A comprehensive performance evaluation of seven state-of-the-art large language models (LLMs) compared to human resident benchmarks on ophthalmology board exam questions. Furthermore, this study aims to define current model strengths and limitations while validating an assessment tool for clinicians to evaluate model-generated outputs. Seven LLMs were assessed: ChatGPT-5, ChatGPT-4, Gemini 2.5 Pro, Gemini 2.5 Flash, Claude Sonnet 4.5, Grok-4-Fast-Reasoning, and Perplexity Sonar Pro. A dataset of 1,037 Israeli ophthalmology board questions (2020–2025) was manually categorized by question type (logical vs. informative), image modality, and 12 subspecialties. Models were evaluated for accuracy compared with resident performance, response latency, question difficulty, and self-assessed confidence. Performance varied substantially across models. Gemini 2.5 Pro achieved the highest accuracy, followed by ChatGPT-5, both outperforming residents. Accuracy declined significantly with increasing question difficulty (Very Hard vs. Easy: aOR 0.28, 95
Markov chains based on spanning trees have been hugely influential in algorithms for assessing fairness in political redistricting. The input graph represents the geographic building blocks of a jurisdiction. The goal is to output a large ensemble of random graph partitions, which is done by drawing and splitting random spanning trees. Crucially, these subtrees must be balanced, since political districts are required to have equal population. The Up-Down walk (on trees or forests) repeatedly adds a random edge then deletes a random edge to produce a new tree or forest; it can be used to efficiently generate a large ensemble, but the rejection rate to maintain balance grows exponentially with the number of parts. ReCom, the most widely-used class of Markov chains, circumvents this complexity barrier by merging and splitting pairs of districts at a time. This runs fast in practice but can have trouble exploring the state space. To overcome these efficiency and mixing barriers, we propose a new Markov chain called the Balanced Up-Down (BUD) walk. The main idea is to run the Up-Down walk on the space of trees, but require all steps to preserve the property that the tree is splittable into balanced subtrees. The BUD walk samples from a known invariant measure under exact balance. We prove that the BUD walk is irreducible in several cases, including a regime where ReCom is not irreducible. Running the BUD walk efficiently presents algorithmic challenges, especially when parts are allowed to deviate from their ideal size. A key subroutine is determining whether a tree is splittable into approximately-balanced subtrees. We give an improved analysis of an existing algorithm for this problem and prove that the associated counting problem is #P-complete. We empirically validate the usefulness of the BUD walk by comparing its performance to that of other existing methods for sampling partitions.
Developing diagnostic biomarkers for Alzheimer's disease (AD) is at the cutting edge of interdisciplinary research and technical advancement. This comprehensive analysis investigates potential options for improving diagnostic accuracy and early detection of AD. Identifying biomarkers other than Aβ and tau proteins, such as synaptic dysfunction markers and metabolic indicators, is a novel technique. Integrating multi-omics data provides a comprehensive picture of AD pathophysiology, assisting in the discovery of biomarkers and treatment targets. Advances in technology, notably nanotechnology and biosensors, show promise for highly sensitive and specific platforms capable of identifying AD-related biomarkers in physiological fluids. AI and machine learning algorithms are critical in analyzing large datasets, improving pattern identification, and increasing diagnostic accuracy. Predictive models based on various biomarkers and clinical data open the way for personalized medicine methods in the treatment of AD. More advancements in PET and MRI tracers are required for targeted and sensitive imaging of specific AD-related clinical alterations. Wearing gadgets and seeing digital health signs have helped us to find diseases early and track them over time. They even allow monitoring from afar and all the time. This comprehensive review brings together new developments and teamwork across different fields. In this way, it guides to enhance how to identify AD. By mixing these new methods, we aim to change the diagnosis of AD early and accurately. This allows us to focus on treatments and push forward new cures for AD.
BACKGROUND:Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by accumulation of amyloid-β (Aβ) plaque, tangles of tau neurofibres, chronic neuroinflammation, and dysfunction of the blood brain barrier (BBB). Monoclonal antibodies targeting Aβ and tau have focused disease-modifying potential, but their clinical impact is limited in brain penetration, immunogenicity, amyloid-related imaging abnormalities (ARIA), high treatment costs, and the need for repeated intravenous administration. These limitations has lead to discover in antibody-based nanoparticle platforms as advanced delivery and diagnosis. OBJECTIVE:This review aims to evaluate antibody-based nanoparticles as emerging tools for the diagnosis and treatment of AD, focusing on nanoparticle design, antibody conjugation strategies, mechanisms of BBB transport, immune modulation, and current translational challenges. CURRENT EVIDENCE:Recent preclinical studies reflects that antibody-functionalized nanoparticles can improve target specificity, enhance BBB transport by receptor-mediated and adsorptive transcytosis, and modulate neuroinflammatory responses by microglial Fc-receptor engagement. Advances in nanoparticle materials including gold, magnetic iron oxide, polymeric, and lipid-based systems has applications in both therapy and molecular imaging using MRI and PET. Critical barriers including nanoparticle instability, immune clearance, antibody denaturation after conjugation, long-term toxicity, manufacturing scalability, and regulatory uncertainty for hybrid biologic nanomaterial products exist. CONCLUSION:Antibody-based nanoparticles represent promising but still evolving platform for precision diagnostics and targeted therapy in AD. While preclinical evidence is encouraging, successful clinical translation depends on standardized manufacturing, comprehensive safety evaluation, and well-designed trials. Future efforts focus on theranostic systems, multi-target antibody platforms addressing pathology, and regulatory frameworks supporting scalable and reproducible nanoparticle-based interventions.
Explainable machine learning techniques have gained increasing attention in engineering applications, especially in aerospace design and analysis, where understanding how input variables influence predictive models is essential. Partial Dependence Plots (PDPs) are widely used for interpreting black-box models by showing the average effect of an input variable on the prediction. However, their global sensitivity metric can be misleading when strong interactions are present, as averaging tends to obscure interaction effects. To address this limitation, we propose a global sensitivity metric based on Individual Conditional Expectation (ICE) curves. The method computes the expected feature importance across ICE curves, along with their standard deviation, to more effectively capture the influence of interactions. The proposed metrics are model-agnostic and can be applied to any predictive model, including but not limited to surrogate models. Furthermore, we provide a mathematical proof demonstrating that the PDP-based sensitivity is a lower bound of the proposed ICE-based metric under additive and multiplicative separability. In addition, we introduce an ICE-based correlation value to quantify how interactions modify the relationship between inputs and the output. Comparative evaluations were performed on three cases: a 5-variable analytical function, a 5-variable wind-turbine fatigue problem, and a 9-variable airfoil aerodynamics case, where ICE-based sensitivity was benchmarked against PDP, SHapley Additive exPlanations (SHAP), and Sobol’ indices. The results show that ICE-based feature importance provides richer insights than the traditional PDP-based approach, while visual interpretations from PDP, ICE, and SHAP complement one another by offering multiple perspectives.
