Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses.

Chatbot-based multimodal AI holds promise for collecting medical histories and diagnosing ophthalmic diseases using textual and imaging data. This study developed and evaluated the ChatGPT-powered Intelligent Ophthalmic Multimodal Interactive Diagnostic System (IOMIDS) to enable patient self-diagnosis and self-triage. IOMIDS included a text model and three multimodal models (text + slit-lamp, text + smartphone, text + slit-lamp + smartphone).

White matter connections within the central sulcus subserving the somato-cognitive action network.

The somato-cognitive action network (SCAN) consists of three nodes interspersed within Penfield's motor effector regions. The configuration of the somato-cognitive action network nodes resembles the one of the 'plis de passage' of the central sulcus: small gyri bridging the precentral and postcentral gyri. Thus, we hypothesize that these may provide a structural substrate of the somato-cognitive action network.

Boosting Cu ion capture in high-salinity environments with amino-functionalized millispheres.

High salinity in wastewater often hampers the performance of traditional adsorbents by disrupting electrostatic interactions and ion exchange processes, limiting their efficiency. This study addresses these challenges by investigating the salt-promoted adsorption of Cu ions onto amino-functionalized chloromethylated polystyrene (EDA@CMPS) millispheres. The adsorbent was synthesized by grafting ethylenediamine (EDA) onto CMPS, which significantly improved Cu adsorption, achieving nearly three times the capacity in saline solutions (1.

N-((perfluorophenyl)amino)glutamine regulates BACE1, tau phosphorylation, synaptic function, and neuroinflammation in Alzheimer's disease models.

Alzheimer's disease (AD) is the most common type of dementia. Its incidence is rising rapidly as the global population ages, leading to a significant social and economic burden. AD involves complex pathologies, including amyloid plaque accumulation, synaptic dysfunction, and neuroinflammation.

Explainable vision transformer for automatic visual sleep staging on multimodal PSG signals.

Polysomnography (PSG) is crucial for diagnosing sleep disorders, but manual scoring of PSG is time-consuming and subjective, leading to high variability. While machine-learning models have improved PSG scoring, their clinical use is hindered by the 'black-box' nature. In this study, we present SleepXViT, an automatic sleep staging system using Vision Transformer (ViT) that provides intuitive, consistent explanations by mimicking human 'visual scoring'.