ABSTRACT
This article considers a way to test the hypothesis that two collections of objects are from the same uniform distribution of such objects. The exact p-value is calculated based on the distribution for the observed overlaps. In addition, an interval estimate of the number of distinct objects, when all objects are equally likely, is indicated.
ABSTRACT
The graphical approach has been proposed as a general framework for clinical trial designs involving multiple hypotheses, where decisions are made only based on the observed marginal p-values. The graphical approach starts from a graph that includes all hypotheses as vertices and gradually removes some vertices when their corresponding hypotheses are rejected. In this paper, we propose a reverse graphical approach, which starts from a set of singleton graphs and gradually adds vertices into graphs until rejection of a set of hypotheses is made. Proofs of familywise error rate control are provided. A simulation study is conducted for statistical power analysis, and a case study is included to illustrate how the proposed approach can be applied to clinical studies.
Subject(s)
Clinical Trials as Topic , Research DesignABSTRACT
Since the 18th century, the p value has been an important part of hypothesis-based scientific investigation. As statistical and data science engines accelerate, questions emerge: to what extent are scientific discoveries based on p values reliable and reproducible? Should one adjust the significance level or find alternatives for the p value? Inspired by these questions and everlasting attempts to address them, here, we provide a systematic examination of the p value from its roles and merits to its misuses and misinterpretations. For the latter, we summarize modest recommendations to handle them. In parallel, we present the Bayesian alternatives for seeking evidence and discuss the pooling of p values from multiple studies and datasets. Overall, we argue that the p value and hypothesis testing form a useful probabilistic decision-making mechanism, facilitating causal inference, feature selection, and predictive modeling, but that the interpretation of the p value must be contextual, considering the scientific question, experimental design, and statistical principles.
ABSTRACT
Biological age and brain age estimated using biological and neuroimaging measures have recently emerged as surrogate aging biomarkers shown to be predictive of diverse health outcomes. As aging underlies the development of many chronic conditions, surrogate aging biomarkers capture health at the whole person level, having the potential to improve our understanding of multimorbidity. Our study investigates whether elevated biological age and brain age are associated with an increased risk of multimorbidity using a large dataset from the Midlife in the United States Refresher study. Ensemble learning is utilized to combine multiple machine learning models to estimate biological age using a comprehensive set of biological markers. Brain age is obtained using Gaussian processes regression and neuroimaging data. Our study is the first to examine the relationship between accelerated brain age and multimorbidity. Furthermore, it is the first attempt to explore how biological age and brain age are related to multimorbidity in mental health. Our findings hold the potential to advance the understanding of disease accumulation and their relationship with aging.
Subject(s)
Mental Health , Multimorbidity , Humans , United States , Aging , Brain/diagnostic imaging , Biomarkers , Chronic DiseaseABSTRACT
Graphical approach provides a useful framework for multiplicity adjustment in clinical trials with multiple endpoints. When designing a graphical approach, initial weight and transition probability for the endpoints are often assigned based on clinical importance. For example, practitioners may prefer putting more weights on some primary endpoints. The clinical preference can be formulated as a constrain in the sample size optimization problem. However, there has been a lack of theoretical guidance on how to specify initial weight and transition probability in a graphical approach to meet the clinical preference but at the same time to minimize the sample size needed for a power requirement. To fill this gap, we propose statistical methods to optimize sample size over initial weight and transition probability in a graphical approach under a common setting, which is to use marginal power for each endpoint in a trial design. Importantly, we prove that some of the commonly used graphical approaches such as putting all initial weights on one endpoint are suboptimal. Our methods are flexible, which can be used for both single-arm trials and randomized controlled trials with either continuous or binary or mixed types of endpoints. Additionally, we prove the existence of optimal solution where all marginal powers are placed exactly at the prespecified values, assuming continuity. Two hypothetical clinical trial designs are presented to illustrate the application of our methods under different scenarios. Results are first presented for a design with two endpoints and are further generalized to three or more endpoints. Our findings are helpful to guide the design of a graphical approach and the sample size calculation in clinical trials.
Subject(s)
Clinical Trials as Topic , Research Design , Humans , Probability , Sample SizeABSTRACT
There are various multiple comparison procedures used in confirmatory clinical studies and exploratory research for multiplicity adjustment. Among them are the Hochberg and Benjamini-Hochberg procedures. A common misconception is that these procedures control the type I error rate properly if the test statistics are independent or positively correlated. In fact, a much stronger positive dependence assumption needs to be satisfied to guarantee the type I error rate control. We give a comprehensive review of the dependence conditions used in multiple testing procedures. We show that a weaker positive dependence assumption may result an inflation of type I error rate by a factor of 2 and discuss the type I error rate control under certain negative dependence conditions.
Subject(s)
Research DesignABSTRACT
Machine learning (ML) has been extensively applied in brain imaging studies to aid the diagnosis of psychiatric disorders and the selection of potential biomarkers. Due to the high dimensionality of imaging data and heterogeneous subtypes of psychiatric disorders, the reproducibility of ML results in brain imaging studies has drawn increasing attention. The reproducibility in brain imaging has been primarily examined in terms of prediction accuracy. However, achieving high prediction accuracy and discovering relevant features are two separate but related goals. An important yet under-investigated problem is the reproducibility of feature selection in brain imaging studies. We propose a new metric to quantify the reproducibility of neuroimaging feature selection via bootstrapping. We estimate the reproducibility index (R-index) for each feature as the reciprocal coefficient of variation of absolute mean difference across a larger number of bootstrap samples. We then integrate the R-index in regularized classification models as penalty weight. Reproducible features with a larger R-index are assigned smaller penalty weights and thus are more likely to be selected by our proposed models. Both simulated and multimodal neuroimaging data are used to examine the performance of our proposed models. Results show that our proposed R-index models are effective in separating informative features from noise features. Additionally, the proposed models yield similar or higher prediction accuracy than the standard regularized classification models while further reducing coefficient estimation error. Improvements achieved by the proposed models are essential to advance our understanding of the selected brain imaging features as well as their associations with psychiatric disorders.
Subject(s)
Machine Learning , Neuroimaging , Humans , Reproducibility of Results , Brain/diagnostic imaging , Biomarkers , Magnetic Resonance Imaging , AlgorithmsABSTRACT
We consider multistage tests of multiple hypotheses under a flexible setting of calendar time and information fraction, focusing on the case where there are two hypotheses under testing. Explicit expressions of statistical powers are derived. With a proof of existence and uniqueness of solution, we develop a numerical method to search the optimal sample size. The proposed method allows us to find the suitable allocation of initial significance level along with the minimum sample size for group sequential designs, with and without hierarchical structures among different endpoints.
Subject(s)
Research Design , Sample SizeABSTRACT
The problem of testing multiple hypotheses using a group sequential procedure often arises in clinical trials. We review several group sequential Holm (GSHM) type procedures proposed in the literature and clarify the relationships between them. In particular, we show which procedures are equivalent or, if different, which are more powerful and what are their pros and cons. We propose a step-up group sequential Hochberg (GSHC) procedure as a reverse application of a particular step-down GSHM procedure. We conducted an extensive simulation study to evaluate the familywise error rate (FWER) and power properties of that GSHM procedure and the GSHC procedure and found that the GSHC procedure controls FWER more closely and is more powerful. All procedures are illustrated with a common numerical example, the data for which are chosen to bring out the differences between them. A real case study is also presented to illustrate application of these procedures. R programs for applying the proposed procedures, additional simulation results, and the proof of the FWER control of the GSHC procedure in a special case are provided in Supplementary Material.
Subject(s)
Clinical Trials as Topic , Computer SimulationABSTRACT
[This corrects the article DOI: 10.3389/fonc.2018.00652.].
ABSTRACT
Along the pathway from behavioral symptoms to the development of psychotic disorders sits the multivariate mediating brain. The functional organization and structural topography of large-scale multivariate neural mediators among patients with brain disorders, however, are not well understood. Here, we design a high-dimensional brain-wide functional mediation framework to investigate brain regions that intermediate between baseline behavioral symptoms and future conversion to full psychosis among individuals at clinical high risk (CHR). Using resting-state functional magnetic resonance imaging (fMRI) data from 263 CHR subjects, we extract an α brain atlas and a ß brain atlas: the former underlines brain areas associated with prodromal symptoms and the latter highlights brain areas associated with disease onset. In parallel, we identify and separate mediators that potentially positively and negatively mediate symptoms and psychosis, respectively, and quantify the effect of each neural mediator on disease development. Taken together, these results paint a brain-wide picture of neural markers that are potentially mediating behavioral symptoms and the development of psychotic disorders; additionally, they underscore a statistical framework that is useful to uncover large-scale intermediating variables in a regulatory biological system.
Subject(s)
Behavioral Symptoms/diagnostic imaging , Brain/diagnostic imaging , Brain/physiopathology , Prodromal Symptoms , Psychotic Disorders/diagnostic imaging , Behavioral Symptoms/physiopathology , Brain Mapping/methods , Female , Humans , Image Interpretation, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Male , Mediation Analysis , Psychotic Disorders/physiopathology , Young AdultABSTRACT
BACKGROUND: Patient engagement is increasing in the presence of digital patient assessment platforms, or physician rating websites. Despite this rapid growth, data remains insufficient regarding how these evaluations impact radiation oncologists. OBJECTIVES: The purpose of this study was to assess radiation oncologists worldwide on their awareness and noted effects of digital patient assessment platforms. METHODS: An electronic survey was delivered to 6,199 members of the American Society of Radiation Oncology. Subjects were radiation oncologists practicing throughout the world. The survey consisted of 14 questions focused on demographics, practice details, patient volume, institutional utilization of patient reviews, and perceptions of radiation oncologists on health care reviews provided by patients. RESULTS: There were 447 responses from practicing radiation oncologists in total, 321 (72%) of which are in the US. Most respondents (228; 51%) either agreed or strongly agreed that patients consider online reviews when deciding which physician to visit. Of all respondents, 188 (42%) reported that their institution checks their online feedback, whereas 157 (36%) and 99 (22%) respectively reported not knowing, or to their knowledge their institution does not check their online feedback. Respondents who saw more than the average number of consults per week were significantly more likely to receive negative feedback (P = 0.005). Forty-five percent of respondents agreed or strongly agreed that online virtual assessment tools contribute to physician burnout. Respondents (100; 22%) who received inappropriate or misdirected feedback were significantly more likely to report that virtual reviews contribute to burnout (P = 0.001). CONCLUSIONS: Radiation oncologists need to be aware that self-reported patient assessments are a data point in the quality of a physician and health care establishment. To best ensure appropriate feedback of a physician's capabilities as a doctor, leadership and employee alignment for patient experience are now more important than ever.
ABSTRACT
BACKGROUND: Tracheal dryness is a concern after total laryngectomy due to the potential for mucus plugs (MP). This study compared heat and moisture exchanger (HME) cassettes to external tracheal humidification (ETH) surrounding MP events. METHODS: A retrospective comparative cohort study comparing outcomes before/after implementation of a patient safety initiative utilizing HME during post laryngectomy hospitalization. The number of MP events were compared with a pre-implementation control group using ETH. Patient characteristics were analyzed for correlation with MP. RESULTS: The rate of MP was significantly lower in the HME group than ETH (0.13 and 0.38 per 10 inpatient days, respectively, P = .02). The proportion of patients with one or more MP events was also significantly reduced in the HME group (50% ETH and 11% HME, P = .01). Method of humidification was the only significant variable associated with MP on logistic regression modeling (P = .008). CONCLUSIONS: HMEs were superior to ETH for prevention of MP.
Subject(s)
Hot Temperature , Laryngectomy , Cohort Studies , Humans , Humidity , Mucus , Retrospective StudiesABSTRACT
The human brain is a dynamic system, where communication between spatially distinct areas facilitates complex cognitive functions and behaviors. How information transfers between brain regions and how it gives rise to human cognition, however, are unclear. In this article, using resting-state functional magnetic resonance imaging (fMRI) data from 783 healthy adults in the Human Connectome Project (HCP) dataset, we map the brain's directed information flow architecture through a Granger-Geweke causality prism. We demonstrate that the information flow profiles in the general population primarily involve local exchanges within specialized functional systems, long-distance exchanges from the dorsal brain to the ventral brain, and top-down exchanges from the higher-order systems to the primary systems. Using an information flow map discovered from 550 subjects, the individual directed information flow profiles can significantly predict cognitive flexibility scores in 233 novel individuals. Our results provide evidence for directed information network architecture in the cerebral cortex, and suggest that features of the information flow configuration during rest underpin cognitive ability in humans.
Subject(s)
Brain/diagnostic imaging , Brain/physiology , Cognition/physiology , Adult , Connectome , Female , Humans , Magnetic Resonance Imaging , Male , Models, Neurological , Models, Psychological , Rest , Signal Processing, Computer-Assisted , Young AdultABSTRACT
INTRODUCTION: Many human breast cancers overexpress the E3 ubiquitin ligase MDM2 and its homolog MDMX. Expression of MDM2 and MDMX occurs in estrogen receptor α-positive (ERα+) breast cancer and triple-negative breast cancer (TNBC). There are p53-independent influences of MDM2 and MDMX, and 80% of TNBC express mutant p53 (mtp53). MDM2 drives TNBC circulating tumor cells (CTCs) in mice, but the context-dependent influences of MDM2 and MDMX on different subtypes of breast cancers expressing mtp53 have not been determined. METHODS: To assess the context-dependent roles, we carried out MDM2 and MDMX knockdown in orthotopic tumors of TNBC MDA-MB-231 cells expressing mtp53 R280K and MDM2 knockdown in ERα+ T47D cells expressing mtp53 L194F. The corresponding cell proliferation was scored in vitro by growth curves and in vivo by orthotopic tumor volumes. Cell migration was assessed in vitro by wound-healing assays and cell intravasation in vivo by sorting GFP-positive CTCs by flow cytometry. The metastasis gene targets were determined by an RT-PCR array card screen and verified by qRT-PCR and Western blot analysis. RESULTS: Knocking down MDMX or MDM2 in MDA-MB-231 cells reduced cell migration and CTC detection, but only MDMX knockdown reduced tumor volumes at early time points. This is the first report of MDMX overexpression in TNBC enhancing the CTC phenotype with correlated upregulation of CXCR4. Experiments were carried out to compare MDM2-knockdown outcomes in nonmetastatic ERα+ T47D cells. The knockdown of MDM2 in ERα+ T47D orthotopic tumors decreased primary tumor volumes, supporting our previous finding that estrogen-activated MDM2 increases cell proliferation. CONCLUSIONS: This is the first report showing that the expression of MDM2 in ERα+ breast cancer and TNBC can result in different tumor-promoting outcomes. Both MDMX and MDM2 overexpression in TNBC MDA-MB-231 cells enhanced the CTC phenotype. These data indicate that both MDM2 and MDMX can promote TNBC metastasis and that it is important to consider the context-dependent roles of MDM2 family members in different subtypes of breast cancer.
Subject(s)
Gene Expression Regulation, Neoplastic , Neoplastic Cells, Circulating/pathology , Nuclear Proteins/metabolism , Proto-Oncogene Proteins c-mdm2/metabolism , Proto-Oncogene Proteins/metabolism , Triple Negative Breast Neoplasms/pathology , Animals , Cell Cycle Proteins , Cell Line, Tumor , Cell Proliferation/genetics , Cyclooxygenase 2/metabolism , Estrogen Receptor alpha/metabolism , Female , Gene Knockdown Techniques , Humans , Mutation , Nuclear Proteins/genetics , Proto-Oncogene Proteins/genetics , Proto-Oncogene Proteins c-mdm2/genetics , RNA, Small Interfering/metabolism , Receptors, CXCR4/metabolism , Triple Negative Breast Neoplasms/blood , Triple Negative Breast Neoplasms/genetics , Tumor Suppressor Protein p53/genetics , Up-Regulation , Xenograft Model Antitumor AssaysABSTRACT
BACKGROUND: Diet plays an important role in chronic disease, and the use of dietary pattern analysis has grown rapidly as a way of deconstructing the complexity of nutritional intake and its relation to health. Pattern analysis methods, such as principal component analysis (PCA), have been used to investigate various dimensions of diet. Existing analytic methods, however, do not fully utilize the predictive potential of dietary assessment data. In particular, these methods are often suboptimal at predicting clinically important variables. METHODS: We propose a new dietary pattern analysis method using the advanced LASSO (Least Absolute Shrinkage and Selection Operator) model to improve the prediction of disease-related risk factors. Despite the potential advantages of LASSO, this is the first time that the model has been adapted for dietary pattern analysis. Hence, the systematic evaluation of the LASSO model as applied to dietary data and health outcomes is highly innovative and novel. Using Food Frequency Questionnaire data from NHANES 2005-2006, we apply PCA and LASSO to identify dietary patterns related to cardiovascular disease risk factors in healthy US adults (n = 2609) after controlling for confounding variables (e.g., age and BMI). Both analyses account for the sampling weights. Model performance in terms of prediction accuracy is evaluated using an independent test set. RESULTS: PCA yields 10 principal components (PCs) that together account for 65% of the variation in the data set and represent distinct dietary patterns. These PCs are then used as predictors in a regression model to predict cardiovascular disease risk factors. We find that LASSO better predicts levels of triglycerides, LDL cholesterol, HDL cholesterol, and total cholesterol (adjusted R2 = 0.861, 0.899, 0.890, and 0.935 respectively) than does the traditional, linear-regression-based, dietary pattern analysis method (adjusted R2 = 0.163, 0.005, 0.235, and 0.024 respectively) when the latter is applied to components derived from PCA. CONCLUSIONS: The proposed method is shown to be an appropriate and promising statistical means of deriving dietary patterns predictive of cardiovascular disease risk. Future studies, involving different diseases and risk factors, will be necessary before LASSO's broader usefulness in nutritional epidemiology can be established.
Subject(s)
Body Mass Index , Cardiovascular Diseases/diagnosis , Diet , Lipids/blood , Nutrition Assessment , Nutrition Surveys/methods , Adult , Cardiovascular Diseases/blood , Female , Humans , Male , Middle Aged , Nutrition Surveys/statistics & numerical data , Principal Component Analysis , Risk Factors , Surveys and QuestionnairesABSTRACT
Background: Liquid biopsy (LB) captures dynamic genomic alterations (alts) across metastatic colorectal cancer (mCRC) therapy and may complement tissue biopsy (TB). We sought to describe the utility of LB and better understand mCRC biology during therapy. Methods: Thirty-three patients (pts) with mCRC underwent LB. We used permutation-based t-tests to assess associations between alts, and clinical variables and used Kendall's tau to measure correlations. Results: Of 33 pts, 15 were women; 22 had colon, and the rest rectal cancer. Pts received a median of two lines of therapy before LB. Nineteen pts had limited testing on TB (RAS/RAF/TP53/APC), 11 extended NGS, and 3 no TB. Maxpct and alts correlated with CEA (p < 0.001, respectively). In 3/5 pts with serial LB, CEA correlated with maxpct trend, and CT tumor burden. In 6 pts, mutant RAS was seen in LB and not TB; 5/6 had received anti-EGFR therapy prior to LB, suggesting RAS alts developed post-therapy. In two pts RAS-mutated by TB, no RAS alts were detected on LB; these pts had low disease burden on CT at time of LB that also did not reveal APC or TP53 alts. In six patients who were KRAS wt based on TB, post anti-EGFR LB revealed subclonal KRAS mutations, likely a treatment effect. The median number of alts was higher post anti-EGFR LB (n = 12) vs. anti-EGFR naïve LB (n = 22) (9.5 vs. 5.5, p = 0.059) but not statistically significant. More alts were also noted in post anti-EGFR therapy LB vs. KRAS wt anti-EGFR-naïve LB (n = 6) (9.5 vs. 5) among patients with KRAS wild-type tumors, although the difference was not significant (p = 0.182). Conclusions: LB across mCRC therapy detects driver mutations, monitors disease burden, and identifies sub-clonal alts that reflect drug resistance, tumor evolution, and heterogeneity. Interpretation of LB results is impacted by clinical context.
ABSTRACT
In this article we review recent advances in [Formula: see text]-value-based multiple test procedures (MTPs). We begin with a brief review of the basic tests of Bonferroni and Simes. Standard stepwise MTPs derived from them using the closure method of Marcus et al. (1976) are discussed next. They include the well-known MTPs of Holm (1979), Hochberg (1988) and Hommel (1988), and their extensions and improvements. This is followed by stepwise MTPs for a priori ordered hypotheses. Next we present gatekeeping MTPs (Dmitrienko and Tamhane, 2007) for hierarchically ordered families of hypotheses with logical relations among them. Finally, we give a brief review of the graphical approach (Bretz et al., 2009) to constructing and visualizing gatekeeping and other MTPs. Simple numerical examples are given to illustrate the various procedures.
Subject(s)
Clinical Trials as Topic/statistics & numerical data , Data Interpretation, Statistical , Models, Statistical , Algorithms , HumansABSTRACT
Glimm et al. (2010) and Tamhane et al. (2010) studied the problem of testing a primary and a secondary endpoint, subject to a gatekeeping constraint, using a group sequential design (GSD) with K=2 looks. In this article, we greatly extend the previous results to multiple (K>2) looks. If the familywise error rate (FWER) is to be controlled at a preassigned α level then it is clear that the primary boundary must be of level α. We show under what conditions one α-level primary boundary is uniformly more powerful than another. Based on this result, we recommend the choice of the O'Brien and Fleming (1979) boundary over the Pocock (1977) boundary for the primary endpoint. For the secondary endpoint the choice of the boundary is more complicated since under certain conditions the secondary boundary can be refined to have a nominal level α'>α, while still controlling the FWER at level α, thus boosting the secondary power. We carry out secondary power comparisons via simulation between different choices of primary-secondary boundary combinations. The methodology is applied to the data from the RALES study (Pitt et al., 1999; Wittes et al., 2001). An R library package gsrsb to implement the proposed methodology is made available on CRAN.