The p-value and model specification in statistics

Stimulus-specific random effects inflate false-positive classification accuracy in multivariate-voxel-pattern-analysis: A solution with generalized mixed-effects modelling

When conducting multivariate-voxel pattern analysis (MVPA), researchers typically compute the average accuracy for each subject and statistically test if the average accuracy is different from the chance level across subjects (by-subject analysis). We argue that this traditional by-subject analysis leads to inflated Type-1 error rates, regardless of the type of machine learning method used (e.g., support vector machine). This is because by-subject analysis does not consider the variance attributed to the idiosyncratic features of the stimuli that have a common influence on all subjects (i.e., the random stimulus effect). As a solution, we proposed the use of generalized linear mixed-effects modelling to evaluate average accuracy. This method only requires post-classification data (i.e., it does not consider the type of classification methods used) and is easily implemented in the analysis pipeline with common statistical software (SPSS, R, Python, etc.). Using both statistical simulation and real fMRI data analysis, we demonstrated that the traditional by-subject method indeed increases Type-1 error rates to a considerable degree, while generalized mixed-effects modelling that incorporates random stimulus effects can indeed maintain the nominal Type-1 error rates.

Predictors for late genitourinary toxicity in men receiving radiotherapy for high-risk prostate cancer using planned and accumulated dose

Background and purpose

Significant deviations between bladder dose planned (D_P) and dose accumulated (D_A) have been reported in patients receiving radiotherapy for prostate cancer. This study aimed to construct multivariate analysis (MVA) models to predict the risk of late genitourinary (GU) toxicity with clinical and D_P or D_A as dose-volume (DV) variables.

Materials and methods

Bladder D_A obtained from 150 patients were compared with D_P. MVA models were built from significant clinical and DV variables (p < 0.05) at univariate analysis. Previously developed dose-based-region-of-interest (DB-ROI) metrics using expanded ring structures from the prostate were included. Goodness-of-fit test and calibration plots were generated to determine model performance. Internal validation was accomplished using Bootstrapping.

Results

Intermediate-high D_A (V_{30-65 Gy} and DB-ROI-20-50 mm) for bladder increased compared to D_P. However, at the very high dose region, D_A (D_{0.003 cc}, V_{75 Gy,} and DB-ROI-5-10 mm) were significantly lower. In MVA, single variable models were generated with odds ratio (OR) < 1. DB-ROI-50 mm was predictive of Grade ≥ 1 GU toxicity for D_A and D_P (D_A and D_P; OR: 0.96, p: 0.04) and achieved an area under the receiver operating curve (AUC) of > 0.6. Prostate volume (OR: 0.87, p: 0.01) was significant in predicting Grade 2 GU toxicity with a high AUC of 0.81.

Conclusions

Higher D_A (V_{30-65 Gy}) received by the bladder were not translated to higher late GU toxicity. DB-ROIs demonstrated higher predictive power than standard DV metrics in associating Grade ≥ 1 toxicity. Smaller prostate volumes have a minor protective effect on late Grade 2 GU toxicity.

Probe Contact Force Monitoring during Conductivity Measurements of the Left Atrial Appendage to Support the Design of Novel Diagnostic and Therapeutic Procedures

The electrical properties of many biological tissues are freely available from the INRC and the IT'IS databases. However, particularly in lower frequency ranges, few studies have investigated the optimal measurement protocol or the key confounders that need to be controlled, monitored, and reported. However, preliminary work suggests that the contact force of the measurement probe on the tissue sample can affect the measurements. The aim of this paper is to investigate the conductivity change due to the probe contact force in detail. Twenty ex vivo bovine heart samples are used, and conductivity measurements are taken in the Left Atrial Appendage, a common target for medical device developments. The conductivity measurements reported in this work (between 0.14 S/m and 0.24 S/m) align with the literature. The average conductivity is observed to change by -21% as the contact force increases from 2 N to 10 N. In contrast, in conditions where the fluid concentration in the measurement area is expected to be lower, very small changes are observed (less than 2.5%). These results suggest that the LAA conductivity is affected by the contact force due to the fluid concentration in the tissue. This work suggests that contact force should be controlled for in all future experiments.

A Machine Learning Approach to Identify Predictors of Frequent Vaping and Vulnerable Californian Youth Subgroups

INTRODUCTION

Machine learning presents a unique opportunity to improve electronic cigarette (vaping) monitoring in youth. Here we built a random forest model to predict frequent vaping status among Californian youth and to identify contributing factors and vulnerable populations.

METHODS

In this prospective cohort study, 1,281 ever-vaping twelfth-grade students from metropolitan Los Angeles were surveyed in Fall and in 6-month in Spring. Frequent vaping was measured at the 6-month follow-up as nicotine-containing vaping on 20 or more days in past 30 days. Predictors (n=131) encompassed sociodemographic characteristics, substance use and perceptions, health status, and characteristics of the household, school and neighborhood. A random forest was developed to identify the top ten predictors of frequent vaping and interactions by sociodemographic variables.

RESULTS

Forty participants (3.1%) reported frequent vaping at the follow-up. The random forest outperformed a logistic regression model in prediction (C-Index=0.87 vs. 0.77). Higher past-month nicotine concentration in vape, more daily vaping sessions, and greater nicotine dependence were the top three of the ten most important predictors of frequent vaping. Interactions were found between age and perceived discrimination, and between age and race/ethnicity, as those who were younger than their classmates and either reported experiencing discrimination frequently or identified as Asian or Native American/Pacific Islander were at increased risk of becoming frequent vapers.

CONCLUSIONS

Machine learning can produce models that accurately predict progression of vaping behaviours among youth. The potential association between frequent vaping and perceived discrimination warrants more in-depth analyses to confirm if discrimination constitutes a cause of increased vaping.

Ginsenoside Rg1 alleviates repeated alcohol exposure-induced psychomotor and cognitive deficits

Background

Chronic alcohol consumption disrupts psychomotor and cognitive functions, most of which are subserved by the dysfunction of hippocampus. Dysregulated excitatory glutamatergic transmission is implicated in repeated alcohol induced psychomotor and cognitive impairment. Ginsenoside Rg1, one of the main active ingredient of the traditional tonic medicine Panax ginseng C.A. Meyer (Araliaceae), has been used to treat cognitive deficits. Particularly, Rg1 has been demonstrated to improve hippocampus-dependent learning in mice and attenuate glutamate-induced excitotoxicity in vitro. Thus, in the present research, we sought to investigate the therapeutic effects of Ginsenoside Rg1 on repeated alcohol induced psychomotor and cognitive deficits in hippocampal-dependent behavioral tasks and unravel the underpinnings of its neuroprotection.

Methods

Male ICR (CD-1) mice were consecutively intragastrically treated with 20% (w/v) alcohol for 21 days. Then, behavior tests were conducted to evaluate repeated alcohol induced psychomotor and cognitive deficits. Histopathological changes, and biochemical and molecular alterations were assessed to determine the potential neuroprotective mechanism of Rg1.

Results

The results suggested that Rg1, at the optimal dose of 6 mg/kg, has the potential to ameliorate repeated alcohol induced cognitive deficits by regulating activities of NR2B containing NMDARs and excitotoxic signaling.

Conclusion

Our findings further provided a new strategy to treat chronic alcohol exposure induced adverse consequences.

Interpretation of omics data analyses

Omics studies attempt to extract meaningful messages from large-scale and high-dimensional data sets by treating the data sets as a whole. The concept of treating data sets as a whole is important in every step of the data-handling procedures: the pre-processing step of data records, the step of statistical analyses and machine learning, translation of the outputs into human natural perceptions, and acceptance of the messages with uncertainty. In the pre-processing, the method by which to control the data quality and batch effects are discussed. For the main analyses, the approaches are divided into two types and their basic concepts are discussed. The first type is the evaluation of many items individually, followed by interpretation of individual items in the context of multiple testing and combination. The second type is the extraction of fewer important aspects from the whole data records. The outputs of the main analyses are translated into natural languages with techniques, such as annotation and ontology. The other technique for making the outputs perceptible is visualization. At the end of this review, one of the most important issues in the interpretation of omics data analyses is discussed. Omics studies have a large amount of information in their data sets, and every approach reveals only a very restricted aspect of the whole data sets. The understandable messages from these studies have unavoidable uncertainty.