Biology Methods and Protocols

BackgroundPostoperative delirium is a common complication in surgical patients, and is associated with a multitude of negative outcomes, including mortality, dementia, and increased healthcare costs. Therefore, a better understanding of what factors contribute to postoperative delirium, especially those that can be easily obtained, is important. MethodsWe conducted a retrospective cohort study using patients from the Medical Information Mart for Intensive Care (MIMIC)-IV database. Adult patient...

Digital breast tomosynthesis (DBT) is a powerful imaging modality that allows for improved lesion visibility, characterization, and localization compared to conventional two-dimensional digital mammography. DBT has been increasingly adopted in screening and diagnostic settings globally, particularly for women with dense breast tissue where tissue overlap presents a significant diagnostic challenge. Here we describe DBT-2026, a real world imaging dataset with 558 DBT exams from 558 patients with ...

ObjectiveThis study investigates whether incorporating physiological coupling concepts into neural network design can support stable and interpretable feature learning for histopathological image classification under limited data conditions. MethodsA physiologically inspired architecture, termed CardioPulmoNet, is introduced to model interacting feature streams analogous to pulmonary ventilation and cardiac perfusion. Local and global tissue features are integrated through bidirectional multi-h...

BackgroundPropofol dosing guidelines recommend age-based reductions because hypnotic sensitivity increases in older adults. Most real-world evaluations of induction practice, however, have relied on total weight-normalized dose (mg/kg) rather than estimating cerebral exposure using pharmacokinetic models. Because age-related pharmacokinetic changes alter the relationship between administered dose and peak effect-site concentration (Ce,max), mg/kg surrogates may misrepresent true age-dependent ex...

AbstractAccurate health information is ineffective if patients cannot understand it. Large Language Model (LLM) health research values veridical precision; however, linguistic accessibility remains an under-examined component of output quality and usability. This study investigated two sources of variability in readability classification: differences across LLM systems and across readability metrics. The analysis tested 1,120 data points from seven systems in English and Portuguese, comparing ba...

BackgroundElectronic Health Records(EHR) are very crucial for Clinical Decision Support Systems and for proper care to be delivered to ICU heart failure patients, there is often missing data due to monitoring device errors thus the need for robust imputation methodologies. ObjectiveTo compare and evaluate three different methodologies for imputing missing data for heart failure patients from the MIMIC-III database: Denoising Autoencoder (DAE), Self-Attention Imputation for Time Series (SAITS), ...

BackgroundDelivering timely, high-quality feedback on resident scholarly projects is labour-intensive, especially in large programmes. We developed an AI-assisted evaluation system, powered by the open-weight LLaMA-3.1 large-language model (LLM), to generate formative feedback on Family Medicine residents scholarly projects and compared its performance with expert human evaluators. MethodsWe evaluated whether the AI-generated feedback achieves comparable quality to expert feedback. The tool ing...

BackgroundQuality measurement in intensive care emphasizes task completion--whether assessments were documented and protocols followed. Electronic health record (EHR) systems capture these signals in real time, yet current metrics cannot distinguish task completion from cognitive clinical engagement. A prior analysis demonstrated that omission of orientation assessment predicted a 4.29-fold increase in hospital mortality among low-acuity ICU patients [1]. Whether combining this marker with routi...

Cox proportional hazard regressions are frequently employed to develop prognostic models for time-to-event data, considering both patient-specific and disease-specific characteristics. In high-dimensional clinical modeling, these biological features can exhibit high collinearity due to inter-feature relationships, potentially causing instability and numerical issues during estimation without regularization. For rare diseases such as acute myeloid leukemia (AML), the sparsity and scarcity of data...

BackgroundRetrieval-augmented generation (RAG) frameworks such as RAPID [1] have demonstrated that staged planning and retrieval grounding improve long-form text generation. However, most implementations remain similarity-driven and open-domain, lacking the epistemic safeguards required for biomedical synthesis, where mechanistic completeness, temporal governance, traceability, and explicit gap classification are essential. ObjectiveTo develop and evaluate a topology-aware, graph-augmented retr...

IntroductionNeurocognitive impairment (NCI) remains common among people living with HIV (PWH), particularly in low- and middle-income countries where accurate diagnostic tools are limited. In Peru, the lack of locally validated neuropsychological (NP) normative data in Spanish poses a major barrier to diagnosing HIV-associated NCI, especially among PWH who develop NCI at younger ages. This study aimed to develop regression-based NP norms for young and middle-aged Spanish-speaking adults in Lima,...

We propose a lesion-centric phenotype learning pipeline for interpretable breast ultrasound (BUS). Predicted lesion masks are used for mask-weighted pooling of segmentation-encoder latents, producing compact embeddings that suppress background influence; a lightweight calibration step improves cross-dataset consistency. We cluster embeddings to discover latent phenotypes and relate phenotype structure to morphology descriptors (compactness, boundary sharpness). On BUSI and BUS-UCLM with external...

Cross-device medical federated learning--where individual patients participate directly rather than institutions--poses a unique challenge: each client holds only a few samples, often just one (e.g., a single diagnostic record), leaving insufficient local data for gradient computation. Existing approaches, such as Secure Aggregation, require client-to-client coordination impractical for intermittently available mobile devices, while homomorphic encryption introduces substantial computational ove...

BackgroundArtificial intelligence (AI) has emerged as a promising tool for interpreting 12-lead electrocardiograms (ECGs), with the potential to enhance diagnostic accuracy for arrhythmia detection. However, published studies vary widely in methodology and validation strategy, warranting a quantitative synthesis of diagnostic performance. MethodsA systematic review and meta-analysis was conducted according to the PRISMA-DTA 2018 guidelines and registered in PROSPERO (CRD420251027264). Searches ...

BackgroundEpigenetic clocks based on DNA methylation (DNAm) provide quantitative indicators of biological aging. However, the extent to which diverse lifestyle factors influence DNAm-based aging measures remains unclear, especially in Japanese populations. We aimed to evaluate the associations between 52 lifestyle-related factors and multiple epigenetic aging indicators, including six DNAm ages (Horvath, Hannum, PhenoAge, GrimAge, GrimAge v2, and PCPhenoAge specific to Japanese Population), the ...

BackgroundBiomedical Large Language Models (LLMs) combined with prompt engineering offer domain-specific reasoning, yet their application to individual-level causality assessment remains unexplored. This study evaluated five combinations of biomedical LLMs, prompting strategies, and causality algorithms by comparing their agreement with two human expert evaluators. Research design and methodsA total of 150 Individual Case Safety Reports (ICSRs) were analyzed: 140 reports from Food and Drug Admi...

Large language models (LLMs) are increasingly transforming scientific workflows, yet their application to rigorous evidence synthesis remains underexplored. Through the execution of a single Python script, we present a fully automated pipeline leveraging the Claude API to generate systematic reviews from literature search through manuscript completion without human intervention. Our pipeline processes hundreds of papers through iterative API calls for inclusion evaluation, information extraction...

Rare diseases affect over 300 million people worldwide, yet patients often endure years-long diagnostic delays that limit timely intervention and trial opportunities. Computational rare disease recognition (RDR) remains constrained by knowledge resources that are often incomplete, heterogeneous, and dependent on extensive multi-disciplinary expert curation that cannot scale. Large language models (LLMs) applied directly for end-to-end diagnosis or disease discrimination face similar knowledge bo...

BackgroundSystematic reviews (SRs) are essential for evidence-based medicine but require extensive time and resources for abstract screening. Large language models (LLMs) offer potential for automating this process, yet concerns about data privacy, intellectual property protection, and reproducibility limit the use of cloud-based solutions in research settings. ObjectiveTo evaluate the performance of a locally deployed 20-billion parameter LLM for automated abstract screening in systematic revi...

A critical challenge in endocrine neurosurgery is intraoperative discrimination between normal pituitary tissue and pituitary neuroendocrine tumors (PitNETs). Suggesting the universal persistence of near-infrared autofluorescence (NIRAF) in endocrine organs and inspired by routine clinical use of NIRAF for parathyroid gland identification, we discovered that pituitary NIRAF can be employed for label-free transsphenoidal surgery guidance. Ex vivo confocal spectral imaging of 33 specimens identifi...