Ross Gore

Multifactorial falls assessment is recommended for older adults at elevated risk but can generate numerous potentially overlapping measurements, increasing testing burden despite potentially diminishing informational returns as correlated measures are added. Characterizing how measures covary may inform subsequent efforts to evaluate more efficient assessment procedures. Community-dwelling older adults (n = 298) completed a single-visit assessment including the Physiological Profile Assessment (PPA), preferred- and maximal-speed walking, Montreal Cognitive Assessment (MoCA), and Modified Falls Efficacy Scale (MFES). Hierarchical agglomerative clustering was applied to 51 variables. Dendrogram fidelity, cluster separation, and resampling stability were evaluated using the cophenetic correlation coefficient (CCC), silhouette width, Jaccard coefficients, and adjusted Rand index (ARI). The dendrogram showed strong fidelity to the correlation-distance structure (CCC = 0.937). Among the examined partitions, k = 2 had the highest mean silhouette width (0.333), indicating weak separation, and demonstrated high resampling stability. This partition grouped MoCA and MFES items with visual, strength, and maximal balance-range measures, separately from gait, postural sway, reaction-time, sensory, and coordinated-stability measures. At k = 3, the latter grouping remained unchanged while MoCA items separated from the MFES and physiologic measures; however, this finer, hypothesis-guided partition had lower separation and lower stability for the MoCA-dominant cluster. These findings describe the covariance organization of this multifactorial assessment battery and provide candidate groupings for future research on measurement redundancy, information retention, and reproducibility across datasets.

Study Design: Prospective observational pilot study of adult spinal deformity surgery patients. Objective: To determine whether preoperative patient sentiment, quantified using a 21-class valence scale extending the CARP paradigm implemented through an offline Large Language Model, predicts postoperative outcomes. Summary of Background Data: Predicting adult spinal deformity surgery outcomes remains challenging with traditional clinical and radiographic parameters alone. Although patient psychological factors and expectations significantly influence postoperative satisfaction and quality of life, systematic approaches to capture these factors are underdeveloped. Offline Large Language Models offer scalable, privacy-preserving psychological risk stratification. Materials and Methods: We prospectively enrolled 18 patients undergoing adult spinal deformity surgery. Seven structured open-ended interview questions administered preoperatively were analyzed using a 21-class sentiment framework (CARP paradigm, −1.0 to +1.0 scale) implemented through Qwen 2.5 32B. This on-premise approach ensures HIPAA compliance without transmitting patient data externally. We assessed 28 validated outcome measures (EQ-5D domains, Neck Disability Index [NDI], SRS-22 components) preoperatively and at 12-month follow-up. Pearson correlation analysis quantified relationships between preoperative sentiment scores and postoperative outcome changes. Results: Preoperative sentiment demonstrated strong predictive associations with postoperative outcomes. Daily life impact sentiment (Question 1) showed the strongest predictive power with 14 significant correlations ( P ≤0.05) across 28 outcome measures. The strongest correlation was between Question 1 sentiment and NDI change ( r =−0.786, P r |=0.408), followed by EQ-5D domains (mean | r |=0.232–0.247). Preoperative optimism/pessimism (Question 7) demonstrated 15 significant correlations: pessimism predicted larger radiographic corrections, while optimism predicted superior functional restoration. Traditional radiographic parameters showed minimal sentiment correlation (mean | r | <0.15). Conclusions: Preoperative patient sentiment quantified through offline LLM-driven CARP analysis provides a rapid, scalable, privacy-preserving screening tool for identifying psychological risk. The open-source implementation enables real-time risk stratification without cloud dependencies. Integration of systematic sentiment assessment into preoperative evaluation may improve patient selection, enable personalized counseling, and identify high-risk psychological phenotypes requiring intervention. Prospective external validation in larger, multicenter cohorts is needed.

Quantum computing promises transformative advances, but recurring misconceptions and methodological pitfalls limit progress. This paper examines challenges that arise when traditional agent-based modeling implementations are directly mapped to quantum optimization frameworks like quadratic unconstrained binary optimization. Using Schelling’s segregation model as a case study, we show that directly translating agent-based modeling state observations into quadratic unconstrained binary optimization formulations not only fails to deliver quantum advantage, but also actively undermines computational efficiency. The fundamental issue is architectural. Traditional agent-based modeling frameworks observe the complete system state at each iteration, which can destroy quantum superposition. This motivates reconsidering the computational structure when seeking quantum advantage. Through analysis of Schelling’s segregation dynamics on lollipop networks, we demonstrate that abandoning the quadratic unconstrained binary optimization reduction paradigm and reconceptualizing the research question—from “simulate agent dynamics iteratively until convergence” to “compute the minimum number of agent moves required for global satisfaction”—enables a faster classical solution. This structural reconceptualization yields an algorithm that exploits network symmetries obscured in traditional agent-based modeling simulations and quadratic unconstrained binary optimization formulations. It establishes an algorithmic lower bound of O(n) for the decision problem on lollipop networks, which any quantum approach must outperform to achieve advantage. This result also extends the equilibrium characterization of Schelling’s model across various graph structures. Our work emphasizes that progress in quantum agent-based modeling should not force classical implementations into quantum frameworks. Instead, it should focus on clarifying when quantum advantage is structurally possible, developing best-in-class classical baselines, and fundamentally reformulating research questions rather than preserving classical iterative paradigms.

Background/Objectives: Accurate assessment of neuromuscular reflexes, such as the Hoffmann reflex (H-reflex), plays a critical role in sports science, rehabilitation, and clinical neurology. Conventional interpretation of H-reflex electromyography (EMG) waveforms is subject to inter-rater variability and interpretive bias, limiting reliability and standardization. This study aims to develop an automated, interpretable, and robust agentic AI–driven framework for H-reflex waveform analysis. Methods: We propose a fine-tuned Vision–Language Model (VLM) consortium combined with a reasoning Large Language Model (LLM)–enabled decision support system for automated H-reflex interpretation. Multiple VLMs were fine-tuned on curated datasets of H-reflex EMG waveform images annotated with expert clinical observations, recovery timelines, and athlete metadata. The VLM outputs were aggregated using a consensus-based strategy and further refined by a specialized reasoning LLM to ensure coherent, transparent, and explainable diagnostic assessments. Model fine-tuning employed Low-Rank Adaptation (LoRA) and 4-bit quantization to enable efficient deployment on consumer-grade hardware. Results: Experimental evaluation demonstrated that the proposed hybrid system delivers accurate, consistent, and clinically interpretable assessments of neuromuscular states, including fatigue, injury, and recovery, directly from EMG waveform images and contextual metadata. Compared with baseline models, the fine-tuned VLM consortium exhibited substantially improved precision, consistency, and contextual awareness, while the reasoning LLM enhanced diagnostic coherence through cross-model consensus and structured reasoning, thereby supporting responsible and explainable AI-driven decision making. Conclusions: This work presents, to the authors’ knowledge, the first integration of a responsible and explainable AI-driven decision support system for H-reflex analysis. The proposed framework advances the automation and standardization of neuromuscular diagnostics and establishes a foundation for next-generation AI-assisted decision support systems in sports performance monitoring, rehabilitation, and clinical neurophysiology.

Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these systems enable powerful new capabilities, increasing autonomy introduces critical challenges related to explainability, accountability, robustness, and governance, especially when agent outputs influence downstream actions or decisions. Existing agentic AI implementations often emphasize functionality and scalability, yet provide limited mechanisms for understanding decision rationale or enforcing responsibility across agent interactions. This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic workflows based on multi-model consensus and reasoning-layer governance. In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context, explicitly exposing uncertainty, disagreement, and alternative interpretations. A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions. Explainability is achieved through explicit cross-model comparison and preserved intermediate outputs, while responsibility is enforced through centralized reasoning-layer control and agent-level constraints. We evaluate the architecture across multiple real-world agentic AI workflows, demonstrating that consensus-driven reasoning improves robustness, transparency, and operational trust across diverse application domains. This work provides practical guidance for designing agentic AI systems that are autonomous and scalable, yet responsible and explainable by construction.

Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language Models(LLMs), tool-augmented capabilities, orchestration logic, and external system interactions to form dynamic pipelines capable of autonomous decision-making and action. As adoption accelerates across industry and research, organizations face a central challenge: how to design, engineer, and operate production-grade agentic AI workflows that are reliable, observable, maintainable, and aligned with safety and governance requirements. This paper provides a practical, end-to-end guide for designing, developing, and deploying production-quality agentic AI systems. We introduce a structured engineering lifecycle encompassing workflow decomposition, multi-agent design patterns, Model Context Protocol(MCP), and tool integration, deterministic orchestration, Responsible-AI considerations, and environment-aware deployment strategies. We then present nine core best practices for engineering production-grade agentic AI workflows, including tool-first design over MCP, pure-function invocation, single-tool and single-responsibility agents, externalized prompt management, Responsible-AI-aligned model-consortium design, clean separation between workflow logic and MCP servers, containerized deployment for scalable operations, and adherence to the Keep it Simple, Stupid (KISS) principle to maintain simplicity and robustness. To demonstrate these principles in practice, we present a comprehensive case study: a multimodal news-analysis and media-generation workflow. By combining architectural guidance, operational patterns, and practical implementation insights, this paper offers a foundational reference to build robust, extensible, and production-ready agentic AI workflows.

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these systems introduce novel and evolving security challenges, including prompt injection attacks, context poisoning, model manipulation, and opaque agent-to-agent communication, that are not effectively captured by traditional threat modeling frameworks. In this paper, we introduce ASTRIDE, an automated threat modeling platform purpose-built for AI agent-based systems. ASTRIDE extends the classical STRIDE framework by introducing a new threat category, A for AI Agent-Specific Attacks, which encompasses emerging vulnerabilities such as prompt injection, unsafe tool invocation, and reasoning subversion, unique to agent-based applications. To automate threat modeling, ASTRIDE combines a consortium of fine-tuned vision-language models (VLMs) with the OpenAI-gpt-oss reasoning LLM to perform end-to-end analysis directly from visual agent architecture diagrams, such as data flow diagrams(DFDs). LLM agents orchestrate the end-to-end threat modeling automation process by coordinating interactions between the VLM consortium and the reasoning LLM. Our evaluations demonstrate that ASTRIDE provides accurate, scalable, and explainable threat modeling for next-generation intelligent systems. To the best of our knowledge, ASTRIDE is the first framework to both extend STRIDE with AI-specific threats and integrate fine-tuned VLMs with a reasoning LLM to fully automate diagram-driven threat modeling in AI agent-based applications.

Software services are crucial for reliable communication and networking; therefore, Site Reliability Engineering (SRE) is important to ensure these systems stay reliable and perform well in cloud-native environments. SRE leverages tools like Prometheus and Grafana to monitor system metrics, defining critical Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for maintaining high service standards. However, a significant challenge arises as many developers often lack in-depth understanding of these tools and the intricacies involved in defining appropriate SLIs and SLOs. To bridge this gap, we propose a novel SRE platform, called SRE-Llama, enhanced by Generative-AI, Federated Learning, Blockchain, and Non-Fungible Tokens (NFTs). This platform aims to automate and simplify the process of monitoring, SLI/SLO generation, and alert management, offering ease in accessibility and efficy for developers. The system operates by capturing metrics from cloud-native services and storing them in a time-series database, like Prometheus and Mimir. Utilizing this stored data, our platform employs Federated Learning models to identify the most relevant and impactful SLI metrics for different services and SLOs, addressing concerns around data privacy. Subsequently, fine-tuned Meta's Llama-3 LLM is adopted to intelligently generate SLIs, SLOs, error budgets, and associated alerting mechanisms based on these identified SLI metrics. A unique aspect of our platform is the encoding of generated SLIs and SLOs as NFT objects, which are then stored on a Blockchain. This feature provides immutable record-keeping and facilitates easy verification and auditing of the SRE metrics and objectives. The automation of the proposed platform is governed by the blockchain smart contracts. The proposed SRE-Llama platform prototype has been implemented with a use case featuring a customized Open5GS 5G Core.

The diagnosis of most mental disorders, including psychiatric evaluations, primarily depends on dialogues between psychiatrists and patients. This subjective process can lead to variability in diagnoses across clinicians and patients, resulting in inconsistencies and challenges in achieving reliable outcomes. To address these issues and standardize psychiatric diagnoses, we propose a Fine-Tuned Large Language Model (LLM) Consortium and OpenAI-gpt-oss Reasoning LLM-enabled Decision Support System for the clinical diagnosis of mental disorders. Our approach leverages fine-tuned LLMs trained on conversational datasets involving psychiatrist-patient interactions focused on mental health conditions (e.g., depression). The diagnostic predictions from individual models are aggregated through a consensus-based decision-making process, refined by the OpenAI-gpt-oss reasoning LLM. We propose a novel method for deploying LLM agents that orchestrate communication between the LLM consortium and the reasoning LLM, ensuring transparency, reliability, and responsible AI across the entire diagnostic workflow. Experimental results demonstrate the transformative potential of combining fine-tuned LLMs with a reasoning model to create a robust and highly accurate diagnostic system for mental health assessment. A prototype of the proposed platform, integrating three fine-tuned LLMs with the OpenAI-gpt-oss reasoning LLM, was developed in collaboration with the U.S. Army Medical Research Team in Norfolk, Virginia, USA. To the best of our knowledge, this work represents the first application of a fine-tuned LLM consortium integrated with a reasoning LLM for clinical mental health diagnosis paving the way for next-generation AI-powered eHealth systems aimed at standardizing psychiatric diagnoses.