A robust weighted Kaplan–Meier approach for data with dependent censoring using linear combinations of prognostic covariates

The weighted Kaplan–Meier (WKM) estimator is often used to incorporate prognostic covariates into survival analysis to improve efficiency and correct for potential bias. In this paper, we generalize the WKM estimator to handle a situation with multiple prognostic covariates and potential‐dependent censoring through the use of prognostic covariates. We propose to combine multiple prognostic covariates into two risk scores derived from two working proportional hazards models. One model is for the event times. The other model is for the censoring times. These two risk scores are then categorized to define the risk groups needed for the WKM estimator. A method of defining categories based on principal components is proposed. We show that the WKM estimator is robust to misspecification of either one of the two working models. In simulation studies, we show that the robust WKM approach can reduce bias due to dependent censoring and improve efficiency. We apply the robust WKM approach to a prostate cancer data set. Copyright 2010 John Wiley & Sons, Ltd.     

A robust method for comparing two treatments in a confirmatory clinical trial via multivariate time‐to‐event methods that jointly incorporate information from longitudinal and time‐to‐event data

We consider regulatory clinical trials that require a prespecified method for the comparison of two treatments for chronic diseases (e.g. Chronic Obstructive Pulmonary Disease) in which patients suffer deterioration in a longitudinal process until death occurs. We define a composite endpoint structure that encompasses both the longitudinal data for deterioration and the time‐to‐event data for death, and use multivariate time‐to‐event methods to assess treatment differences on both data structures simultaneously, without a need for parametric assumptions or modeling. Our method is straightforward to implement, and simulations show that the method has robust power in situations in which incomplete data could lead to lower than expected power for either the longitudinal or survival data. We illustrate the method on data from a study of chronic lung disease. Copyright © 2009 John Wiley & Sons, Ltd.     

Two‐dimensional MR spectroscopy of minimal hepatic encephalopathy and neuropsychological correlates in vivo

Purpose:

To evaluate regional cerebral metabolic and structural changes in patients with minimal hepatic encephalopathy (MHE) using two‐dimensional (2D) MR spectroscopy (MRS) and T‐weighted MRI, to correlate the observed MR changes with neuropsychological (NP) test scores, and to compare the diagnostic accuracy of MRI, 2D MRS, and NP tests in discriminating between patients and healthy subjects.

Materials and Methods:

Thirty‐three MHE patients and 30 healthy controls were investigated. The 2D localized correlated spectroscopy (L‐COSY) was performed in the frontal and occipital brain on a 1.5 Tesla (T) MR scanner. The NP test battery included 15 tests, grouped into 6 cognitive domains. Globus pallidus signal intensities were calculated from T₁‐weighted images.

Results:

The 2D MRS showed significant differences in ratios of the following metabolite(s) peaks with respect to creatine (Cr): decreased myo‐inositol (mI), choline (Ch), mICh, and increased (glutamate plus glutamine) (Glx) in patients compared with healthy subjects in both occipital and frontal lobes. Frontal lobe taurine also showed a decline in patients. The NP test results revealed declines in cognitive speed, motor function, executive function, and global cognitive status. Significant correlations were found between the altered metabolites and NP tests. Alteration in the mICh/Cr ratio was noted as a powerful discriminant between healthy subjects and the patients.

Conclusion:

The study demonstrates that relative metabolite levels determined by 2D MRS, in particular mICh/Cr, provide the best diagnostic prediction for MHE. The results suggest that depletions of myo‐inositol, choline and taurine with respect to creatine correlate with measures of neuropsychological impairment. J. Magn. Reson. Imaging 2010;32:35–43. © 2010 Wiley‐Liss, Inc.     

Establishing normative data for multi-trial memory tests: the multivariate regression-based approach

Abstract

Objective: Multi-trial memory tests are widely used in research and clinical practice because they allow for assessing different aspects of memory and learning in a single comprehensive test procedure. However, the use of multi-trial memory tests also raises some key data analysis issues. Indeed, the different trial scores are typically all correlated, and this correlation has to be properly accounted for in the statistical analyses. In the present paper, the focus is on the setting where normative data have to be established for multi-trial memory tests. At present, normative data for such tests are typically based on a series of univariate analyses, i.e. a statistical model is fitted for each of the test scores separately. This approach is suboptimal because (1) the correlated nature of the data is not accounted for, (2) multiple testing issues may arise, and (3) the analysis is not parsimonious. Method and results: Here, a normative approach that is not hampered by these issues is proposed (the so-called multivariate regression-based approach). The methodology is exemplified in a sample of N = 221 Dutch-speaking children (aged between 5.82 and 15.49 years) who were administered Rey’s Auditory Verbal Learning Test. An online Appendix that details how the analyses can be conducted in practice (using the R software) is also provided. Conclusion: The multivariate normative regression-based approach has some substantial methodological advantages over univariate regression-based methods. In addition, the method allows for testing substantive hypotheses that cannot be addressed in a univariate framework (e.g. trial by covariate interactions can be modeled).     

Nurse in patients’ health status assessment: Data from a pilot study assessing agreement among nurse and gastroenterologist in computing IBD-clinical scores

IntroductionCrohn’s Disease (CD) and Ulcerative Colitis (UC) are chronic, systemic Inflammatory Bowel Diseases (IBDs) that need a multidisciplinary approach involving not only different medical specialists but also qualified nurses.AimWe evaluated the concordance between IBD-nurse and physician in computing Clinical Activity Scores in IBD-patients treated with biologics.MethodsWe enrolled all consecutive IBD-patients treated with biologics in two referral centers for IBD-care. For each patient, a gastroenterologist and a nurse blindly filled-out a form to assess the Harvey–Bradshaw Index (HBI) in CD or the partial MAYO score in UC. All data were recorded to assess the beyond chance agreement (concordance) using the k statistic.Results87 patients were enrolled. The agreement in all patients by k value was substantial (66%), ranging from moderate to substantial (95% CI from 51% to 80%). The main reason of disagreement was about the scoring of remission versus mild activity, and that of mild versus moderate activity, both in CD and UC. For the HBI, the best agreement was for well-being on the previous day (k 62%) and the least one for abdominal mass (k 35%).ConclusionsOur study shows an acceptable strength of agreement among nurse and gastroenterologist in evaluating the disease activity of IBD-patients through the calculation of clinical scores.     

A propensity score approach to correction for bias due to population stratification using genetic and non‐genetic factors

Confounding due to population stratification (PS) arises when differences in both allele and disease frequencies exist in a population of mixed racial/ethnic subpopulations. Genomic control, structured association, principal components analysis (PCA), and multidimensional scaling (MDS) approaches have been proposed to address this bias using genetic markers. However, confounding due to PS can also be due to non‐genetic factors. Propensity scores are widely used to address confounding in observational studies but have not been adapted to deal with PS in genetic association studies. We propose a genomic propensity score (GPS) approach to correct for bias due to PS that considers both genetic and non‐genetic factors. We compare the GPS method with PCA and MDS using simulation studies. Our results show that GPS can adequately adjust and consistently correct for bias due to PS. Under no/mild, moderate, and severe PS, GPS yielded estimated with bias close to 0 (mean=?0.0044, standard error=0.0087). Under moderate or severe PS, the GPS method consistently outperforms the PCA method in terms of bias, coverage probability (CP), and type I error. Under moderate PS, the GPS method consistently outperforms the MDS method in terms of CP. PCA maintains relatively high power compared to both MDS and GPS methods under the simulated situations. GPS and MDS are comparable in terms of statistical properties such as bias, type I error, and power. The GPS method provides a novel and robust tool for obtaining less‐biased estimates of genetic associations that can consider both genetic and non‐genetic factors. Genet. Epidemiol. 33:679–690, 2009. © 2009 Wiley‐Liss, Inc.     

Comparison of QCT-derived and DXA-derived areal bone mineral density and T scores

Summary  Two-dimensional areal bone mineral density (aBMD) of the proximal femur measured by three-dimensional quantitative computed tomography (QCT) in 91 elderly women was compared to dual-energy X-ray absorptiometry (DXA) aBMD results measured in the same patients. The measurements were highly correlated, though QCT aBMD values were marginally lower in absolute units. Transformation of the QCT aBMD values to T score values using National Health and Nutrition Examination Survey (NHANES) DXA-derived reference data improved agreement and clinical utility. Introduction  World Health Organization guidelines promulgate aBMD (g cm⁻²) measurement of the proximal femur for the diagnosis of bone fragility. In recent years, there has been increasing interest in QCT to facilitate understanding of three-dimensional bone structure and strength. Objective  To assist in comparison of QCT-derived data with DXA aBMD results, a technique for deriving aBMD from QCT measurements has been developed. Methods  To test the validity of the QCT method, 91 elderly females were scanned on both DXA and CT scanners. QCT-derived DXA equivalent aBMD (QCT_DXA aBMD) was calculated using CTXA Hip™ software (Mindways Software Inc., Austin, TX, USA) and compared to DXA-derived aBMD results. Results  Test retest analysis indicated lower root mean square (RMS) errors for CTXA; F test between CTXA and DXA was significantly different at femoral neck (FN) and trochanter (TR) (p < 0.05). QCT underestimates DXA values by 0.02 ± 0.05 g cm⁻² (total hip, TH), 0.01 ± 0.04 g cm⁻² (FN), 0.03 ± 0.07 g cm⁻² (inter-trochanter, IT), and 0.02 ± 0.05 g cm⁻² (TR). The RMS errors (standard error of estimate) between QCT and DXA T scores for TH, FN, IT, and TR were 0.36, 0.40, 0.39, and 0.49, respectively. Conclusions  This study shows that results from QCT aBMD appropriately adjusted can be evaluated against NHANES reference data to diagnose osteoporosis.     

Residency applicants misinterpret their United States Medical Licensing Exam Scores

Proper interpretation of the results of the United States Medical Licensing Exam (USMLE) is important for program directors, residents, and faculty who advise applicants about applying for residency positions. We suspected that applicants often misinterpreted their performance in relationship to others who took the same examination. In 2005, 54 consecutive applicants to the University of Tennessee, College of Medicine internal medicine residency program were asked to complete a brief survey about their performance on Parts 1 and 2 of the USMLE exam. When asked what percentile their Part I score represented, slightly over one in ten were unsure or did not know, and nearly three out of five wrote in their two-digit score. Of the 15 who wrote in another number, only a third were within ten percentile points of their estimated percentile. Similar results were seen for Part II. A higher percentage of international medical graduates (IMGs) than U.S. applicants responded to the percentile question with their two-digit scores (79% vs. 50% p = .08). Applicants to residency programs frequently misinterpret their performance on the USMLE compared to their peers. Unless they are high performers, those who misinterpret their two-digit scores as percentiles markedly overestimate their performance. The sponsors of the USMLE should discontinue reporting the two-digit score and consider re-instating the reporting of percentiles.     

试题库在预防医学课程考核中的应用效果分析

目的 了解新乡医学院三全学院不同专业医学生预防医学课程考试情况,促进课程考核方式和试题库建设质量的提高.方法 运用教育测量学的原理和方法,对试卷的质量和学生的成绩进行分析.结果 本次考试学生的平均成绩为72.73分,呈正态分布.不同专业学生的考试成绩差异具有统计学意义( P＜0.001).试卷平均难度、区分度和信度分别为0.61、0.43和0.71.结论 试卷题型分布合理、难度适中、区分度尚可、信度高,试题库可以用于课程考核.同时,还需要加强不同专业学生预防医学课程的教育力度.