DMC reports in the 21st century: towards better tools for decision-making.

Data Monitoring Committees (DMCs) have the important task to protect the safety of current and future patients during the conduct of a clinical study. Unfortunately, their work is often made difficult by voluminous DMC reports that are poorly structured and difficult to digest. In this article, we suggest improved solutions. Starting from a principled approach and building upon previous proposals, we offer concrete and easily understood displays, including related computer code. While leveraging modern tools, the most important is that these displays support the DMC's workflow in answering the relevant questions of interest. We hope that the adoption of these proposals can ease the task of DMCs, and importantly, lead to better decision-making for the benefit of patients.

Learning and Predicting from Dynamic Models for COVID-19 Patient Monitoring.

COVID-19 has challenged health systems to learn how to learn. This paper describes the context, methods and challenges for learning to improve COVID-19 care at one academic health center. Challenges to learning include: (1) choosing a right clinical target; (2) designing methods for accurate predictions by borrowing strength from prior patients' experiences; (3) communicating the methodology to clinicians so they understand and trust it; (4) communicating the predictions to the patient at the moment of clinical decision; and (5) continuously evaluating and revising the methods so they adapt to changing patients and clinical demands. To illustrate these challenges, this paper contrasts two statistical modeling approaches - prospective longitudinal models in common use and retrospective analogues complementary in the COVID-19 context - for predicting future biomarker trajectories and major clinical events. The methods are applied to and validated on a cohort of 1,678 patients who were hospitalized with COVID-19 during the early months of the pandemic. We emphasize graphical tools to promote physician learning and inform clinical decision making.

Variation partitioning in double-constrained multivariate analyses: linking communities, environment, space, functional traits, and ecological niches.

Constrained multivariate analysis is a common tool for linking ecological communities to environment. The follow-up is the development of the double-constrained correspondence analysis (dc-CA), integrating traits as species-related predictors. Further, methods have been proposed to integrate information on phylogenetic relationships and space variability. We expand this framework, proposing a dc-CA-based algorithm for decomposing variation in community structure and testing the simple and conditional effects of four sets of predictors: environment characteristics and space configuration as predictors related to sites, while traits and niche (dis)similarities as species-related predictors. In our approach, ecological niches differ from traits in that the latter are distinguished by and characterize the individual level, while niches are measured on the species level, and when compared, they are characteristics of communities and should be used as separate predictors. The novelties of this approach are the introduction of new niche parameters, niche dissimilarities, synthetic niche-based diversity which we related to environmental features, the development of an algorithm for the full variation decomposition and testing of the community-environment-niche-traits-space (CENTS) space by dc-CAs with and without covariates, and new types of diagrams for the results. Applying these methods to a dataset on freshwater mollusks, we learned that niche predictors may be as important as traits in explaining community structure and are not redundant, overweighting the environmental and spatial predictors. Our algorithm opens new pathways for developing integrative methods linking life, environment, and other predictors, both in theoretical and practical applications, including assessment of human impact on habitats and ecological systems.

Cómo leer y generar publicaciones científicas: exploración gráfica de datos cuantitativos: la importancia de mirar la información / How to read and generate scientific publications: in this issue: graphical exploration of quantitative data: the importance of looking at the information

Once the collection of data from a study has been completed and the respective database is available, the researcher is often impatient to answer the research question and ventures into the final steps of the analysis. However, a key stage, prior to a more complex or sophisticated statistical analysis, is data exploration and descriptive statistics. Unfortunately, the exploratory analysis of the data is often performed without much dedication, or is simply "skipped", which can have important consequences on the results obtained and lead to the report of erroneous conclusions. On the one hand, exploration allows to detect errors in the data and, if possible, to correct them from the source of origin or take them into account to make decisions about what to do with them. On the other hand, exploration allows to know the behavior of the variables evaluated in terms of their distribution (key concept in Statistics) and possible relationships among them, which is essential for subsequent descriptive and inferential analysis. The objective of this article is to show graphic tools for the exploration of quantitative data, in order to visualize its distribution and compare groups according to categories of qualitative variables.

Una vez finalizada la recolección de datos de un estudio y contado con la respectiva base de datos, es frecuente que el investigador esté impaciente por responder a la pregunta de investigación y se aventure a realizar los pasos finales del análisis. No obstante, una etapa clave, previa a un análisis estadístico más complejo o sofisticado, es la exploración de datos y la estadística descriptiva. Lamentablemente, el análisis exploratorio de los datos muchas veces es realizado sin mucha dedicación, o simplemente es "saltado", lo que puede tener consecuencias importantes en los resultados obtenidos y conducir al reporte de conclusiones erróneas. Por un lado, la exploración permite detectar errores en los datos y, si es posible, corregirlos desde la fuente de origen o tenerlos en cuenta para tomar decisiones respecto a qué hacer con ellos. Por otra parte, la exploración permite conocer el comportamiento de las variables evaluadas en términos de su distribución (concepto clave en Estadística) y posibles relaciones entre ellas, lo cual es fundamental para los análisis descriptivo e inferencial posteriores. El objetivo de este artículo es mostrar herramientas gráficas para la exploración de datos cuantitativos, con el fin de visualizar su distribución y comparar grupos según categorías de variables cualitativas.

Visualization methods for differential expression analysis.

BACKGROUND: Despite the availability of many ready-made testing software, reliable detection of differentially expressed genes in RNA-seq data is not a trivial task. Even though the data collection is considered high-throughput, data analysis has intricacies that require careful human attention. Researchers should use modern data analysis techniques that incorporate visual feedback to verify the appropriateness of their models. While some RNA-seq packages provide static visualization tools, their capabilities should be expanded and their meaningfulness should be explicitly demonstrated to users. RESULTS: In this paper, we 1) introduce new interactive RNA-seq visualization tools, 2) compile a collection of examples that demonstrate to biologists why visualization should be an integral component of differential expression analysis. We use public RNA-seq datasets to show that our new visualization tools can detect normalization issues, differential expression designation problems, and common analysis errors. We also show that our new visualization tools can identify genes of interest in ways undetectable with models. Our R package "bigPint" includes the plotting tools introduced in this paper, many of which are unique additions to what is currently available. The "bigPint" website is located at https://lindsayrutter.github.io/bigPint and contains short vignette articles that introduce new users to our package, all written in reproducible code. CONCLUSIONS: We emphasize that interactive graphics should be an indispensable component of modern RNA-seq analysis, which is currently not the case. This paper and its corresponding software aim to persuade 1) users to slightly modify their differential expression analyses by incorporating statistical graphics into their usual analysis pipelines, 2) developers to create additional complex and interactive plotting methods for RNA-seq data, possibly using lessons learned from our open-source codes. We hope our work will serve a small part in upgrading the RNA-seq analysis world into one that more wholistically extracts biological information using both models and visuals.

How can we make better graphs? An initiative to increase the graphical expertise and productivity of quantitative scientists.

Graphics are at the core of exploring and understanding data, communicating results and conclusions, and supporting decision-making. Increasing our graphical expertise can significantly strengthen our impact as professional statisticians and quantitative scientists. In this article, we present a concerted effort to improve the way we create graphics at Novartis. We provide our vision and guiding principles, before describing seven work packages in more detail. The actions, principles, and experiences laid out in this paper are applicable generally, also beyond drug development, which is our field of work. The purpose of this article is to share our experiences and help foster the use of good graphs in pharmaceutical statistics and beyond. A Graphics Principles "Cheat Sheet" is available online at https://graphicsprinciples.github.io/.