Fatigue, anxiety and depression in parents of children with retinoblastoma: a cohort study.

Background: Retinoblastoma (RB) is the most common primary ocular malignancy in childhood, possibly causing vision loss and even a threat to life. Parents, as the primary caregivers of children with RB, are prone to negative emotions such as fatigue, anxiety, and depression. This study aimed to investigate the longitudinal fluctuations in fatigue, anxiety, and depression in parents of children with RB and the factors influencing them.

Feasibility of Physical Exam and Performance-Based Tests in Individuals With Chronic Low Back Pain: A Descriptive Study.

Background: Despite the wide utilization of physical tests and pain assessments to evaluate individuals with chronic low back pain (cLBP), there is limited information about their feasibility in terms of test duration, the ability of individuals with cLBP to perform these tests, and associated adverse events. The literature also lacks reports on comprehensive characterization of physical tests to serve as a reference for clinicians and researchers. The objectives of the present work are to assess the feasibility of a comprehensive battery of physical tests and pain assessments germane to individuals with cLBP and characterize the tests' values in the context of a large cohort.

An Automated Mobile Cognitive Test for the Identification of Cognitive Impairment: A Cross-sectional Feasibility and Diagnostic Study.

Objective: To develop Digital Processing Speed Test (DPST), a free, automated, multilingual, artificial intelligence-based cognitive testing application, with the aim to enhance recognition of cognitive impairment in underserved communities by leveraging mobile health to improve cognitive testing's accessibility.

Patients And Methods: In this cross-sectional feasibility and diagnostic study, we determined the test performance of DPST for the identification of mild cognitive impairment (MCI) and dementia, compared with traditional cognitive tests, such as Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA). The study was conducted from January 19, 2021, to November 12, 2023.

Short- and long-term weekly patient-reported outcomes prediction undergoing radiotherapy: single-patient time series model vs. transformer-based multi-patient time series model.

Background: Patient-reported outcomes (PROs) are direct reports from patients on health status, symptoms, quality of life, or treatment satisfaction, offering critical insights into subjective experiences that clinical metrics may overlook. Accurately predicting personalized short- and long-term weekly PROs during radiotherapy is essential for monitoring health status, optimizing treatment efficacy, and enabling timely interventions to manage side effects.

Methods: Based on the well-documented prostate cancer PRO dataset with 17 patients after pre-processing, this study evaluates single-patient time series models (i.

All-in-one medical image-to-image translation.

The growing availability of public multi-domain medical image datasets enables training omnipotent image-to-image (I2I) translation models. However, integrating diverse protocols poses challenges in domain encoding and scalability. Therefore, we propose the "every domain all at once" I2I (EVA-I2I) translation model using DICOM-tag-informed contrastive language-image pre-training (DCLIP).

Enhancing stroke recovery assessment: A machine learning approach to real-world hand function analysis.

Background: Hand weakness is a major contributor to long-term disability in stroke survivors, severely affecting daily function and quality of life. Although wrist-worn accelerometers offer an objective means of measuring upper limb (UL) use in daily life, traditional metrics such as movement duration and interlimb ratios provide only limited insight. When combined with unsupervised clustering, these heuristic measures often fail to capture meaningful clinical differences as the groupings frequently show substantial overlap on clinical scales like the Action Research Arm Test (ARAT).

Enabling Physicians to Make an Informed Adoption Decision on Artificial Intelligence Applications in Medical Imaging Diagnostics: Qualitative Study.

Background: Artificial intelligence (AI) applications hold great promise for improving accuracy and efficiency in medical imaging diagnostics. However, despite the expected benefit of AI applications, widespread adoption of the technology is progressing slower than expected due to technological, organizational, and regulatory obstacles, and user-related barriers, with physicians playing a central role in adopting AI applications.

Objective: This study aims to provide guidance on enabling physicians to make an informed adoption decision regarding AI applications by identifying and discussing measures to address key barriers from physicians' perspectives.

Advancing infection profiling under data uncertainty through contagion potential.

During the COVID-19 pandemic, the prevalence of asymptomatic cases challenged the reliability of epidemiological statistics in policymaking. To address this, we introduced contagion potential (CP) as a continuous metric derived from sociodemographic and epidemiological data to quantify the infection risk posed by the asymptomatic within a region. However, CP estimation is hindered by incomplete or biased incidence data, where underreporting and testing constraints make direct estimation infeasible.

Enhancing the gravity model for commuters: Time-and-spatial-structure-based improvements in Japan's metropolitan areas.

Metropolitan commuting flows reveal crucial insights into urban spatial dynamics; however, existing mobility models often struggle to capture the complex, heterogeneous patterns within these regions. This study introduces the Spatially Segregated Urban Gravity (SSUG) model, a novel approach that synergistically combines urban classification with gravity-based flow prediction to address this limitation. The SSUG model's key innovations include: (1) demonstrating the existence of different scaling laws in metropolitan areas, (2) identifying the existence of data-driven bifurcation that delineates urban-suburban commuting behaviors, (3) employing scaling exponents to reveal spatial segregation, and (4) leveraging high-resolution Global Positioning System (GPS) data for precise deterrence factor measurement.

Less is more: improving cell-type identification with augmentation-free single-cell RNA-Seq contrastive learning.

Motivation: Cell-type identification is one of the most important tasks in single-cell RNA Sequencing (scRNA-Seq) analysis. Recent research has revealed contrastive learning's great potential in handling multiple cell-type identification tasks.

Results: In this work, we proposed a novel augmentation-free scRNA-Seq contrastive learning (AF-RCL) algorithm, which simplifies the conventional data augmentation operation and adopts a new contrastive learning loss function.

Staff Enablement of the Tovertafel for Enrichment in Residential Aged Care: Field Study.

Background: Enrichment activities are essential for enhancing the psychosocial well-being of older adults living in residential aged care homes. There has been increasing interest in using digital technology for enrichment, but the implementation of technology requires careful support and enablement from staff to ensure that residents experience the intended benefits.

Objective: This study aimed to understand how care staff facilitate aged care residents' use of the Tovertafel ("magic table" in Dutch), a technology that projects images onto a tabletop to enable groups of people to play games.

EVIT-UNET: U-NET LIKE EFFICIENT VISION TRANSFORMER FOR MEDICAL IMAGE SEGMENTATION ON MOBILE AND EDGE DEVICES.

With the rapid development of deep learning, CNN-based U-shaped networks have succeeded in medical image segmentation and are widely applied for various tasks. However, their limitations in capturing global features hinder their performance in complex segmentation tasks. The rise of Vision Transformer (ViT) has effectively compensated for this deficiency of CNNs and promoted the application of ViT-based U-networks in medical image segmentation.

Responsible and adaptive robots in care home settings: an implementation framework analysis of a workshop with public and professionals.

As populations grow, research looks to emerging adaptive technologies for the urgent challenge in providing suitable care for older adults. Drawing on implementation science, we conducted a holistic examination looking at broader, contextual factors relating to the acceptability of robotics and sensor technologies in care homes. We held a workshop that brought together members of the public and researchers with experience in care home, to try such technologies and discuss their application in different care home scenarios.

Environmental adaptations in metagenomes revealed by deep learning.

Background: Deep learning has emerged as a powerful tool in the analysis of biological data, including the analysis of large metagenome data. However, its application remains limited due to high computational costs, model complexity, and difficulty extracting biological insights from these artificial neural networks (ANNs). In this study, we applied a transfer learning approach using the ESM-2 protein structure prediction model and our own smaller ANN to classify proteins containing the domain of unknown function 3494 (DUF3494) by their source environments.

DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge.

Diffusion-weighted MRI is critical for diagnosing and managing ischemic stroke, but variability in images and disease presentation limits the generalizability of AI algorithms. We present DeepISLES, a robust ensemble algorithm developed from top submissions to the 2022 Ischemic Stroke Lesion Segmentation challenge we organized. By combining the strengths of best-performing methods from leading research groups, DeepISLES achieves superior accuracy in detecting and segmenting ischemic lesions, generalizing well across diverse axes.

MPGM:Multi-prompt generation model with self-supervised contrastive learning for aspect sentiment triplet extraction.

Generative models are widely used in natural language processing and achieve remarkable results in the Aspect Sentiment Triplet Extraction (ASTE) task. Although existing generative methods can effectively identify triplets within sentences, their performance still needs to be improved when dealing with complex sentences containing multi-span terms. The main issues are the insufficient recognition of long-span terms and the lack of comprehensive recognition of complete triplets.

OCELOT 2023: Cell detection from cell-tissue interaction challenge.

Pathologists routinely alternate between different magnifications when examining Whole-Slide Images, allowing them to evaluate both broad tissue morphology and intricate cellular details to form comprehensive diagnoses. However, existing deep learning-based cell detection models struggle to replicate these behaviors and learn the interdependent semantics between structures at different magnifications. A key barrier in the field is the lack of datasets with multi-scale overlapping cell and tissue annotations.

Advanced dynamic ensemble framework with explainability driven insights for precision brain tumor classification across datasets.

Accurate detection of brain tumors remains a significant challenge due to the diversity of tumor types along with human interventions during diagnostic process. This study proposes a novel ensemble deep learning system for accurate brain tumor classification using MRI data. The proposed system integrates fine-tuned Convolutional Neural Network (CNN), ResNet-50 and EfficientNet-B5 to create a dynamic ensemble framework that addresses existing challenges.

Antimicrobial, photodegradation and BioReRAM applications of multifaceted green zinc oxide nanoparticles synthesized using coffee leaves extract.

The comprehensive utilization of plant biomass is a cornerstone in the development of sustainable circular bioeconomy. Several studies explore the conversion of primary biomass polymers and macromolecules, such as cellulose, hemicellulose, and lignin, into value-added chemical compounds, sustainable materials and biofuels. However, extractives warrant further investigations.

Application of AI-based techniques for anomaly management in wastewater treatment plants: A review.

Effective anomaly management of wastewater treatment plants (WWTPs) is crucial for environmental conservation and public health security. Traditional monitoring methods often struggle with challenges such as multivariate coupling, nonlinear dynamics, and external interferences inherent in wastewater treatment processes, which has driven growing interest towards artificial intelligence (AI)-based anomaly management solutions. This paper critically reviews recent advancements in AI-based anomaly management strategies for WWTPs, emphasizing three integral aspects: sensor data quality control and self-calibration, early anomaly detection and diagnosis, and fault-tolerant control and resilience enhancement.

Predicting antigenic peptides using a multi-level pooling-based transformer model with enhanced Kolaskar & Tongaonkar's algorithm for feature selection.

Antigenic peptide (AP) prediction is one of the most important roles in improve vaccine design and interpreting immune responses. This paper develops a Multi-Level Pooling-based Transformer (MLPT) model, which improves the accuracy and efficiency of predicting T-cell epitopes (TCEs). The model has utilized peptide sequences from the Immune Epitope Database (IEDB) and utilized a refined Kolaskar & Tongaonkar algorithm for feature extraction as well as a Self-Improved Black-winged Kite optimization algorithm to optimize the scoring matrix.

Data quality in crowdsourcing and spamming behavior detection.

As crowdsourcing emerges as an efficient and cost-effective method for obtaining labels for machine learning datasets, it is important to assess the quality of crowd-provided data to improve analysis performance and reduce biases in subsequent machine learning tasks. Given the lack of ground truth in most cases of crowdsourcing, we refer to data quality as the annotators' consistency and credibility. Unlike the simple scenarios where kappa coefficient and intraclass correlation coefficient usually can apply, online crowdsourcing requires dealing with more complex situations.

The Impact of Tokenizer Selection in Genomic Language Models.

Genomic language models have recently emerged as a new method to decode, interpret, and generate genetic sequences. Existing genomic language models have utilized various tokenization methods, including character tokenization, overlapping and non-overlapping k-mer tokenization, and byte-pair encoding, a method widely used in natural language models. Genomic sequences differ from natural language because of their low character variability, complex and overlapping features, and inconsistent directionality.

Prevalence of Agitation and Depression Amongst People with Dementia in Australian Residential Aged Facilities: A Cross-Sectional Study Using LLMs.

This preliminary study investigates the prevalence of agitation and depression among dementia residents in Australian Residential Aged Care Facilities (RACFs), utilizing Llama 3.1-8B. Analysis of 9,658 nursing notes from 40 RACFs highlighted significant sex- and age-specific differences and symptom cooccurrence trends.

Temporal Evolution of Public Health Sentiment: A Longitudinal Analysis.

This study advances our understanding of public health crisis communication by conducting a longitudinal analysis. As COVID-19 has been the largest public health crisis to date, we performed sentiment analysis on it. While previous research focused on discrete time periods, our study examines the arc of pandemic-related discourse from 2020 to 2022, revealing long-term patterns in public sentiment evolution.