A permutation approach for selecting the penalty parameter in penalized model selection

Procrustes is a machine-learning approach that removes cross-platform batch effects from clinical RNA sequencing data

With the increased use of gene expression profiling for personalized oncology, optimized RNA sequencing (RNA-seq) protocols and algorithms are necessary to provide comparable expression measurements between exome capture (EC)-based and poly-A RNA-seq. Here, we developed and optimized an EC-based protocol for processing formalin-fixed, paraffin-embedded samples and a machine-learning algorithm, Procrustes, to overcome batch effects across RNA-seq data obtained using different sample preparation protocols like EC-based or poly-A RNA-seq protocols. Applying Procrustes to samples processed using EC and poly-A RNA-seq protocols showed the expression of 61% of genes (N = 20,062) to correlate across both protocols (concordance correlation coefficient > 0.8, versus 26% before transformation by Procrustes), including 84% of cancer-specific and cancer microenvironment-related genes (versus 36% before applying Procrustes; N = 1,438). Benchmarking analyses also showed Procrustes to outperform other batch correction methods. Finally, we showed that Procrustes can project RNA-seq data for a single sample to a larger cohort of RNA-seq data. Future application of Procrustes will enable direct gene expression analysis for single tumor samples to support gene expression-based treatment decisions.

Variable selection for discrete survival model with frailty in presence of left truncation and right censoring: Studying association of environmental toxicants on time-to-pregnancy

Understanding the association between mixtures of environmental toxicants and time-to-pregnancy (TTP) is an important scientific question as sufficient evidence has emerged about the impact of individual toxicants on reproductive health and that individuals are exposed to a whole host of toxicants rather than an individual toxicant. Assessing mixtures of chemical effects on TTP poses significant statistical challenges, namely (i) TTP being a discrete survival outcome, typically subject to left truncation and right censoring, (ii) chemical exposures being strongly correlated, (iii) appropriate transformation to account for some lipid-binding chemicals, (iv) non-linear effects of some chemicals, and (v) high percentage of concentration below the limit of detection (LOD) for some chemicals. We propose a discrete frailty modeling framework (named Discnet) that allows selection of correlated covariates while appropriately addressing the methodological issues mentioned above. Discnet is shown to have better and stable false negative and false positive rates compared to alternative methods in various simulation settings. We did a detailed analysis of the pre-conception endocrine disrupting chemicals and TTP from the LIFE study and found that older females, female exposure to cotinine (smoking), DDT conferred a delay in getting pregnant, which was consistent across various approaches to account for LOD as well as non-linear associations.

Development and validation of a risk score to predict the frequent emergency house calls among older people who receive regular home visits

Background

The demand for home healthcare is increasing in Japan, and a 24-hour on-call system could be a burden for primary care physicians. Identifying high-risk patients who need frequent emergency house calls could help physicians prepare and allocate medical resources. The aim of the present study was to develop a risk score to predict the frequent emergency house calls in patients who receive regular home visits.

Methods

We conducted a retrospective cohort study with linked medical and long-term care claims data from two Japanese cities. Participants were ≥ 65 years of age and had newly started regular home visits between July 2014 and March 2018 in Tsukuba city and between July 2012 and March 2017 in Kashiwa city. We followed up with patients a year after they began the regular home visits or until the month following the end of the regular home visits if this was completed within 1 year. We calculated the average number of emergency house calls per month by dividing the total number of emergency house calls by the number of months that each person received regular home visits (1–13 months). The primary outcome was the “frequent” emergency house calls, defined as its use once per month or more, on average, during the observation period. We used the least absolute shrinkage and selection operator (LASSO) logistic regression with 10-fold cross-validation to build the model from 19 candidate variables. The predictive performance was assessed with the area under the curve (AUC).

Results

Among 4888 eligible patients, frequent emergency house calls were observed in 13.0% of participants (634/4888). The risk score included three variables with the following point assignments: home oxygen therapy (3 points); long-term care need level 4–5 (1 point); cancer (4 points). While the AUC of a model that included all candidate variables was 0.734, the AUC of the 3-risk score model was 0.707, suggesting good discrimination.

Conclusions

This easy-to-use risk score would be useful for assessing high-risk patients and would allow the burden on primary care physicians to be reduced through measures such as clustering high-risk patients in well-equipped medical facilities.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12875-022-01742-7.

Bayesian penalized Buckley-James method for high dimensional bivariate censored regression models

For high dimensional gene expression data, one important goal is to identify a small number of genes that are associated with progression of the disease or survival of the patients. In this paper, we consider the problem of variable selection for multivariate survival data. We propose an estimation procedure for high dimensional accelerated failure time (AFT) models with bivariate censored data. The method extends the Buckley-James method by minimizing a penalized [Formula: see text] loss function with a penalty function induced from a bivariate spike-and-slab prior specification. In the proposed algorithm, censored observations are imputed using the Kaplan-Meier estimator, which avoids a parametric assumption on the error terms. Our empirical studies demonstrate that the proposed method provides better performance compared to the alternative procedures designed for univariate survival data regardless of whether the true events are correlated or not, and conceptualizes a formal way of handling bivariate survival data for AFT models. Findings from the analysis of a myeloma clinical trial using the proposed method are also presented.

New adaptive lasso approaches for variable selection in automated pharmacovigilance signal detection

Background

Adverse effects of drugs are often identified after market introduction. Post-marketing pharmacovigilance aims to detect them as early as possible and relies on spontaneous reporting systems collecting suspicious cases. Signal detection tools have been developed to mine these large databases and counts of reports are analysed with disproportionality methods. To address disproportionality method biases, recent methods apply to individual observations taking into account all exposures for the same patient. In particular, the logistic lasso provides an efficient variable selection framework, yet the choice of the regularization parameter is a challenging issue and the lasso variable selection may give inconsistent results.

Methods

We propose a new signal detection methodology based on the adaptive lasso. We derived two new adaptive weights from (i) a lasso regression using the Bayesian Information Criterion (BIC), and (ii) the class-imbalanced subsampling lasso (CISL), an extension of stability selection. The BIC is used in the adaptive lasso stage for variable selection. We performed an extensive simulation study and an application to real data, where we compared our methods to the existing adaptive lasso, and recent detection approaches based on lasso regression or propensity scores in high dimension. For both studies, we evaluate the methods in terms of false discoveries and sensitivity.

Results

In the simulations and the application, both proposed adaptive weights show equivalent or better performances than the other competitors, with an advantage for the CISL-based adaptive weights. CISL and lasso regression using BIC are solid alternatives.

Conclusion

Our proposed adaptive lasso is an appealing methodology for signal detection in pharmacovigilance. Although we cannot rely on test theory, our approaches show a low and stable False Discovery Rate in all simulation settings. All methods evaluated in this work are implemented in the adapt4pv R package.

Supplementary Information

The online version contains supplementary material available at (10.1186/s12874-021-01450-3).

Predictors of Successful Yttrium-90 Radioembolization Bridging or Downstaging in Patients with Hepatocellular Carcinoma

PURPOSE

This study aims to identify clinical and imaging prognosticators associated with the successful bridging or downstaging to liver transplantation (LT) in patients undergoing Yttrium-90 radioembolization (Y90-RE) for hepatocellular carcinoma (HCC).

METHODS

Retrospectively, patients with Y90-RE naïve HCC who were candidates or potential candidates for LT and underwent Y90-RE were included. Patients were then divided into favorable (maintained or achieved Milan criteria (MC) eligibility) or unfavorable (lost eligibility or unchanged MC ineligibility) cohorts based on changes to their MC eligibility after Y90-RE. Penalized logistic regression analysis was performed to identify the significant baseline prognosticators.

RESULTS

Between 2013 and 2018, 135 patients underwent Y90-RE treatment. Among the 59 (42%) patients within MC, LT eligibility was maintained in 49 (83%) and lost in 10 (17%) patients. Within the 76 (56%) patients outside MC, eligibility was achieved in 32 (42%) and unchanged in 44 (58%). Among the 81 (60%) patients with a favorable response, 16 (20%) went on to receive LT. Analysis of the baseline characteristics revealed that lower Albumin-Bilirubin score, lower Child-Pugh class, lower Barcelona Clinic Liver Cancer stage, HCC diagnosis using dynamic contrast-enhanced imaging on CT or MRI, normal/higher albumin levels, decreased severity of tumor burden, left lobe HCC disease, and absence of HBV-associated cirrhosis, baseline abdominal pain, or fatigue were all associated with a higher likelihood of bridging or downstaging to LT eligibility (p's < 0.05).

CONCLUSION

Certain baseline clinical and tumor characteristics are associated with the successful bridging or downstaging of potential LT candidates with HCC undergoing Y90-RE.

Integrating additional knowledge into the estimation of graphical models

Graphical models such as brain connectomes derived from functional magnetic resonance imaging (fMRI) data are considered a prime gateway to understanding network-type processes. We show, however, that standard methods for graphical modeling can fail to provide accurate graph recovery even with optimal tuning and large sample sizes. We attempt to solve this problem by leveraging information that is often readily available in practice but neglected, such as the spatial positions of the measurements. This information is incorporated into the tuning parameter of neighborhood selection, for example, in the form of pairwise distances. Our approach is computationally convenient and efficient, carries a clear Bayesian interpretation, and improves standard methods in terms of statistical stability. Applied to data about Alzheimer's disease, our approach allows us to highlight the central role of lobes in the connectivity structure of the brain and to identify an increased connectivity within the cerebellum for Alzheimer's patients compared to other subjects.

I-Boost: an integrative boosting approach for predicting survival time with multiple genomics platforms

We propose a statistical boosting method, termed I-Boost, to integrate multiple types of high-dimensional genomics data with clinical data for predicting survival time. I-Boost provides substantially higher prediction accuracy than existing methods. By applying I-Boost to The Cancer Genome Atlas, we show that the integration of multiple genomics platforms with clinical variables improves the prediction of survival time over the use of clinical variables alone; gene expression values are typically more prognostic of survival time than other genomics data types; and gene modules/signatures are at least as prognostic as the collection of individual gene expression data.

Class-imbalanced subsampling lasso algorithm for discovering adverse drug reactions

Background All methods routinely used to generate safety signals from pharmacovigilance databases rely on disproportionality analyses of counts aggregating patients' spontaneous reports. Recently, it was proposed to analyze individual spontaneous reports directly using Bayesian lasso logistic regressions. Nevertheless, this raises the issue of choosing an adequate regularization parameter in a variable selection framework while accounting for computational constraints due to the high dimension of the data. Purpose Our main objective is to propose a method, which exploits the subsampling idea from Stability Selection, a variable selection procedure combining subsampling with a high-dimensional selection algorithm, and adapts it to the specificities of the spontaneous reporting data, the latter being characterized by their large size, their binary nature and their sparsity. Materials and method Given the large imbalance existing between the presence and absence of a given adverse event, we propose an alternative subsampling scheme to that of Stability Selection resulting in an over-representation of the minority class and a drastic reduction in the number of observations in each subsample. Simulations are used to help define the detection threshold as regards the average proportion of false signals. They are also used to compare the performances of the proposed sampling scheme with that originally proposed for Stability Selection. Finally, we compare the proposed method to the gamma Poisson shrinker, a disproportionality method, and to a lasso logistic regression approach through an empirical study conducted on the French national pharmacovigilance database and two sets of reference signals. Results Simulations show that the proposed sampling strategy performs better in terms of false discoveries and is faster than the equiprobable sampling of Stability Selection. The empirical evaluation illustrates the better performances of the proposed method compared with gamma Poisson shrinker and the lasso in terms of number of reference signals retrieved.

Prenatal Phthalate, Perfluoroalkyl Acid, and Organochlorine Exposures and Term Birth Weight in Three Birth Cohorts: Multi-Pollutant Models Based on Elastic Net Regression

BACKGROUND

Some legacy and emerging environmental contaminants are suspected risk factors for intrauterine growth restriction. However, the evidence is equivocal, in part due to difficulties in disentangling the effects of mixtures.

OBJECTIVES

We assessed associations between multiple correlated biomarkers of environmental exposure and birth weight.

METHODS

We evaluated a cohort of 1,250 term (≥ 37 weeks gestation) singleton infants, born to 513 mothers from Greenland, 180 from Poland, and 557 from Ukraine, who were recruited during antenatal care visits in 2002-2004. Secondary metabolites of diethylhexyl and diisononyl phthalates (DEHP, DiNP), eight perfluoroalkyl acids, and organochlorines (PCB-153 and p,p´-DDE) were quantifiable in 72-100% of maternal serum samples. We assessed associations between exposures and term birth weight, adjusting for co-exposures and covariates, including prepregnancy body mass index. To identify independent associations, we applied the elastic net penalty to linear regression models.

RESULTS

Two phthalate metabolites (MEHHP, MOiNP), perfluorooctanoic acid (PFOA), and p,p´-DDE were most consistently predictive of term birth weight based on elastic net penalty regression. In an adjusted, unpenalized regression model of the four exposures, 2-SD increases in natural log-transformed MEHHP, PFOA, and p,p´-DDE were associated with lower birth weight: -87 g (95% CI: -137, -340 per 1.70 ng/mL), -43 g (95% CI: -108, 23 per 1.18 ng/mL), and -135 g (95% CI: -192, -78 per 1.82 ng/g lipid), respectively; and MOiNP was associated with higher birth weight (46 g; 95% CI: -5, 97 per 2.22 ng/mL).

CONCLUSIONS

This study suggests that several of the environmental contaminants, belonging to three chemical classes, may be independently associated with impaired fetal growth. These results warrant follow-up in other cohorts.