There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously ...studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.
Building performant and robust artificial intelligence (AI)–based applications for dentistry requires large and high-quality data sets, which usually reside in distributed data silos from multiple ...sources (e.g., different clinical institutes). Collaborative efforts are limited as privacy constraints forbid direct sharing across the borders of these data silos. Federated learning is a scalable and privacy-preserving framework for collaborative training of AI models without data sharing, where instead the knowledge is exchanged in form of wisdom learned from the data. This article aims at introducing the established concept of federated learning together with chances and challenges to foster collaboration on AI-based applications within the dental research community.
Background and purpose
Recently, the CRYSTAL AF trial detected paroxysmal atrial fibrillation (AF) in 12.4% of patients after cryptogenic ischaemic stroke (IS) or cryptogenic transient ischaemic ...attack (TIA) by an insertable cardiac monitor (ICM) within 1 year of monitoring. Our aim was (i) to assess if an AF risk factor based pre‐selection of ICM candidates would enhance the rate of AF detection and (ii) to determine AF risk factors with significant predictive value for AF detection.
Methods
Seventy‐five patients with cryptogenic IS/TIA were consecutively enrolled if at least one of the following AF risk factors was present: a CHA2DS2‐VASc score ≥4, atrial runs, left atrium (LA) size >45 mm, left atrial appendage (LAA) flow ≤0.2 m/s, or spontaneous echo contrast in the LAA. The electrocardiographic and echocardiographic criteria were chosen as they have been repeatedly reported to predict AF; the same applies for four of the six items of the CHA2DS2‐VASc score. The study end‐point was the detection of one or more episodes of AF (≥2 min).
Results
Seventy‐four patients underwent implantation of an ICM; one patient had AF at the date of implantation. After 6 months, AF was detected in 21/75 patients (28%), after 12 months in 25/75 patients (33.3%). 92% of AF episodes were asymptomatic. LA size >45 mm and the presence of atrial runs were independently associated with AF detection hazard ratio 3.6 (95% confidence interval 1.6–8.4), P = 0.002, and 2.7 (1.2–6.7), P = 0.023, respectively.
Conclusions
The detection rate of AF is one‐third after 1 year if candidates for an ICM after cryptogenic IS/TIA are selected by AF risk factors. LA dilation and atrial runs independently predict AF.
Click here to view the accompanying paper in this issue.
In the last decades, the development and design of drug delivery systems have attracted great attention. Especially siRNA carriers have been of special interest since discovered as suitable tool for ...gene silencing. Self-assembled structures consisting of amphiphilic molecules are the most investigated carriers with regards to siRNA delivery. Liposomes as drug vehicles already found their way into clinical use, as they are highly biocompatible and their colloidal stability and circulation time in blood can be significantly enhanced by PEGylation. Fully synthetic polymersomes inspired by these natural structures provide enhanced stability and offer a wide range of modification-possibilities. Therefore, their design as carrier vehicles has become of great interest. This mini-review highlights the possibilities of using polymeric vesicles for potential drug delivery and gives a brief overview of their potential regarding fine-tuning towards targeted delivery or triggered drug release.
•We give an overview on liposomes as drug delivery system and their accomplishments also in clinical use.•We introduce polymersomes as potential alternative for liposomes as drug delivery vehicle on a research level.•Polymersomes are feasible for future biomedical application as to drug delivery due to diverse modification options.•Polymersomes are a suitable model for cell-uptake of nanomaterials.
In disordered media, quantum interference effects are expected to induce complete suppression of electron conduction. The phenomenon, known as Anderson localization, has a counterpart with classical ...waves that has been observed in acoustics, electromagnetism and optics, but a direct observation for particles remains elusive. Here, we report the observation of the three-dimensional localization of ultracold atoms in a disordered potential created by a speckle laser field. A phenomenological analysis of our data distinguishes a localized component of the resulting density profile from a diffusive component. The observed localization cannot be interpreted as the classical trapping of particles with energy below the classical percolation threshold in the disorder, nor can it be understood as quantum trapping in local potential minima. Instead, our data are compatible with the self-consistent theory of Anderson localization tailored to our system, involving a heuristic energy shift that offers scope for future interpretation. PUBLICATION ABSTRACT
An important goal in Brain-Computer Interfacing (BCI) is to find and enhance procedural strategies for users for whom BCI control is not sufficiently accurate. To address this challenge, we conducted ...offline analyses and online experiments to test whether the classification of different types of motor imagery could be improved when the training of the classifier was performed on the data obtained with the assistive muscular stimulation below the motor threshold. 10 healthy participants underwent three different types of experimental conditions: a) Motor imagery (MI) of hands and feet b) sensory threshold neuromuscular electrical stimulation (STM) of hands and feet while resting and c) sensory threshold neuromuscular electrical stimulation during performance of motor imagery (BOTH). Also, another group of 10 participants underwent conditions a) and c). Then, online experiments with 15 users were performed. These subjects received neurofeedback during MI using classifiers calibrated either on MI or BOTH data recorded in the same experiment. Offline analyses showed that decoding MI alone using a classifier based on BOTH resulted in a better BCI accuracy compared to using a classifier based on MI alone. Online experiments confirmed accuracy improvement of MI alone being decoded with the classifier trained on BOTH data. In addition, we observed that the performance in MI condition could be predicted on the basis of a more pronounced connectivity within sensorimotor areas in the frequency bands providing the best performance in BOTH. These finding might offer a new avenue for training SMR-based BCI systems particularly for users having difficulties to achieve efficient BCI control. It might also be an alternative strategy for users who cannot perform real movements but still have remaining afferent pathways (e.g., ALS and stroke patients).
•Afferent stimulation (STM) in the calibration phase was used to enhance BCI performance.•Concurrent motor imagery and STM had stronger modulation of sensorimotor oscillations.•STM significantly improved BCI accuracy particularly for poorly performing subjects.•Classifiers trained with STM can be successfully used online even without stimulation.•These findings ease the practical applicability of STM-based BCI systems.
INFERENCE WITH FEW HETEROGENEOUS CLUSTERS Ibragimov, Rustam; Müller, Ulrich K.
The review of economics and statistics,
03/2016, Letnik:
98, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Suppose estimating a model on each of a small number of potentially heterogeneous clusters yields approximately independent, unbiased, and Gaussian parameter estimators. We make two contributions in ...this setup. First, we show how to compare a scalar parameter of interest between treatment and control units using a two-sample t-statistic, extending previous results for the one-sample t-statistic. Second, we develop a test for the appropriate level of clustering; it tests the null hypothesis that clustered standard errors from a much finer partition are correct. We illustrate the approach by revisiting empirical studies involving clustered, time series, and spatially correlated data.
Abstract Objective Internet addiction becomes a growing health problem worldwide with prevalence rates up to 3%. Still, uncertainties exist regarding its diagnostics and clinical characterization. ...Especially the lacking clinical evidence regarding self-report measures assessing Internet addiction has been criticized. Methods This study aimed to characterize 290 German treatment seekers and to determine the diagnostic accuracy of a self-report scale for Internet addiction. Patients filled in self-report measures (SCL-90R, PHQ, AICA-S – Scale for the Assessment of Internet and Computer game Addiction) and underwent diagnostic interviews to assess symptoms of Internet addiction and level of functioning. Results Of the predominantly male treatment seekers 71% met the clinical diagnosis of Internet addiction. These displayed higher levels of psychopathology, especially depressive and dissociative symptoms. Half of the patients met criteria for one further psychiatric disorder according to clinical interviews, especially depressive disorders. Their level of functioning was decreased in all domains. AICA-S showed good psychometric properties and satisfying diagnostic accuracy (sensitivity: 80.5%; specificity: 82.4%). Discussion In this sample, Internet addiction was associated with high levels of psychosocial distress that is mainly related to depressive symptoms. Co-morbid disorders were common among those patients. First analyses on diagnostic accuracy of AICA-S (using the therapist's rating on Internet addiction as an independent external criterion) showed promising results.