; p <0.001), at baseline were significantly associated with cognitive resistance. Absence of depression, absence of obesity, or high education were not associated with cognitive resistance.ConclusionIndividuals at high risk for AD who do not have diabetes or hypertension, or do not smoke may be cognitively resistant to AD. These findings support the heart‐brain connection for dementia prevention and healthy cognitive aging.

Our aim was to evaluate liver transplant outcomes involving donors with high macrosteatosis grafts in the obese modern liver transplant recipient population. A high-steatosis graft was defined as donor graft macrosteatosis ≥30% on biopsy. Recipient obesity was defined as body mass index (BMI) >35 adjusted for ascites. Raw and adjusted recipient liver transplant survival were evaluated and compared between 4 cohorts: (1) high-steatosis graft in high-BMI recipient; (2) low-steatosis graft in high-BMI recipient; (3) high-steatosis graft in normal-BMI recipient; and (4) low-steatosis graft in normal-BMI recipient. After adjustment for multiple factors, recipient high-BMI remained an independent predictor of posttransplant mortality at 30 days (P < 0.0001) and persisted at 1 year (P = 0.009). A high-steatosis graft was the strongest independent predictor of mortality at 30 days (hazard ratio 2.05, 1.66-2.53; P < 0.0001) and that effect was diminished but persistent at 1 year (1.27, 1.10-1.46; P = 0.001). Recipient high-BMI and a high-steatosis graft are both significant independent and equally powerful predictors of mortality after modern liver transplant. High-steatosis grafts transplanted into obese recipients have the highest mortality. The increase in mortality associated with a high-steatosis graft into a normal-BMI recipient is similar in magnitude to a low-steatosis graft placed into a high-BMI recipient.