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.

Digital Twins of Patients: A Cohort Matching Interpretation.

Digital Twins (DTs) are essentially virtual replicas of physical entities. DTs have evolved significantly over time. They have been applied in various fields.

Automated Detection of Invasive Fungal Infections in Clinical Reports Using Medical Language Models.

Invasive fungal infections (IFIs) pose significant risks to patients with weakened immune systems, requiring timely detection. To improve IFI detection from clinical reports, we explore the value of recent advances in NLP techniques for this task, including transformer-based pre-trained language models (PLMs) and generative large language models (LLMs). Experimental results show these methods are more effective for IFI detection than prior approaches, with a hybrid approach missing only one positive case over a public benchmark dataset, CHIFIR.

Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes.

De-identifying private information in medical records is crucial to prevent confidentiality breaches. Rule-based and learning-based methods struggle with generalizability and require large annotated datasets, while LLMs offer better language comprehension but face privacy risks and high computational costs. We propose LPPA, an LLM-empowered Privacy-protected PHI Annotation framework, which uses few-shot learning with pre-trained LLMs to generate synthetic clinical notes, reducing the need for extensive datasets.

Leveraging Retrieval Augmented Generation-Driven Large Language Models to Extract Dementia Agitation Symptoms and Triggers from Free-Text Nursing Notes.

Unstructured electronic health records are a rich source of patient-specific information but are challenging for analysis due to inconsistent terminology, diverse data formats, and extensive free-text content. To address this, we developed a named entity recognition model leveraging retrieval-augmented generation (RAG) powered by generative artificial intelligence. The model identifies symptoms and triggers of agitation in dementia from nursing notes within residential aged care facilities (RACFs).

Pilot Application of a Large Language Model to Identify Hospitalisation from Unstructured Electronic Health Records in Residential Aged Care Facilities.

Older people in residential aged care facilities (RACFs) visit hospitals and utilise healthcare services more often than others in the community. Trends in hospitalization rates are essential for designing targeted aged care interventions to reduce preventable hospitalizations and optimize resource use. Unstructured free-text nursing notes in Australian RACFs provide updated health information but require significant manual annotation due to their lack of standardization for supervised learning applications.

Designing an Ontology for a Smart Learning Health System Framework.

The concept of a "Learning Health System Framework" has been defined in various forms, making it difficult for healthcare leaders to adopt an appropriate framework for organisational transformation. There is a pressing need to standardise its components and relationships. Limitations of the existing LHS frameworks include their lack of flexibility to adapt to sociotechnical changes and inability to guide the automatic evaluation initiative on health organisational performance.

Essential Design Features of Mhealth Applications That Improve Medication Adherence for People with Diabetes.

Mobile health (mHealth) applications play an increasingly significant role in enhancing healthcare delivery and supporting the self-management of long-term conditions. This study aims to identify the essential features of mHealth applications that improve medication adherence and health outcomes in adults with long-term conditions. Using qualitative methods, we recruited 42 participants, including 17 with diabetes, and analysed interview data to generate six core themes: blood glucose improvement, convenience of use, decision-making support, emotional wellbeing, clinician-patient relationship enhancement, and patient empowerment.

The Patient-Oriented Neuroendocrine Tumor Registry for Australia.

Neuroendocrine tumors (NETs) are rare forms of cancer. At present different clinical centers across Australia are responsible for the diagnosis, treatment and ongoing management of NET patients. Due to the lack of a cohesive, uniform health system, there is at present a fragmentation of data that negatively impacts insights that can be gleaned from population-wide data.

LLM-Integrated Normalization and Knowledge for FHIR (LINK-FHIR).

Current approaches lack efficient methods to convert diverse healthcare data formats into standardized Fast Healthcare Interoperability Resources (FHIR). LINK-FHIR is a novel system for converting diverse Electronic Health Records into FHIR-compliant resources. The system leverages fine-tuned Large Language Models through a unified pipeline to efficiently process unstructured clinical notes, semi-structured lab reports, and structured tables.

Accelerating clinical evidence synthesis with large language models.

Clinical evidence synthesis largely relies on systematic reviews (SR) of clinical studies from medical literature. Here, we propose a generative artificial intelligence (AI) pipeline named TrialMind to streamline study search, study screening, and data extraction tasks in SR. We chose published SRs to build TrialReviewBench, which contains 100 SRs and 2,220 clinical studies.

A novel approach for joint indoor localization and activity recognition using a hybrid CNN-GRU and MRF framework.

This work proposes a new hybrid model for joint indoor localization and activity recognition by combining a Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) model with a Markov Random Field (MRF) for better classification. The CNN-GRU successfully captures spatial and temporal dependencies, while the MRF models the mutual relations of activities and locations by estimating their joint probability distribution. The new system was tested on a public smart home dataset with four activities (sitting, lying, walking, and standing) and four indoor locations (kitchen, bedroom, living room, and stairs).

A Virtual Reality-Based Cognitive Defusion Application for Youth Depression and Anxiety: Mixed Methods Experimental Study.

Background: Third-wave psychological treatments such as acceptance and commitment therapy can be effective for improving depression and anxiety in youth. However, third-wave therapeutic techniques such as cognitive defusion can be abstract, challenging to learn, and difficult to apply in real-world settings. Translating these techniques into virtual reality (VR) may provide interactive, enjoyable, and concrete learning opportunities, potentially enhancing engagement and effectiveness.

Circular RNA Profiling Identifies as a -Derived Regulator of Endothelial Proliferation and Stress Responses.

Background: The gene encodes the BMPR-II (bone morphogenetic protein receptor type-II) and is a known regulator of endothelial proliferation, apoptosis, and translational stress responses. While these effects are generally attributed to the actions of BMPR-II protein, we used circular RNA profiling to identify and as new -derived functional RNAs.

Methods: Circular RNAs were profiled by ultradeep RNA sequencing of human pulmonary artery endothelial cells.

Eco-friendly preparation of titanium dioxide/carbon nitride nanocomposites for photoelectrocatalytic applications.

Titanium dioxide (TiO) and its heterostructures are among the most extensively studied materials for photo- and electrocatalytic applications. Optimizing their synthesis remains crucial for enhancing performance and reducing production costs. In this work, we report a simple, eco-friendly method for preparing TiO/graphitic carbon nitride (g-CN) nanocomposites in both powder and thin-film forms.

A framework for EO-based National Agricultural Monitoring (EO-NAM) for the African Context.

Effective agriculture monitoring is vital for food security and achieving UN Sustainable Development Goal 2: Zero Hunger. Earth-observations (EO) offer unparalleled potential for scalable data, yet many developing nations, particularly in Africa, face challenges due to limited investments in human capacity and technology. We present a phased framework for EO-based agriculture monitoring systems, emphasizing national commitment and leveraging existing structures for long-term sustainability and adopting and adapting future advancements.

Integrating multimodal ultrasound imaging for improved radiomics sentinel lymph node assessment in breast cancer.

Background: Accurate preoperative assessment of sentinel lymph node (SLN) is critical for treatment planning in breast cancer (BC). While SLN biopsy (SLNB) remains the gold standard, it is invasive and may be unnecessary for all patients, particularly those with clinically node-negative disease. Combining conventional B-mode ultrasound (BMUS) and color Doppler ultrasound (CDUS) with new techniques like radiomics and deep learning may improve SLN prediction, but this approach has not been widely studied yet.

Artificial intelligence in personalized nutrition and food manufacturing: a comprehensive review of methods, applications, and future directions.

Artificial Intelligence (AI) is emerging as a key driver at the intersection of nutrition and food systems, offering scalable solutions for precision health, smart manufacturing, and sustainable development. This study aims to present a comprehensive review of AI-driven innovations that enable precision nutrition through real-time dietary recommendations, meal planning informed by individual biological markers (., blood glucose or cholesterol levels), and adaptive feedback systems.

Targeting neurodegeneration: three machine learning methods for G9a inhibitors discovery using PubChem and scikit-learn.

In light of the increasing interest in G9a's role in neuroscience, three machine learning (ML) models, that are time efficient and cost effective, were developed to support researchers in this area. The models are based on data provided by PubChem and performed by algorithms interpreted by the scikit-learn Python-based ML library. The first ML model aimed to predict the efficacy magnitude of active G9a inhibitors.

Effect of Comprehensive Medication Management on Mortality in Critically Ill Patients.

Objectives: Medication management in the ICU is causally linked to both treatment success and adverse drug events. The purpose of this evaluation was to explore the effect of comprehensive medication management (CMM) on mortality in critically ill patients.

Design: Retrospective, observational, propensity-matched cohort study.

Unraveling the impact of human mobility on dengue outbreaks in Peninsular Malaysia: a Granger causality approach.

Dengue is a vector-borne disease transmitted by mosquito of the Aedes genus. This disease has caused financial burdens on public health systems with considerable morbidity and mortality. It became endemic in Southeast Asia and many countries worldwide.

Defected ground structure antenna array with metasurface inspired interlinked CSRR for 5G millimeter wave applications.

This paper introduces a high-performance antenna array optimized for 5G millimeter-wave (mm-Wave) applications, efficiently operating within the 25-30 GHz frequency range. Three integrated techniques enhance performance without increasing physical size: First, a Defected Ground Structure (DGS) with a 25 × 25 mm square slot and embedded interlinked complementary split-ring resonators (CSRRs) inspired by metasurface (MTS) principles broaden bandwidth and improve impedance matching. Second, four oblique slots (4.

YOLO-LeafNet: a robust deep learning framework for multispecies plant disease detection with data augmentation.

Plant diseases significantly harm crops, resulting in significant economic losses across the globe. In order to reduce the harm that these diseases produce, plant diseases must be diagnosed accurately and timely manner. In this work, a YOLO-LeafNet approach is proposed for detecting diseases from leaf images of four distinct species, namely, grape, bell pepper, corn, and potato.