Search

Predicting cancer-associated clinical events is challenging in oncology. In Multiple Myeloma (MM), a cancer of plasma cells, disease progression is determined by changes in biomarkers, such as serum concentration of the paraprotein secreted by plasma cells (M-protein). Therefore, the time-dependent behaviour of M-protein and the transition across lines of therapy (LoT) that may be a consequence of disease progression should be accounted for in statistical models to predict relevant clinical outcomes. Furthermore, it is important to understand the contribution of the patterns of longitudinal biomarkers, upon each LoT initiation, to time-to-death or time-to-next-LoT. Motivated by these challenges, we propose a Bayesian joint model for trajectories of multiple longitudinal biomarkers, such as M-protein, and the competing risks of death and transition to next LoT. Additionally, we explore two estimation approaches for our joint model: simultaneous estimation of all parameters (joint estimation) and sequential estimation of parameters using a corrected two-stage strategy aiming to reduce computational time. Our proposed model and estimation methods are applied to a retrospective cohort study from a real-world database of patients diagnosed with MM in the US from January 2015 to February 2022. We split the data into training and test sets in order to validate the joint model using both estimation approaches and make dynamic predictions of times until clinical events of interest, informed by longitudinally measured biomarkers and baseline variables available up to the time of prediction., Comment: 38 pages, 13 figures

Duration of response (DOR) and time to response (TTR) are typically evaluated as secondary endpoints in early-stage clinical studies in oncology when efficacy is assessed by the best overall response (BOR) and presented as the overall response rate (ORR). Despite common use of DOR and TTR in particular in single-arm studies, the definition of these endpoints and the questions they are intended to answer remain unclear. Motivated by the estimand framework, we present relevant scientific questions of interest for DOR and TTR and propose corresponding estimand definitions. We elaborate on how to deal with relevant intercurrent events which should follow the same considerations as implemented for the primary response estimand. A case study in mantle cell lymphoma illustrates the implementation of relevant estimands of DOR and TTR. We close the paper with practical recommendations to implement DOR and TTR in clinical study protocols.

Most applications of machine learning for finance are related to forecasting tasks for investment decisions. Instead, we aim to promote a better understanding of financial markets with machine learning techniques. Leveraging the tremendous progress in deep learning models for natural language processing, we construct a hierarchical Reformer ([15]) model capable of processing a large document level dataset, SEDAR, from canadian financial regulatory filings. Using this model, we show that it is possible to predict trade volume changes using regulatory filings. We adapt the pretraining task of HiBERT ([36]) to obtain good sentence level representations using a large unlabelled document dataset. Finetuning the model to successfully predict trade volume changes indicates that the model captures a view from financial markets and processing regulatory filings is beneficial. Analyzing the attention patterns of our model reveals that it is able to detect some indications of material information without explicit training, which is highly relevant for investors and also for the market surveillance mandate of financial regulators., Comment: KDD ML in Finance workshop 2021

The anchoring biofilm layer is expected to exhibit a different response to environmental stresses than for portions in the bulk, due to the protection from other strata and the proximity to the attachment surface. The effect of hydrodynamic stress on surface-adhered biofilm layers was tested using a specially designed microfluidic bio flow cell with an embedded three-electrode detection system. In situ electrochemical impedance spectroscopy (EIS) measurements of biocapacitance and bioresistance of Pseudomonas sp. biofilms were conducted during the growth phase and under different shear flow conditions with verification by other surface sensitive techniques. Distinctive, but reversible changes to the amount of biofilm and its structure at the attachment surface were observed during the application of elevated shear stress. In contrast, regular microscopy revealed permanent distortion to the biofilm bulk, in the form of streamers and ripples. Following the application of extreme shear stresses, complete removal of significant portions of biofilm outer layers occurred, but this did not change the measured quantity of biofilm at the electrode attachment surface. The structure of the remaining biofilm, however, appeared to be modified and susceptible to further changes following application of shear stress directly to the unprotected biofilm layers at the attachment surface., Comment: 29 pages, 6 figures

Bacterial biofilms are among the oldest and most prevalent multicellular life forms on Earth and are increasingly relevant in research areas related to industrial fouling, medicine and biotechnology. The main hurdles to obtaining definitive experimental results include time-varying biofilm properties, structural and chemical heterogeneity, and especially their strong sensitivity to environmental cues. Therefore, in addition to judicious choice of measurement tools, a well-designed biofilm study requires strict control over experimental conditions, more so than most chemical studies. Due to excellent control over a host of physiochemical parameters, microfluidic flow cells have become indispensable in microbiological studies. Not surprisingly, the number of lab-on-chip studies focusing on biofilms and other microbiological systems with expanded analytical capabilities has expanded rapidly in the past decade. In this paper, we comprehensively review the current state of microfluidic bioanalytical research applied to bacterial biofilms and offer a perspective on new approaches that are expected to drive continued advances in this field., Comment: 16 pages, 8 figures, 2 tables

Clark et al. [2020] claims that the ELECTRA approach is highly efficient in NLP performances relative to computation budget. As such, this reproducibility study focus on this claim, summarized by the following question: Can we use ELECTRA to achieve close to SOTA performances for NLP in low-resource settings, in term of compute cost?, Comment: Submission for ML Reproducibility Challenge 2020

A method combining video imaging in parallel microchannels with a semi-empirical mathematical model provides non-intrusive, high-throughput measurements of time-varying biofilm viscosity. The approach is demonstrated for early growth Pseudomonas sp. biofilms exposed to constant flow streams of nutrient solutions with different ionic strengths. The ability to measure viscosities at early growth stages, without inducing a shear-thickening response, enabled measurements that are among the lowest reported to date. In addition, good time resolution enabled the detection of a rapid thickening phase, which occurred at different times after the exponential growth phase finished, depending on the ionic strength. The technique opens the way for a combinatorial approach to beter understand the complex dynamical response of biofilm mechanical properties under well-controlled physical, chemical and biological growth conditions and time-limited perturbations., Comment: Manuscript: 6 pages, 6 figures. Supporting information: 5 pages, 4 figures