Variable selection in linear regression models: Choosing the best subset is not always the best choice.

We consider the question of variable selection in linear regressions, in the sense of identifying the correct direct predictors (those variables that have nonzero coefficients given all candidate predictors). Best subset selection (BSS) is often considered the "gold standard," with its use being restricted only by its NP-hard nature. Alternatives such as the least absolute shrinkage and selection operator (Lasso) or the Elastic net (Enet) have become methods of choice in high-dimensional settings. A recent proposal represents BSS as a mixed-integer optimization problem so that large problems have become computationally feasible. We present an extensive neutral comparison assessing the ability to select the correct direct predictors of BSS compared to forward stepwise selection (FSS), Lasso, and Enet. The simulation considers a range of settings that are challenging regarding dimensionality (number of observations and variables), signal-to-noise ratios, and correlations between predictors. As fair measure of performance, we primarily used the best possible F1-score for each method, and results were confirmed by alternative performance measures and practical criteria for choosing the tuning parameters and subset sizes. Surprisingly, it was only in settings where the signal-to-noise ratio was high and the variables were uncorrelated that BSS reliably outperformed the other methods, even in low-dimensional settings. Furthermore, FSS performed almost identically to BSS. Our results shed new light on the usual presumption of BSS being, in principle, the best choice for selecting the correct direct predictors. Especially for correlated variables, alternatives like Enet are faster and appear to perform better in practical settings.

Adverse drug reaction or innocent bystander? A systematic comparison of statistical discovery methods for spontaneous reporting systems.

PURPOSE: Spontaneous reporting systems (SRSs) are used to discover previously unknown relationships between drugs and adverse drug reactions (ADRs). A plethora of statistical methods have been proposed over the years to identify these drug-ADR pairs. The objective of this study is to compare a wide variety of methods in their ability to detect these signals, especially when their detection is complicated by the presence of innocent bystanders (drugs that are mistaken to be associated with the ADR, since they are prescribed together with the drug that is the ADR's actual cause). METHODS: Twelve methods, 24 measures in total, ranging from simple disproportionality measures (eg, the reporting odds ratio), hypothesis tests (eg, test of the Poisson mean), Bayesian shrinkage estimates (eg, the Bayesian confidence propagation neural network, BCPNN) to sparse regression (LASSO), are compared in their ability to detect drug-ADR pairs in a large number of simulated SRSs with varying numbers of innocent bystanders and effect sizes. The area under the precision-recall curve is used to assess the measures' performance. RESULTS: Hypothesis tests (especially the test of the Poisson mean) perform best when the associations are weak and there is little to no confounding by other drugs. When the level of confounding increases and/or the effect sizes become larger, Bayesian shrinkage methods should be preferred. The LASSO proves to be the most robust against the innocent bystander effect. CONCLUSIONS: There is no absolute "winner". Which method to use for a particular SRS depends on the effect sizes and the level of confounding present in the data.

[Detection of drug risks after approval : Methods development for the use of routine statutory health insurance data]. / Aufdeckung von Arzneimittelrisiken nach der Zulassung : Methodenentwicklung zur Nutzung von Routinedaten der gesetzlichen Krankenversicherungen.

Adverse drug reactions are among the leading causes of death. Pharmacovigilance aims to monitor drugs after they have been released to the market in order to detect potential risks. Data sources commonly used to this end are spontaneous reports sent in by doctors or pharmaceutical companies. Reports alone are rather limited when it comes to detecting potential health risks. Routine statutory health insurance data, however, are a richer source since they not only provide a detailed picture of the patients' wellbeing over time, but also contain information on concomitant medication and comorbidities.To take advantage of their potential and to increase drug safety, we will further develop statistical methods that have shown their merit in other fields as a source of inspiration. A plethora of methods have been proposed over the years for spontaneous reporting data: a comprehensive comparison of these methods and their potential use for longitudinal data should be explored. In addition, we show how methods from machine learning could aid in identifying rare risks. We discuss these so-called enrichment analyses and how utilizing pharmaceutical similarities between drugs and similarities between comorbidities could help to construct risk profiles of the patients prone to experience an adverse drug event.Summarizing these methods will further push drug safety research based on healthcare claim data from German health insurances which form, due to their size, longitudinal coverage, and timeliness, an excellent basis for investigating adverse effects of drugs.

A high-quality human reference panel reveals the complexity and distribution of genomic structural variants.

Structural variation (SV) represents a major source of differences between individual human genomes and has been linked to disease phenotypes. However, the majority of studies provide neither a global view of the full spectrum of these variants nor integrate them into reference panels of genetic variation. Here, we analyse whole genome sequencing data of 769 individuals from 250 Dutch families, and provide a haplotype-resolved map of 1.9 million genome variants across 9 different variant classes, including novel forms of complex indels, and retrotransposition-mediated insertions of mobile elements and processed RNAs. A large proportion are previously under reported variants sized between 21 and 100 bp. We detect 4 megabases of novel sequence, encoding 11 new transcripts. Finally, we show 191 known, trait-associated SNPs to be in strong linkage disequilibrium with SVs and demonstrate that our panel facilitates accurate imputation of SVs in unrelated individuals.