A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks.

To fit sparse linear associations, a LASSO sparsity inducing penalty with a single hyperparameter provably allows to recover the important features (needles) with high probability in certain regimes even if the sample size is smaller than the dimension of the input vector (haystack). More recently learners known as artificial neural networks (ANN) have shown great successes in many machine learning tasks, in particular fitting nonlinear associations. Small learning rate, stochastic gradient descent algorithm and large training set help to cope with the explosion in the number of parameters present in deep neural networks. Yet few ANN learners have been developed and studied to find needles in nonlinear haystacks. Driven by a single hyperparameter, our ANN learner, like for sparse linear associations, exhibits a phase transition in the probability of retrieving the needles, which we do not observe with other ANN learners. To select our penalty parameter, we generalize the universal threshold of Donoho and Johnstone (Biometrika 81(3):425-455, 1994) which is a better rule than the conservative (too many false detections) and expensive cross-validation. In the spirit of simulated annealing, we propose a warm-start sparsity inducing algorithm to solve the high-dimensional, non-convex and non-differentiable optimization problem. We perform simulated and real data Monte Carlo experiments to quantify the effectiveness of our approach.

Effects of the Interactive Web-Based Video "Mon Coeur, Mon BASIC" on Drug Adherence of Patients With Myocardial Infarction: Randomized Controlled Trial.

BACKGROUND: Secondary prevention strategies after acute coronary syndrome (ACS) presentation with the use of drug combinations are essential to reduce the recurrence of cardiovascular events. However, lack of drug adherence is known to be common in this population and to be related to treatment failure. To improve drug adherence, we developed the "Mon Coeur, Mon BASIC" video. This online video has been specifically designed to inform patients about their disease and their current medications. Interactivity has been used to increase patient attention, and the video can also be viewed on smartphones and tablets. OBJECTIVE: The objective of this study was to assess the long-term impact of an informative web-based video on drug adherence in patients admitted for an ACS. METHODS: This randomized study was conducted with consecutive patients admitted to University Hospital of Lausanne for ACS. We randomized patients to an intervention group, which had access to the web-based video and a short interview with the pharmacist, and a control group receiving usual care. The primary outcome was the difference in drug adherence, assessed with the Adherence to Refills and Medication Scale (ARMS; 9 multiple-choice questions, scores ranging from 12 for perfect adherence to 48 for lack of adherence), between groups at 1, 3, and 6 months. We assessed the difference in ARMS score between both groups with the Wilcoxon rank sum test. Secondary outcomes were differences in knowledge, readmissions, and emergency room visits between groups and patients' satisfaction with the video. RESULTS: Sixty patients were included at baseline. The median age of the participants was 59 years (IQR 49-69), and 85% (51/60) were male. At 1 month, 51 patients participated in the follow-up, 50 patients participated at 3 months, and 47 patients participated at 6 months. The mean ARMS scores at 1 and 6 months did not differ between the intervention and control groups (13.24 vs 13.15, 13.52 vs 13.68, respectively). At 3 months, this score was significantly lower in the intervention group than in the control group (12.54 vs 13.75; P=.03). We observed significant increases in knowledge from baseline to 1 and 3 months, but not to 6 months, in the intervention group. Readmissions and emergency room visits have been very rare, and the proportion was not different among groups. Patients in the intervention group were highly satisfied with the video. CONCLUSIONS: Despite a lower sample size than we expected to reach, we observed that the "Mon Coeur, Mon BASIC" web-based interactive video improved patients' knowledge and seemed to have an impact on drug adherence. These results are encouraging, and the video will be offered to all patients admitted to our hospital with ACS. TRIAL REGISTRATION: ClinicalTrials.gov NCT03949608; https://clinicaltrials.gov/ct2/show/NCT03949608.

Modeling whole body trace metal concentrations in aquatic invertebrate communities: A trait-based approach.

Trace metal risk assessment and environmental quality standard definition require realistic models that quantify metal exposure and accumulation by biota. In the present study we propose a novel trait-based approach to predict whole body concentrations of metals in aquatic invertebrates from concentrations measured in different environmental compartments. Field data from a large riverine floodplain was used to calibrate and test the model. The prediction performance of the trait-based model was unbiased and uncertainty was below the twofold of measured concentrations for the four studied metals (Ni, Cu, Cd, Pb). The relative contribution of feeding, respiration and locomotion patterns as well as metal concentrations in three environmental compartments provided insights into the importance of different uptake pathways. The relation with the sediment (i.e., to what degree taxa live in or directly on the sediment) was shown to be the most important trait to predict metal accumulation. Overall, this study demonstrated the potential use of bioecological traits for the modeling of whole body metal concentrations of entire aquatic invertebrate communities.

BARD1 serum autoantibodies for the detection of lung cancer.

PURPOSE: Currently the screening for lung cancer for risk groups is based on Computed Tomography (CT) or low dose CT (LDCT); however, the lung cancer death rate has not decreased significantly with people undergoing LDCT. We aimed to develop a simple reliable blood test for early detection of all types of lung cancer based on the immunogenicity of aberrant forms of BARD1 that are specifically upregulated in lung cancer. METHODS: ELISA assays were performed with a panel of BARD1 epitopes to detect serum levels of antibodies against BARD1 epitopes. We tested 194 blood samples from healthy donors and lung cancer patients with a panel of 40 BARD1 antigens. Using fitted Lasso logistic regression we determined the optimal combination of BARD1 antigens to be used in ELISA for discriminating lung cancer from healthy controls. Random selection of samples for training sets or validations sets was applied to validate the accuracy of our test. RESULTS: Fitted Lasso logistic regression models predict high accuracy of the BARD1 autoimmune antibody test with an AUC = 0.96. Validation in independent samples provided and AUC = 0.86 and identical AUCs were obtained for combined stages 1-3 and late stage 4 lung cancers. The BARD1 antibody test is highly specific for lung cancer and not breast or ovarian cancer. CONCLUSION: The BARD1 lung cancer test shows higher sensitivity and specificity than previously published blood tests for lung cancer detection and/or diagnosis or CT scans, and it could detect all types and all stages of lung cancer. This BARD1 lung cancer test could therefore be further developed as i) screening test for early detection of lung cancers in high-risk groups, and ii) diagnostic aid in complementing CT scan.

Assessment and analysis of mechanical allodynia-like behavior induced by spared nerve injury (SNI) in the mouse.

Experimental models of peripheral nerve injury have been developed to study mechanisms of neuropathic pain. In the spared nerve injury (SNI) model in rats, the common peroneal and tibial nerves are injured, producing consistent and reproducible pain hypersensitivity in the territory of the spared sural nerve. In this study, we investigated whether SNI in mice is also a valid model system for neuropathic pain. SNI results in a significant decrease in withdrawal threshold in SNI-operated mice. The effect is very consistent between animals and persists for the four weeks of the study. We also determined the relative frequency of paw withdrawal for each of a series of 11 von Frey hairs. Analysis of response frequency using a mixed-effects model that integrates all variables (nerve injury, paw, gender, and time) shows a very stable effect of SNI over time and also reveals subtle divergences between variables, including gender-based differences in mechanical sensitivity. We tested two variants of the SNI model and found that injuring the tibial nerve alone induces mechanical hypersensitivity, while injuring the common peroneal and sural nerves together does not induce any significant increase in mechanical sensitivity in the territory of the spared tibial nerve. SNI induces a mechanical allodynia-like response in mice and we believe that our improved method of assessment and data analysis will reveal additional internal and external variability factors in models of persistent pain. Use of this model in genetically altered mice should be very effective for determining the mechanisms involved in neuropathic pain.

Natural variation in baseline data: when do we call a new sample 'resistant'?

Mortality of pear psylla to amitraz was studied by means of bioassays. Variation between samples, temporal variation within the season in one orchard and spatial variation between Swiss regions were considered. Variation between samples was large enough to produce different Probit functions and LC50 values. Temporal and spatial variations were too small to indicate resistance. Prediction intervals of the pooled functions using bootstrapping were calculated to determine if future samples come from a population with decreased sensitivity. Probabilistic criteria on the population level were proposed for resistance.