Tutorial on Biostatistics: Sample Size and Power Calculation for Ophthalmic Studies With Correlated Binary Eye Outcomes.

Purpose: To describe and demonstrate sample size and power calculation for ophthalmic studies with a binary outcome from one or both eyes. Methods: We describe sample size and power calculation for four commonly used eye designs: (1) one-eye design or person-design: one eye per subject or outcome is at person-level; (2) paired design: two eyes per subject and two eyes are in different treatment groups; (3) two-eye design: two eyes per subject and both eyes are in the same treatment group; and (4) mixture design: mixture of one eye and two eyes per subject. For each design, we demonstrate sample size and power calculations in real ophthalmic studies. Results: Using formulas and commercial or free statistical packages including SAS, STATA, R, and PS, we calculated sample size and power. We demonstrated that different statistical packages require different parameters and provide similar, yet not identical, results. We emphasize that studies using data from two eyes of a subject need to account for the intereye correlation for appropriate sample size and power calculations. We demonstrate the gain in efficiency in designs that include two eyes of a subject compared to one-eye designs. Conclusions: Ophthalmic studies use different eye designs that include one or both eyes in the same or different treatment groups. Appropriate sample size and power calculations depend on the eye design and should account for intereye correlation when two eyes from some or all subjects are included in a study. Calculations can be executed using formulas and commercial or free statistical packages.

Wakefield's Harm-Based Critique of the Biostatistical Theory.

Jerome Wakefield criticizes my biostatistical analysis of the pathological-as statistically subnormal biological part-functional ability relative to species, sex, and age-for its lack of a harm clause. He first charges me with ignoring two general distinctions: biological versus medical pathology, and disease of a part versus disease of a whole organism. He then offers 10 counterexamples that, he says, are harmless dysfunctions but not medical disorders. Wakefield ends by arguing that we need a harm clause to explain American psychiatry's 1973 decision to declassify homosexuality. I reply, first, that his two distinctions are philosophic fantasies alien to medical usage, invented only to save his own harmful-dysfunction analysis (HDA) from a host of obvious counterexamples. In any case, they do not coincide with the harmless/harmful distinction. In reality, medicine admits countless chronic diseases that are, contrary to Wakefield, subclinical for most of their course, as well as many kinds of typically harmless skin pathology. As for his 10 counterexamples, no medical source he cites describes them as he does. I argue that none of his examples contradicts the biostatistical analysis: all either are not part-dysfunctions (situs inversus, incompetent sperm, normal-flora infection) or are indeed classified as medical disorders (donated kidney, Typhoid Mary's carrier status, latent tuberculosis or HIV, cherry angiomas). And if Wakefield's HDA fits psychiatry, the fact that it does not fit medicine casts doubt on psychiatry's status as a medical specialty.

Bayesian joint modeling of multivariate longitudinal and survival outcomes using Gaussian copulas.

There is an increasing interest in the use of joint models for the analysis of longitudinal and survival data. While random effects models have been extensively studied, these models can be hard to implement and the fixed effect regression parameters must be interpreted conditional on the random effects. Copulas provide a useful alternative framework for joint modeling. One advantage of using copulas is that practitioners can directly specify marginal models for the outcomes of interest. We develop a joint model using a Gaussian copula to characterize the association between multivariate longitudinal and survival outcomes. Rather than using an unstructured correlation matrix in the copula model to characterize dependence structure as is common, we propose a novel decomposition that allows practitioners to impose structure (e.g., auto-regressive) which provides efficiency gains in small to moderate sample sizes and reduces computational complexity. We develop a Markov chain Monte Carlo model fitting procedure for estimation. We illustrate the method's value using a simulation study and present a real data analysis of longitudinal quality of life and disease-free survival data from an International Breast Cancer Study Group trial.

Fundamento y generalidades de la construcción de modelos estadísticos multinivel en el ámbito de la investigación en salud / Construction of multilevel statistical models in health research: Foundations and generalities

Este trabajo tiene como objetivo presentar una mirada global de la aplicabilidad de los modelos de análisis multinivel en el ámbito de la investigación sanitaria. Ofrece información sobre los fundamentos teóricos, metodológicos y estadísticos y, además, menciona los pasos básicos para la construcción de estos modelos, y da ejemplos de su uso, según la estructura jerárquica de los datos. Cabe resaltar que, antes de utilizar estos modelos, se requiere contar con un soporte teórico sobre la necesidad de uso y una valoración estadística que dé cuenta del porcentaje de varianza explicada por el efecto de agrupación de las observaciones. Los requisitos para llevar a cabo este tipo de análisis dependen de condiciones especiales como el tipo de variables, la cantidad de unidades por nivel o el tipo de estructura jerárquica. Se concluye que los modelos de análisis multinivel son una herramienta útil para lograr la integración de información, dadas la complejidad de las relaciones y las interacciones que determinan la mayoría de las condiciones de salud, incluida la pérdida de independencia entre las unidades de observación.

This topic review aims to present a global vision of multilevel analysis models' applicability to health research, explaining its theoretical, methodological, and statistical foundations. We describe the basic steps to build these models and examples of their application according to the data hierarchical structure. It ir worth noticing that before using these models, researchers must have a rationale for needing them, and a statistical evaluation accounting for the variance percentage explained by the observations grouping effect. The requirements to conduct this type of analysis depends on special conditions such as the type of variables, the number of units per level, or the type of hierarchical structure. We conclude that multilevel analysis models are a useful tool to integrate information, considering the complexity of the relationships and interactions involved in most health conditions, including the loss of independence between observation units.

Aplicación móvil para el análisis estadístico en Android / Mobile application for statistics analysis on Android

El uso de dispositivos móviles en la vida moderna es imprescindible debido a las ventajas que brindan al ofrecer nuevas posibilidades e implementar de manera virtual servicios ya establecidos. La mayor existencia de móviles que computadoras en los estudiantes de Cuba nos motivó a la realización de esta aplicación. El objetivo de este artículo es describir la aplicación nombrada Cálculos estadísticos y tasas en salud (Calc. Tasas versión 1.7) construida para realizar cálculos en un curso de Bioestadística, cubriendo gran parte del contenido de esta asignatura en la enseñanza de pregrado de las universidades médicas, así como otros contenidos de interés en esta materia. También incorpora una base de datos con información demográfica y sanitaria de Cuba y sus provincias en el período 2013-2020. Como resultado se logró independencia tecnológica al dejar de usar programas foráneos y se logró una mayor portabilidad pues funciona tanto en móviles como en computadoras utilizando un emulador de Android(AU)

The use of mobile devices in modern life is essential due to the advantages they provide, offering new possibilities and implementing virtual services. The existence of greater number of mobiles phones than computers in Cuban students motivated the realization of this application. The objective of the article is to describe the application Statistical calculations and rates in health (Calc. Rates version 1.7) built to perform calculations in a Biostatistics course, covering a large part of the content of this subject in the undergraduate teaching of medical universities, as well as other content related with this topic. It also incorporates a database with demographic and health information on Cuba and its provinces in the period 2013-2020. As a result, technological independence was achieved by stopping using foreign programs and a greater portability, since it works on both mobile phones and computers through an Android emulator(AU)

Propuesta metodológica para la validación de bases de datos aplicada a las ciencias de la salud / Methodological proposal for validation of databases applied to health sciences

La estadística es uno de los pilares de la ciencia, especialmente para describir y analizar los datos, la que ha progresado exponencialmente en los últimos años. Se le debe entender como un apoyo fundamental para la toma de decisiones en las distintas disciplinas. Los análisis exploratorios son descritos como el primer paso en la estadística, buscando organizar, representar y describir los datos, pero muchas veces este proceso se vuelve complejo, siendo importante realizar una revisión exhaustiva de la matriz de datos. Es objetivo de este manuscrito describir una propuesta metodológica para la validación de bases de datos aplicada a las ciencias de la salud. Esta metodología consta de seis etapas: cuatro de ellas obligatorias y sucesivas, y las otras dos opcionales. En la literatura médica, estos procedimientos general-mente son pasados por alto; buscamos, en consecuencia, recalcar la importancia de este proceso como previo a los análisis exploratorios.

Statistics is one of the pillars of science, especially to describe and analyze data, it has progressed exponentially in recent years. Being the fundamental support for decision-making in different disciplines. Exploratory analyzes are described as the first step in statistics, seeking to organize, represent and describe the data, but many times this process becomes complex, and it is important to carry out an exhaustive review of the data matrix. The aim of this manuscript was to describe a methodological proposal for databases validation applied to health sciences. This methodology consists of 6 stages, 4 of them compulsory and successive, and the other two, optional. In the literature these procedures are generally overlooked, our purpose is thus to emphasize the importance of this process prior to exploratory analyzes.

Uso de Moodle para la formación de especialistas en Bioestadística en tiempos de COVID-19 / Usage of Moodle for training Biostatistics Specialists during COVID-19 times

Introducción: La Escuela Nacional de Salud Pública es el centro coordinador y rector de la formación de especialistas en Bioestadística del país. A partir de la emergencia generada por la COVID-19, el proceso formativo de esta especialidad se vio interrumpido. La educación a distancia a través de entornos de enseñanza-aprendizaje resultó la única opción posible para reanudar el proceso. Objetivo: Exponer la experiencia de uso de Moodle en la formación de especialistas en Bioestadística a partir de la epidemia de COVID-19. Métodos: Estudio de caso descriptivo, realizado entre septiembre de 2020 y febrero de 2021. El universo de estudio estuvo constituido por los dos estudiantes matriculados en el primer año del curso académico 2020-2021. Se aplicó una encuesta estructurada a los alumnos sobre aspectos del curso 1 y 2 del programa y se realizó consulta a expertos para la evaluación. Resultados: Se identificaron las carencias para reorientar el proceso. La selección de las actividades prácticas y evaluativas estuvo guiada por el análisis de los objetivos temáticos y la naturaleza de los contenidos. La evaluación de los resultados y el análisis de la encuesta permitió conocer en profundidad aspectos a perfeccionar en futuras ediciones. Conclusiones: El estudio evidenció que la modalidad virtual constituía una vía factible para la formación de posgrado en salud, particularmente durante la COVID-19. Con el análisis de las cuatro condiciones contempladas para los sistemas de instrucción se reconoció la importancia de la etapa de planificación previa y su perfeccionamiento para alcanzar mejores resultados(AU)

Introduction: The National School of Public Health is the center that coordinates and guides the training of Biostatistics specialists in Cuba. Since the emergency caused by COVID-19, the training process of this specialty was interrupted. Distance education through teaching-learning environments was the only possible option to resume the process. Objective: To expose the experience of using Moodle in the training of Biostatistics specialists during the COVID-19 epidemic. Methods: Descriptive case study carried out between September 2020 and February 2021. The study universe consisted of the two first-year students enrolled for the 2020-2021 academic year. A structured survey was applied to the students regarding aspects of the first two courses the program; expert consultation was carried out for the evaluation. Results: Shortcomings were identified as affecting the reorientation of the process. The selection of practical and evaluative activities was guided by the analysis of the thematic objectives and the nature of the contents. The assessment of the results and the analysis of the survey provided in-depth knowledge of aspects to be improved in future editions. Conclusions: The study evidenced that the virtual modality was a feasible way for postgraduate training in health, particularly during the COVID-19. With the analysis of the four conditions that should be present in instructional systems, the pre-planning stage and its improvement was recognized as important to achieve better results(AU)

Understanding the literature: Complexity of statistical methods used in high-impact cardiothoracic surgery research.

OBJECTIVE: Biostatistics are frequently used in research published in the domain of cardiothoracic surgery. The objective of this study was to describe the scope of statistical techniques reported in the literature and to highlight implications for editorial review and critical appraisal. METHODS: Original research articles published between January and April 2017 in the Journal of Thoracic and Cardiovascular Surgery, Annals of Thoracic Surgery, and the European Journal of Cardio-Thoracic Surgery were examined. For each article, the statistical method(s) reported were recorded and categorized by complexity. RESULTS: We reviewed 293 articles that reported 1068 statistical methods. The mean number of different statistical methods reported per article was 3.6 ± 1.9, with variation by subspecialty and journal. The most common statistical methods were contingency tables (in 59% of articles), t tests (49%), and survival methods (49%). Only 4% of articles used descriptive statistics alone. An introductory level of statistical knowledge was deemed sufficient for understanding 16% of articles, whereas for the remainder a higher level of knowledge would be needed. CONCLUSIONS: Contemporary cardiothoracic surgery research frequently requires the use of complex statistical methods. This was evident across articles for all cardiothoracic surgical subspecialties as reported in 3 high-impact journals. Routine review of manuscript submissions by biostatisticians is needed to ensure the appropriate use and reporting of advanced statistical methods in cardiothoracic surgery research.

Nivel y accesibilidad estadística en artículos originales publicados en una revista de pediatría / Statistical level and accessibility in original articles published in a pediatric journal

Describir las herramientas estadísticas las herramientas estadísticas empleadas para la presentación de resultados de investigación en los artículos publicados en la revista Archivos Argentinos de Pediatría a fin de evaluar el nivel y accesibilidad de aquéllas. Estudio observacional, descriptivo y retrospectivo. Se analizaron las publicaciones del período 2015-2019. Aplicando la escala de Mora Ripoll adaptada por Praena Fernández, fueron revisados 236 trabajos que cumplieron con los criterios de inclusión en la sección Artículos originales de la revista Archivos Argentinos de Pediatría. El 14,4% de los artículos correspondió al nivel I, 22,9% al nivel II y 62,7% al nivel III. Así, un lector cuyo repertorio de conocimientos estadísticos equivaliera al nivel I accedería al 14,4% de los artículos mientras que quien contara con un nivel II elevaría la accesibilidad al 37,3%. Del análisis de los artículos originales publicados en los AAP, resulta evidente que quien desee realizar un análisis crítico de la totalidad de los hallazgos presentados en la revista, deberá contar con un apropiado nivel de conocimiento que, lamentablemente, no suele alcanzarse en la carrera de grado de Medicina.

Describes the statistical tools used to present research results in articles published in the Argentine Archives of Pediatrics to assess their level and accessibility. Observational, descriptive and retrospective study. Publications for the period 2015-2019 were analyzed. Applying the Mora Ripoll scale, adapted by Praena Fernández, 236 papers satisfying the inclusion criteria were reviewed in its original articles section. 14.4% of the articles corresponded to level I, 22.9% to level II and 62.7% to level III. Thus, a reader whose repertoire of statistical knowledge equals level I would access 14.4% of the articles, while a reader with a level II would increase accessibility to 37.3%. From the analysis of the original articles published in the AAP, it is evident that anyone who wishes to carry out a critical analysis of all the findings presented in the journal, must have an appropriate level of knowledge that, unfortunately, it is not usually achieved in the undergraduate degree of Medicine.

Rank normalization empowers a t-test for microbiome differential abundance analysis while controlling for false discoveries.

A major task in the analysis of microbiome data is to identify microbes associated with differing biological conditions. Before conducting analysis, raw data must first be adjusted so that counts from different samples are comparable. A typical approach is to estimate normalization factors by which all counts in a sample are multiplied or divided. However, the inherent variation associated with estimation of normalization factors are often not accounted for in subsequent analysis, leading to a loss of precision. Rank normalization is a nonparametric alternative to the estimation of normalization factors in which each count for a microbial feature is replaced by its intrasample rank. Although rank normalization has been successfully applied to microarray analysis in the past, it has yet to be explored for microbiome data, which is characterized by high frequencies of 0s, strongly correlated features and compositionality. We propose to use rank normalization as an alternative to the estimation of normalization factors and examine its performance when paired with a two-sample t-test. On a rigorous 3rd-party benchmarking simulation, it is shown to offer strong control over the false discovery rate, and at sample sizes greater than 50 per treatment group, to offer an improvement in performance over commonly used normalization factors paired with t-tests, Wilcoxon rank-sum tests and methodologies implemented by R packages. On two real datasets, it yielded valid and reproducible results that were strongly in agreement with the original findings and the existing literature, further demonstrating its robustness and future potential. Availability: The data underlying this article are available online along with R code and supplementary materials at https://github.com/matthewlouisdavisBioStat/Rank-Normalization-Empowers-a-T-Test.

Binary Classification for Failure Risk Assessment.

Survival analysis is tremendously powerful, and is a popular methodology for analyzing time to event models in bioinformatics. Furthermore, several of its extensions can simultaneously perform variable selection in conjunction with model estimation. While this flexibility is extremely desirable, under certain scenarios, binary class variable selection and classification methods might provide more reliable risk estimates. Synthetic simulations and real data case studies suggest that when (1) randomly censored points comprise only a small portion of data, (2) biological markers are weak, (3) it is desired to compute risk across predetermined time intervals, and (4) the assumptions of the competing time to event models are violated, binary class models tend to perform superior. In practice, it might be prudent to test both model families to guarantee adequate analysis. Here we describe the pipeline of binary class feature selection and classification for time to event risk assessment.

Managing a Large-Scale Multiomics Project: A Team Science Case Study in Proteogenomics.

Highly collaborative scientists are often called on to extend their expertise to different types of projects and to expand the scope and scale of projects well beyond their previous experience. For a large-scale project involving "big data" to be successful, several different aspects of the research plan need to be developed and tested, which include but are not limited to the experimental design, sample collection, sample preparation, metadata recording, technical capability, data acquisition, approaches for data analysis, methods for integration of different data types, recruitment of additional expertise as needed to guide the project, and strategies for clear communication throughout the project. To capture this process, we describe an example project in proteogenomics that built on our collective expertise and experience. Key steps included definition of hypotheses, identification of an appropriate clinical cohort, pilot projects to assess feasibility, refinement of experimental designs, and extensive discussions involving the research team throughout the process. The goal of this chapter is to provide the reader with a set of guidelines to support development of other large-scale multiomics projects.

Tradução, adaptação cultural e validação da Sickle Cell Self-efficacy Scale (SCSES) / Translation, Cultural Adaption and Validation of the Sickle Cell Self-Efficacy Scale (SCSES)

A validação de instrumentos específicos em doença falciforme são uma importante estratégia em saúde e, podem subsidiar e avaliar práticas e intervenções educativas que tem o intuito de melhorar a autoeficácia e habilidades no manejo da doença. Objetivo: Realizar a tradução, adaptação e validação do instrumento The Sickle Cell Self-Efficacy Scale (SCSES) para aplicação no contexto cultural brasileiro. Métodos: Trata-se de um estudo metodológico realizado em 6 etapas: 1- Tradução inicial; 2- Síntese da tradução; 3- Retrotradução (back-translation); 4- Avaliação pelo comitê de juízes, com cálculo de Índice de Validade de Conteúdo (IVC); 5- Adequação cultural (pré-teste); 6- Reprodutibilidade. A etapa de tradução foi realizada em parceria com o Laboratório Experimental de Tradução da Faculdade de Letras e o Laboratório de Bioestatística da UFMG. Na etapa de adaptação cultural, as versões original e traduzida foram submetidas à análise por um Comitê de Juízes composto por cinco profissionais da área de saúde. A partir da avaliação obtida foi calculado o Índice de Validade de Conteúdo (IVC) e a porcentagem de aceitação dos juízes em relação à adequação dos itens avaliados. Com o objetivo de avaliar a confiabilidade do instrumento adaptado culturalmente, este foi aplicado no pré-teste com a participação de um total de 10 adolescentes e jovens adultos com doença falciforme através de ligação telefônica e as respostas obtidas foram registradas na plataforma web e-Surv. Após realização do pré-teste, foi realizada a validação do instrumento com 55 adolescentes e jovens adultos com doença falciforme e destes, 43 participaram do reteste. O intervalo médio entre as aplicações foi de 17 dias. As análises da consistência interna e reprodutibilidade calculadas através do coeficiente alfa de Cronbach e pelo Coeficiente de Correlação Intraclasse (ICC) foram realizadas no ambiente de programação estatística R. Resultados: O instrumento traduzido apresentou boa aceitação entre os juízes, atingindo Índice de Validade de Conteúdo médio igual a 1,0. Na avaliação da confiabilidade, a escala apresentou consistência interna aceitável, com alfa de Cronbach igual a 0,84. Na análise de concordância, o coeficiente de correlação intraclasse foi de 0,923 (IC 95%: 0.857 a 0.958), o que indica boa reprodutibilidade temporal. Conclusões: O processo de tradução, adaptação cultural e validação gerou a versão brasileira da Escala de Autoeficácia em Doença Falciforme (EADF) considerada válida e confiável para ser aplicada em adolescentes e jovens adultos com doença falciforme.

The validation of specific instruments in sickle cell disease is an important health strategy that can support and evaluate educational practices and interventions aimed at improving self-efficacy and skills in disease management. Objective: To translate, adapt and validate The Sickle Cell Self-Efficacy Scale (SCSES) for application in the Brazilian cultural context. Methods: This is a methodological study carried out in 6 stages: 1- Initial translation; 2- Translation synthesis; 3- Back-translation; 4- Evaluation by the judges committee, with calculation of the Content Validity Index (CVI); 5- Cultural adequacy (pre-test); 6- Reproducibility. The translation stage was carried out in partnership with the Experimental Translation Laboratory of the School of Languages and the Biostatistics Laboratory of UFMG. In the cultural adaptation stage, the original and translated versions were submitted to analysis by a Committee of Judges composed of five health professionals. From the evaluation obtained the Content Validity Index (CVI) and the percentage of acceptance of the judges in relation to the adequacy of the items evaluated were calculated. Aiming to assess the reliability of the culturally adapted instrument, it was applied in pre-test with the participation of a total of 10 adolescents and young adults with sickle cell disease by telephone call and the responses obtained were recorded on the web platform e-Surv. After the pre-test, the instrument was validated with 55 adolescents and young adults with sickle cell disease, and of these, 43 participated in the retest. The average interval between applications was 17 days. The analyses of internal consistency and reproducibility calculated through Cronbach's alpha coefficient and the Intraclass Correlation Coefficient (ICC) were performed in the R statistical programming environment. Results: The translated instrument presented good acceptance among the judges, reaching an average Content Validity Index equal to 1.0. In assessing reliability, the scale showed acceptable internal consistency, with Cronbach's alpha equal to 0.84. In the agreement analysis, the intraclass correlation coefficient was 0.923 (95% CI: 0.857 to 0.958), indicating good temporal reproducibility. Conclusions: The process of translation, cultural adaptation and validation generated the Brazilian version of the Sickle Cell Self-Efficacy Scale (SES) considered valid and reliable to be applied in adolescents and young adults with sickle cell disease.

Introdução à inferência causal em epidemiologia: uma abordagem gráfica e contrafatual / Introduction to causal inference in epidemiology: a graphic and counterfactual approach

Apresenta o desenvolvimento mais recente dos métodos de inferência causal utilizados em epidemiologia, em especial as abordagens contrafatual e gráfica, abordando temas como modelo de respostas potenciais para estimativas de efeitos causais via escore de propensão, gráficos acíclicos direcionados, computação G e análise de sensibilidade

Revisiones rápidas: definiciones y usos / Rapid reviews: definitions and uses

Este artículo es el primero de una serie metodológica colaborativa de revisiones narrativas sobre temáticas de bioestadística y epidemiología clínica. El objetivo de esta revisión es presentar las revisiones rápidas, compararlas con las revisiones sistemáticas y mencionar su uso actual. Las revisiones rápidas utilizan una metodología similar a las revisiones sistemáticas, pero mediante atajos utilizados en su desarrollo; permiten alcanzar respuestas en menos de seis meses y con menos recursos, por lo que son utilizadas por tomadores de decisiones tanto en América como Europa. No existe consenso sobre cuáles atajos tienen menor impacto en la confiabilidad de las conclusiones, por lo que las revisiones rápidas son heterogéneas entre sí. Los consumidores deben identificar estos atajos en la metodología y ser precavidos en la interpretación de las conclusiones, aunque generalmente alcanzan respuestas concordantes con las obtenidas mediante una revisión sistemática tradicional. Su principal atractivo es ajustarse a las necesidades de los tomadores de decisiones en salud, cuando el contexto exige respuestas en plazos de tiempo acotados.

This article is the first in a collaborative methodological series of narrative reviews on biostatistics and clinical epidemiology. This review aims to present rapid reviews, compare them with systematic reviews, and mention how they can be used. Rapid reviews use a methodology like systematic reviews, but through shortcuts applied, they can attain answers in less than six months and with fewer resources. Decision-makers use them in both America and Europe. There is no consensus on which shortcuts have the least impact on the reliability of conclusions, so rapid reviews are heterogeneous. Users of rapid reviews should identify these shortcuts in the methodology and be cautious when interpreting the conclusions, although they generally reach answers concordant with those obtained through a formal systematic review. The principal value of rapid reviews is to respond to health decision-makers' needs when the context demands answers in limited time frames.