Statistical errors in modern medical research

BACKGROUND: Research estimates of inadvertent harm to patients undergoing modern healthcare demonstrate a serious problem. Much attention has been paid to analysis of the causes of error and harm, but researchers have typically focussed either on human interaction and communication or on systems design, without fully considering the other components. Existing models for analysing harm are principally derived from theory and the analysis of individual incidents, and their practical value is often limited by the assumption that identifying causal factors automatically suggests solutions...

A stratified matched-pair study is often designed for adjusting a confounding effect or effect of different trails/centers/ groups in modern medical studies. The relative risk is one of the most frequently used indices in comparing efficiency of two treatments in clinical trials. In this paper, we propose seven confidence interval estimators for the common relative risk and three simultaneous confidence interval estimators for the relative risks in stratified matched-pair designs. The performance of the proposed methods is evaluated with respect to their type I error rates, powers, coverage probabilities, and expected widths...

We introduce a statistical, process-oriented metadata model to describe the process of medical research data collection, management, results analysis and dissemination. Our approach explicitly provides a structure for pieces of information used in Clinical Study Data Management Systems, enabling a more active role for any associated metadata. Using the object-oriented paradigm, we describe the classes of our model that participate during the design of a clinical trial and the subsequent collection and management of the relevant data...

In 2004, Garcia-Berthou and Alcaraz published "Incongruence between test statistics and P values in medical papers," a critique of statistical errors that received a tremendous amount of attention. One of their observations was that the final reported digit of p-values in articles published in the journal Nature departed substantially from the uniform distribution that they suggested should be expected. In 2006, Jeng critiqued that critique, observing that the statistical analysis of those terminal digits had been based on comparing the actual distribution to a uniform continuous distribution, when digits obviously are discretely distributed...

BACKGROUND: The Medicare Modernization Act of 2003 requires drug plan sponsors to provide medication therapy management programs (MTMPs) to beneficiaries with (1) drug expenditures above $4,000, (2) multiple comorbidities, and (3) multiple prescription drugs. The Medical Expenditure Panel Survey (MEPS) is a national probability survey conducted annually by the Agency for Healthcare Research and Quality and the National Center for Health Statistics to provide nationally representative estimates of health care use, expenditures, sources of payments, and insurance coverage for the U...

Pathology is both a medical specialty and an investigative scientific discipline, concerned with understanding the essential nature of human disease. Ultimately, pathology is accountable as well, as measured by the accuracy of our diagnoses and the resultant patient care outcomes. As such, we must consider the evidence base underlying our practices. Within the realm of Laboratory Medicine, extensive attention has been given to testing accuracy and precision. Critical examination of the evidence base supporting the clinical use of specific laboratory tests or technologies is a separate endeavor, to which specific attention must be given...

While Nazism is almost universally recognized as a great evil, control of science and medicine by the totalitarian Nazi state might be viewed as increasing efficiency. Scientific methods are applied to semiquantitatively analyze the effects of Nazism on medical progress in gastroenterology to document its pernicious effects, and to honor outstanding gastroenterologists persecuted or murdered by the Nazis. This is a retrospective, quasi-case-controlled study. To disprove the null hypothesis that Nazism was efficient, retarded progress in gastroenterology is demonstrated by (1) enumerating the loss to Nazi Germany from 1933 to 1944 due to violent death, incarceration, or forced exile of key researchers in gastroenterology, defined by authorship of at least one book or 10 articles in peer-reviewed journals or other outstanding scholarship; (2) demonstrating a statistically significantly greater loss in Nazi Germany than in non-Nazi (Weimar German Republic from 1921 to 1932) or anti-Nazi (democratic America from 1933 to 1944) control groups; and (3) demonstrating that each loss was directly due to Nazism (murder, incarceration, or exile due to documented threat of violence/death or revocation of medical license)...

Greater focus is needed on improving patient safety in modern healthcare systems and the first step to achieving this is to reliably identify the safety issues arising in healthcare. Research has shown the accident and emergency (A&E) department to be a particularly problematic environment where safety is a concern due to various factors, such as the range, nature and urgency of presenting conditions and the high turnover of patients. As in all healthcare environments clinical incident reporting in A&E is an important tool for detecting safety issues which can result in identifying solutions, learning from error and enhancing patient safety...

The U.S. Food and Drug Administration (FDA) Modernization Act of 1997 has a Section (No. 112) entitled 'Expediting Study and Approval of Fast Track Drugs' (the Act). In 1998, the FDA issued a 'Guidance for Industry: the Fast Track Drug Development Programs' (the FTDD programmes) to meet the requirement of the Act. The purpose of FTDD programmes is to 'facilitate the development and expedite the review of new drugs that are intended to treat serious or life-threatening conditions and that demonstrate the potential to address unmet medical needs'...

Contemporary pathophysiology is essentially based upon three principal pillars of support: First the experimental method (formulated by Cl. Bernard); second experimental design (proposed by R. A. Fisher); and finally, present-day information resources, which are easily accessible in sophisticated databases, following the so-called information explosion. These three underlying principles, sensitively interrelated, should be employed appropriately when engaging in pathophysiological research or education. Three points of support invariably offer stable equilibrium, as does a tripod, and it would be an error a priori to attempt to support research work exclusively on high-tech methodology, or overreliance on statistical software, or pseudo-abundance of citations from journals enjoying a high impact factor, whilst lacking significant balancing support from either of the other two legs of the tripod--or indeed other sources altogether...

Cognitive screening tests and items have been found to perform differently across groups that differ in terms of education, ethnicity and race. Despite the profound implications that such bias holds for studies in the epidemiology of dementia, little research has been conducted in this area. Using the methods of modern psychometric theory (in addition to those of classical test theory), we examined the performance of the Attention subscale of the Mattis Dementia Rating Scale. Several item response theory models, including the two- and three-parameter dichotomous response logistic model, as well as a polytomous response model were compared...

An important problem exists in the interpretation of modern medical research data: Biological understanding and previous research play little formal role in the interpretation of quantitative results. This phenomenon is manifest in the discussion sections of research articles and ultimately can affect the reliability of conclusions. The standard statistical approach has created this situation by promoting the illusion that conclusions can be produced with certain "error rates," without consideration of information from outside the experiment...

Statistics is the science that studies variability in all its forms and, in essence, is an instrument that allows us to analyze variable phenomena and detect small, but nevertheless important, differences. The instrumental character of this science made Statistics a fundamental tool for the study of biological and clinical phenomena, but the purpose of this discussion is to focus on the fact that Statistics, either directly or indirectly, is presently the basis of virtually all medical decision-making processes and, consequently, has had a major influence on clinical practice itself...

This article examines how scientists use human, animal, and bacterial evidence to develop policy recommendations about the health consequences of human exposure to modern chemicals. Human evidence is limited because many epidemiological studies are contaminated with selection effects or unobserved heterogeneity. Changes in the aggregate incidence of morbidity (such as cancer) in the population over time are not a substitute for the lack of good individual-level data because incidence data are contaminated by the medicalization of cancer...

Biostatistical methods have become thoroughly integrated into modern biomedical and clinical research. Nevertheless, every observer who has evaluated articles in medical journals has noted that as many as half the reported results were based on questionable statistical analysis. This situation, combined with the fact that most errors involve relatively simple statistical procedures, points to the need for researchers and practitioners to be able to personally judge the quality of the statistical analyses in what they read...

Using computer simulation of family data sets within segregation analysis limits the comparative research of the autosomal major locus model (MLM) and the multifactorial model (MFM) which described the basic types of inheritance of the alternative traits (affected--nonaffected) has been conducted. Robustness of models (statistical aspect) and the power of the analysis (its possibility to discriminate MLM and MFM) are tested. It is shown that permissible level of relative errors for estimated population's frequency is increased, when the values of parameters of models are increased (with decrease of sporadic cases' portion)...