Compreendendo os métodos de escore de propensão na pesquisa clínica / Understanding the methods of propensity score in clinical research

Os métodos de escore de propensão são a probabilidade de um sujeito receber um tratamento condicional em um conjunto de características de base (confundidores), sendo usado para comparar pacientes com distribuição similar de fatores de confusão, de modo que a diferença nos resultados forneça estimativa imparcial do efeito do tratamento. Esta revisão mostra os conceitos básicos dos escore de propensão e fornece orientação na implementação de métodos de propensão, além de outros, como estratificação, ponderação e ajuste de covariáveis, tornando-se uma guia prático para o clínico

The propensity score methods are the probability of a subject receiving conditional treatment on a set of baseline characteristics (confounders), and are used to compare patients with similar confounding distributions, so that the difference in results provides an unbiased estimate of the treatment effect. This review shows the basic concepts of propensity scores, and provides guidelines for the implementation of propensity methods, and others based on it, such as stratification, weighting, and adjustment of covariables, becoming a practical guide for the clinician

The propensity score method and it′s application / 中华预防医学杂志

Propensity score method, as an analytical strategy for adjusting multiple covariates, has been widely used in observational comparative effectiveness research. This paper introduces this method covered basic principles, case illustration and software implementation, in order to help readers understand propensity score method, apply it correctly in their researches, improve the efficiency of data utilization, and enhance the level of statistical analysis.

Aplicación de grafos acíclicos dirigidos en la evaluación de un set mínimo de ajuste de confusores: un complemento al modelamiento estadístico en estudios epidemiológicos observacionales / Directed acyclic graphs in statistical modelling of epidemiological studies

Background: Confusion in observational epidemiological studies distorts the relationship between exposure and event. "Step by step" regression models, diverts the decision to a statistical algorithm with little causal basis. Directed Acyclic Graphs (DAGs), qualitatively and visually assess the confusion. They can complement the decision on confounder control during statistical modeling. Aim: To evaluate the minimum set of confounders to be controlled in a cause-effect relationship with the use of "step-by-step regression" and DAGs, in a study of arsenic exposure. Material and Methods: We worked with data from Cáceres et al., 2010 in 66 individuals from northern Chile. The interindividual variability in the urinary excretion of dimethyl arsenic acid attributable to the GSTT1 polymorphism was estimated. A causal DAG was constructed using DAGitty v2.3 with the list of variables. A multiple linear regression model with the step-by-step backwards methodology was carried out. Results: The causal diagram included 12 non-causal open pathways. The minimum adjustment set corresponded to the variables "sex", "body mass index" and "fish and seafood ingest". Confusion retention of the multivariate model included normal and overweight status, gender and the interaction between "water intake" and GSTT1. Conclusions: The use of DAG prior to the modeling would allow a more comprehensive, coherent and biologically plausible analysis of causal relationships in public health.

Signal Detection of Adverse Drug Reactions through LASSO Logistic Regression Using an Electronic Health Records Database：A Case-Control Study / 薬剤疫学

Objective：The objective of this study was to apply Least Absolute Shrinkage and Selection Operator （LASSO）logistic regression to detection of adverse drug reaction （ADR） signals using an electronic health records database as a comprehensive and quantitative method to supplement the current pharmacovigilance activities in Japan.Design：case-control studyMethods：We analyzed data from 40767 inpatients using a single-institution hospital database and identified two ADRs, suspected pancreatitis and thrombocytopenia, using abnormal laboratory test results. LASSO logistic regression analysis was applied to detect ADR signals with adjustment for age, sex, comorbidities and medical procedures. The positive predictive value （PPV） was calculated using reference standard of known drug-ADR associations based on drug product labels.Results：The number of case group was 6735 for suspected pancreatitis and 11561 for thrombocytopenia. The number of ADR signals detected using LASSO logistic regression was 27 for suspected pancreatitis and 40 for thrombocytopenia. The calculated PPV was 3.7% for suspected pancreatitis and 55.0% for thrombocytopenia.Conclusion：LASSO logistic regression analysis efficiently detects ADR signals by adjusting for confounding factors such as comorbidities and medical procedures. The false positive signals may contain unknown signals and further signal assessment will be needed.

<b>Signal Detection of Adverse Drug Reactions through LASSO Logistic Regression </b><b>Using an Electronic Health Records Database</b>：<b>A Case-Control Study </b> / 薬剤疫学

<p><b>Objective</b>：The objective of this study was to apply Least Absolute Shrinkage and Selection Operator （LASSO）logistic regression to detection of adverse drug reaction （ADR） signals using an electronic health records database as a comprehensive and quantitative method to supplement the current pharmacovigilance activities in Japan.</p><p><b>Design</b>：case-control study</p><p><b>Methods</b>：We analyzed data from 40767 inpatients using a single-institution hospital database and identified two ADRs, suspected pancreatitis and thrombocytopenia, using abnormal laboratory test results. LASSO logistic regression analysis was applied to detect ADR signals with adjustment for age, sex, comorbidities and medical procedures. The positive predictive value （PPV） was calculated using reference standard of known drug-ADR associations based on drug product labels.</p><p><b>Results</b>：The number of case group was 6735 for suspected pancreatitis and 11561 for thrombocytopenia. The number of ADR signals detected using LASSO logistic regression was 27 for suspected pancreatitis and 40 for thrombocytopenia. The calculated PPV was 3.7% for suspected pancreatitis and 55.0% for thrombocytopenia.</p><p><b>Conclusion</b>：LASSO logistic regression analysis efficiently detects ADR signals by adjusting for confounding factors such as comorbidities and medical procedures. The false positive signals may contain unknown signals and further signal assessment will be needed.</p><p></p>