Transforming Alzheimer's Digital Caregiving through Large Language Models.

Introduction/objective: Alzheimer's Disease and Related Dementias (AD/ADRD) present significant caregiving challenges, with increasing burdens on informal caregivers. This study examines the potential of AI-driven Large Language Models (LLMs) in developing digital caregiving strategies for AD/ADRD. The objectives include analyzing existing caregiving education materials (CEMs) and mobile application descriptions (MADs) and aligning key caregiving tasks with digital functions across different stages of disease progression.

Computer vision for kinematic metrics of the drinking task in a pilot study of neurotypical participants.

Assessment of the upper limb is critical to guiding the rehabilitation cycle. Drawbacks of observation-based assessment include subjectivity and coarse resolution of ordinal scales. Kinematic assessment gives rise to objective quantitative metrics, but uptake is encumbered by costly and impractical setups.

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy.

Simultaneous electroencephalogram and functional magnetic resonance imaging (EEG-fMRI) is a unique combined technique that provides synergy in the understanding and localization of seizure onset in epilepsy. However, reported experimental protocols for EEG-fMRI recordings fail to address details about conducting such procedures on epilepsy patients. In addition, these protocols are limited solely to research settings.

Biodegradation of polystyrene by intestinal symbiotic bacteria isolated from mealworms, the larvae of .

Objectives: Polystyrene is a plastic that leads to environmental pollution. In particular, expanded polystyrene is very light and takes up much space, causing additional environmental problems. The aim of this study was to isolate new symbiotic bacteria which degraded polystyrene from mealworms.

Predicting grade school scientific literacy from aspects of the early home science environment.

Fostering scientific literacy has become an increasingly salient goal as evidence accumulates regarding the early emergence of foundational skills and knowledge in this domain, as well as their relation to long-term success and engagement. Despite the potential that the home context has for nurturing early scientific literacy, research specifying its role has been limited. In this longitudinal study, we examined associations between children's early science-related experiences at home and their subsequent scientific literacy.

Neural Decoders Using Reinforcement Learning in Brain Machine Interfaces: A Technical Review.

Creating flexible and robust brain machine interfaces (BMIs) is currently a popular topic of research that has been explored for decades in medicine, engineering, commercial, and machine-learning communities. In particular, the use of techniques using reinforcement learning (RL) has demonstrated impressive results but is under-represented in the BMI community. To shine more light on this promising relationship, this article aims to provide an exhaustive review of RL's applications to BMIs.

Kernel Temporal Differences for EEG-based Reinforcement Learning Brain Machine Interfaces.

Kernel temporal differences (KTD) (λ) algorithm integrated in Q-learning (Q-KTD) has shown its applicability and feasibility for reinforcement learning brain machine interfaces (RLBMIs). RLBMI with its unique learning strategy based on trial-error allows continuous learning and adaptation in BMIs. Q-KTD has shown good performance in both open and closed-loop experiments for finding a proper mapping from neural intention to control commands of an external device.

Metric Learning in Freewill EEG Pre-Movement and Movement Intention Classification for Brain Machine Interfaces.

Decoding movement related intentions is a key step to implement BMIs. Decoding EEG has been challenging due to its low spatial resolution and signal to noise ratio. Metric learning allows finding a representation of data in a way that captures a desired notion of similarity between data points.

Feasibility of a deep learning-based algorithm for automated detection and classification of nasal polyps and inverted papillomas on nasal endoscopic images.

Background: Discrimination of nasal cavity mass lesions is a challenging work requiring extensive experience. A deep learning-based automated diagnostic system may help clinicians to classify nasal cavity mass lesions. We demonstrated the feasibility of a convolutional neural network (CNN)-based diagnosis system for automatic detection and classification of nasal polyps (NP) and inverted papillomas (IP).

Changes in Intestinal Microbiota Due to the Expanded Polystyrene Diet of Mealworms ().

Expanded polystyrene (EPS), which is difficult to decompose, is usually buried or incinerated, causing the natural environment to be contaminated with microplastics and environmental hormones. Digestion of EPS by mealworms has been identified as a possible biological solution to the problem of pollution, but the complete degradation mechanism of EPS is not yet known. Intestinal microorganisms play a significant role in the degradation of EPS by mealworms, and relatively few other EPS degradation microorganisms are currently known.

Histological Characterization of the Irritative Zones in Focal Cortical Dysplasia Using a Preclinical Rat Model.

Current clinical practice in focal epilepsy involves brain source imaging (BSI) to localize brain areas where from interictal epileptiform discharges (IEDs) emerge. These areas, named , have been useful to define candidate seizures-onset zones during pre-surgical workup. Since human histological data are mostly available from final resected zones, systematic studies characterizing pathophysiological mechanisms and abnormal molecular/cellular substrates in irritative zones-independent of them being epileptogenic-are challenging.

Time-Dependent Discrepancies between Assessments of Sensory Function after Incomplete Cervical Spinal Cord Injury.

We recently demonstrated that the electrical perceptual threshold (EPT) examination reveals spared sensory function at lower spinal segments compared with the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) examination in humans with chronic incomplete cervical spinal cord injury (SCI). Here, we investigated whether discrepancies in sensory function detected by both sensory examinations change over time after SCI. Forty-five participants with acute (<1 year), chronic (≥1-10 years), and extended-chronic (>10 years) incomplete cervical SCI and 30 control subjects were tested on dermatomes C2-T4 bilaterally.

Validating Non-invasive EEG Source Imaging Using Optimal Electrode Configurations on a Representative Rat Head Model.

The curtain of technical limitations impeding rat multichannel non-invasive electroencephalography (EEG) has risen. Given the importance of this preclinical model, development and validation of EEG source imaging (ESI) is essential. We investigate the validity of well-known human ESI methodologies in rats which individual tissue geometries have been approximated by those extracted from an MRI template, leading also to imprecision in electrode localizations.

Dysfunction of Neurovascular/Metabolic Coupling in Chronic Focal Epilepsy.

Goal: We aim to evaluate the mechanisms underlying the neurovascular/metabolic coupling in the epileptogenic cortices of rats with chronic focal epilepsy.

Methods: We performed and analyzed intracranial recordings obtained from the seizure-onset zones during ictal periods on epileptic rats, and then, used these data to fit a metabolically coupled balloon model. Normal rats undergoing forepaw stimulation were used as control.

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings.

Electroencephalogram (EEG) has been traditionally used to determine which brain regions are the most likely candidates for resection in patients with focal epilepsy. This methodology relies on the assumption that seizures originate from the same regions of the brain from which interictal epileptiform discharges (IEDs) emerge. Preclinical models are very useful to find correlates between IED locations and the actual regions underlying seizure initiation in focal epilepsy.

Kernel temporal differences for neural decoding.

We study the feasibility and capability of the kernel temporal difference (KTD)(λ) algorithm for neural decoding. KTD(λ) is an online, kernel-based learning algorithm, which has been introduced to estimate value functions in reinforcement learning. This algorithm combines kernel-based representations with the temporal difference approach to learning.

Information-theoretic metric learning: 2-D linear projections of neural data for visualization.

Intracortical neural recordings are typically high-dimensional due to many electrodes, channels, or units and high sampling rates, making it very difficult to visually inspect differences among responses to various conditions. By representing the neural response in a low-dimensional space, a researcher can visually evaluate the amount of information the response carries about the conditions. We consider a linear projection to 2-D space that also parametrizes a metric between neural responses.

A new method of concurrently visualizing states, values, and actions in reinforcement based brain machine interfaces.

This paper presents the first attempt to quantify the individual performance of the subject and of the computer agent on a closed loop Reinforcement Learning Brain Machine Interface (RLBMI). The distinctive feature of the RLBMI architecture is the co-adaptation of two systems (a BMI decoder in agent and a BMI user in environment). In this work, an agent implemented using Q-learning via kernel temporal difference (KTD)(λ) decodes the neural states of a monkey and transforms them into action directions of a robotic arm.

Reinforcement learning via kernel temporal difference.

This paper introduces a kernel adaptive filter implemented with stochastic gradient on temporal differences, kernel Temporal Difference (TD)(λ), to estimate the state-action value function in reinforcement learning. The case λ=0 will be studied in this paper. Experimental results show the method's applicability for learning motor state decoding during a center-out reaching task performed by a monkey.