Search

Human prescription drug labeling contains a summary of the essential scientific information needed for the safe and effective use of the drug and includes the Prescribing Information, FDA-approved patient labeling (Medication Guides, Patient Package Inserts and/or Instructions for Use), and/or carton and container labeling. Drug labeling contains critical information about drug products, such as pharmacokinetics and adverse events. Automatic information extraction from drug labels may facilitate finding the adverse reaction of the drugs or finding the interaction of one drug with another drug. Natural language processing (NLP) techniques, especially recently developed Bidirectional Encoder Representations from Transformers (BERT), have exhibited exceptional merits in text-based information extraction. A common paradigm in training BERT is to pretrain the model on large unlabeled generic language corpora, so that the model learns the distribution of the words in the language, and then fine-tune on a downstream task. In this paper, first, we show the uniqueness of language used in drug labels, which therefore cannot be optimally handled by other BERT models. Then, we present the developed PharmBERT, which is a BERT model specifically pretrained on the drug labels (publicly available at Hugging Face). We demonstrate that our model outperforms the vanilla BERT, ClinicalBERT and BioBERT in multiple NLP tasks in the drug label domain. Moreover, how the domain-specific pretraining has contributed to the superior performance of PharmBERT is demonstrated by analyzing different layers of PharmBERT, and more insight into how it understands different linguistic aspects of the data is gained. [ABSTRACT FROM AUTHOR]

There is currently no simple, widely available screening method for Alzheimer's disease (AD), partly because the diagnosis of AD is complex and typically involves expensive and sometimes invasive tests not commonly available outside highly specialized clinical settings. Here, we developed an artificial intelligence (AI)-powered end-to-end system to detect AD and predict its severity directly from voice recordings. At the core of our system is the pre-trained data2vec model, the first high-performance self-supervised algorithm that works for speech, vision, and text. Our model was internally evaluated on the ADReSSo (Alzheimer's Dementia Recognition through Spontaneous Speech only) dataset containing voice recordings of subjects describing the Cookie Theft picture, and externally validated on a test dataset from DementiaBank. The AI model can detect AD with average area under the curve (AUC) of 0.846 and 0.835 on held-out and external test set, respectively. The model was well-calibrated (Hosmer-Lemeshow goodness-of-fit p-value = 0.9616). Moreover, the model can reliably predict the subject's cognitive testing score solely based on raw voice recordings. Our study demonstrates the feasibility of using the AI-powered end-to-end model for early AD diagnosis and severity prediction directly based on voice, showing its potential for screening Alzheimer's disease in a community setting. [ABSTRACT FROM AUTHOR]

Bistable perception refers to the phenomenon of spontaneously alternating percepts while viewing the same stimulus continuously. Bistable stimuli allow dissociation between stimuli and perception, and thus, provide a unique opportunity for understanding the neural basis of visual perception. In this paper, we focus on a relaxation (RELAX) based algorithm to select features from the multitaper spectral estimates of the multichannel intracortical local field potential (LFP), simultaneously collected from the middle temporal visual cortex of a macaque monkey, for decoding its bistable structure-from-motion (SFM) perception. We demonstrate that RELAX surpasses the conventional sequential forward selection (SFS) by offering the flexibility of modifying selected features. We propose a redundancy reduction preprocessing technique to significantly reduce the computational load for both SFS and RELAX. We exploit the support vector machines classifier based on the selected features for single-trial decoding the reported perception. Our results demonstrate the excellent performance of the RELAX feature selection algorithm. Furthermore, we find that the features in the gamma frequency band (30-100 Hz) of LFP are most relevant to bistable SFM perception. This finding is novel in awake monkey studies and suggests that gamma oscillations carry the most discriminative information for bistable perception of SFM stimuli. Index Terms--Bistable stimuli, feature selection, local field potential (LFP), middle temporal (MT), multitaper spectral analysis, perception, redundancy, relaxation (RELAX), relevance, sequential forward selection (SFS), single-trial decoding, structure-from-motion (SFM), support vector machines (SVMs).

In this letter, we consider how to combine neuronal signals from multiple electrodes to optimally predict behavioral choices from observed neural activity. The predictability is often quantified by the area under the receiver operating characteristic (ROC) curve, also called choice probability (CP) in neurophysiology. We exploit a distribution-free relaxation based multichannel signal combination (RELAX-MUSIC) approach that requires only simple pairwise combination and recursive implementation for optimizing the area under the ROC curve. A permutation test is employed to assess the statistical significance of the derived CP. We demonstrate that the RELAX-MUSIC approach outperforms the commonly used response pooling and Fisher linear discriminant (FLD) methods. The excellent performances of the RELAX-MUSIC approach for predicting perceptual decisions from neural activity are demonstrated via examples using simulated and experimental data. Index Terms--Fisher linear discriminant (FLD), middle temporal (MT), multichannel combination, receiver operating characteristic (ROC), single unit activity (SUA), structure from motion (SFM), visual cortex.

The underdetermined problem poses a significant challenge in blind source separation (BSS) where the number of the source signals is greater than that of the mixed signals. Motivated by the fact that the security of many cryptosystems relies on the apparent intractability of the computational problems such as the integer factorization problem, we exploit the intractability of the underdetermined BSS problem to present a novel BSS-based speech encryption by properly constructing the underdetermined mixing matrix for encryption, and by generating the key signals that satisfy the necessary condition for the proposed method to be unconditionally secure. Both extensive computer simulations and performance analyses results show that the proposed method has high level of security while retaining excellent audio quality. Index Terms--Blind source separation (BSS), independent component analysis (ICA), speech encryption.

The Empirical Mode Decomposition (EMD) is a general signal processing method for analyzing nonlinear and nonstationary time series. The central idea of EMD is to decompose a time series into a finite and often small number of intrinsic mode functions (IMFs). An IMF is defined as any function having the number of extrema and the number of zero-crossings equal (or differing at most by one), and also having symmetric envelopes defined by the local minima, and maxima respectively. The decomposition procedure is adaptive, data-driven, therefore, highly efficient. In this contribution, we applied the idea of EMD to develop strategies to automatically identify the relevant IMFs that contribute to the slow-varying trend in the data, and presented its application on the analysis of esophageal manometric time series in gastroesophageal reflux disease. The results from both extensive simulations and real data show that the EMD may prove to be a vital technique for the analysis of esophageal manometric data. Index Terms--Empirical mode decomposition, esophageal motility, gastroesophageal reflux disease, lower esophageal sphincter.