ECG-based machine learning model for AF identification in patients with first ischemic stroke.

Background: The recurrence rate of strokes associated with atrial fibrillation (AF) can be substantially reduced through the administration of oral anticoagulants. However, previous studies have not demonstrated a clear benefit from the universal application of oral anticoagulants in patients with embolic stroke of undetermined source. Timely detection of AF remains a challenge in patients with stroke.

On-chip integrated metasystem for spin-dependent multi-channel color holography.

On-chip integrated metasurface driven by in-plane guided waves is of great interests in various light-field manipulation applications such as colorful augmented reality and holographic display. However, it remains a challenge to design colorful multichannel holography by a single on-chip metasurface. Here we present metasurfaces integrated on top of a guided-wave photonic slab that achieves multi-channel colorful holographic light display.

Inverse design of a light nanorouter for a spatially multiplexed optical filter.

It is attractive to use an optical nanorouter by artificial nanostructures to substitute the traditional Bayer filter for an image array sensor, which, however, poses great challenges in balancing the design strategy and the ease of fabrication. Here, we implement and compare two inverse design schemes for rapid optimization of RGGB Bayer-type optical nanorouter. One is based on the multiple Mie scattering theory and the adjoint gradient that is applicable to arrays of nanospheres with varying sizes, and the other is based on the rigorous coupled wave analysis and the genetic algorithm.

Identification of Patients with Potential Atrial Fibrillation during Sinus Rhythm Using Isolated P Wave Characteristics from 12-Lead ECGs.

Atrial fibrillation (AF) is largely underdiagnosed. Previous studies using deep neural networks with large datasets have shown that screening AF with a 12-lead electrocardiogram (ECG) during sinus rhythm (SR) is possible. However, the poor availability of these trained models and the small size of the retrievable datasets limit its reproducibility.