ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment

• URL: http://arxiv.org/abs/2608.06110v2
• Date: Tue, 11 Aug 2026 10:32:54 GMT
• Title: ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment
• Abstract summary: ECHO (Enhanced Care & Health Observer) is a locally-deployable conversational health assistant for long-term chronic care management.<n>ECHO integrates three complementary software modules developed under shared supervision as a unified system.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management. ECHO integrates three complementary software modules developed under shared supervision as a unified system. The core module is an agentic chatbot built on a ReAct loop orchestrated via LangGraph, equipped with 17 clinical tools and a temporal knowledge graph for persistent cross-session memory; it achieves a 94.9% tool-execution pass rate across a 59-scenario benchmark with GPT-5 Mini. A two-stage hybrid safety layer intercepts all incoming queries: a rule-based layer handles explicit crisis signals and jailbreak attempts in under 1ms, while a signed graph neural network (GNN) with APPNP-style propagation classifies boundary cases by clinical intent, achieving 88.8% accuracy and 90.6% unsafe recall on a 2,537-query annotated Turkish health dataset while outperforming zero-shot LLM baselines including Llama 3.3 70B. A multimodal speech assessment module combining Whisper acoustic encoding and BERT text encoding with cross-attention fusion estimates emotion, depression, and pain, reaching a mean macro F1 of 0.652. The full system is implemented as a web application that can run entirely on consumer hardware, with no patient data transmitted to external services, supporting compliance with GDPR and KVKK.

Related papers

• Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G [90.42669277637026]
  Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence.<n>This article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks.
  arXiv  Detail & Related papers  (2026-09-09T01:36:44Z)
• LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents [56.902747731541695]
  We present LEGO-RL, a framework that bridges native coding-agent harnesses with scalable policy-gradient optimization.<n>We evaluate LEGO-RL by training the sparse MoE model Qwen3.5-35B-A3B with GSPO across three native coding-agent harnesses.
  arXiv  Detail & Related papers  (2026-08-18T05:34:35Z)
• Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence [45.78409219344429]
  Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations undermine trustworthy use.<n>We propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection.<n>We conduct systematic evaluations on 2 tasks and 5 datasets using textttLLaVA-1.5-7B, texttLLaVA-Med-1.5-7B, texttQwen3-VL-8B/32B, and textttInternVL
  arXiv  Detail & Related papers  (2026-06-30T08:07:25Z)
• Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography [75.7789001619107]
  Vision-language pre-training holds great promise for general-purpose medical AI.<n>We propose a tailored framework featuring three key components.<n>A diagnosis-aware prompt strategy employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap.
  arXiv  Detail & Related papers  (2026-06-24T08:24:45Z)
• SigmaMedStat: Temporal Signal Modeling for ICU False Alarm Reduction [0.0]
  This paper presents SigmaMedStat, a machine learning system that evaluates the trustworthiness of physiological alarm signals before clinical action is taken.<n>Four approaches were evaluated on the PhysioNet/Computing in Cardiology Challenge 2015 dataset of 498 four-channel ICU alarm recordings.
  arXiv  Detail & Related papers  (2026-05-28T01:52:05Z)
• ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data [1.995753801570114]
  We propose an action-conditioned latent world-model framework for learning patient trajectories from longitudinal care data.<n>We instantiate CMWM for annual estimated glomerular filtration rate (eGFR) trajectory forecasting in chronic kidney disease (CKD)<n>The framework is not CKD-specific its architecture, loss design, and training protocol apply to any chronic condition that can be cast as periodic clinical state interleaved with structured and conversational interventions.
  arXiv  Detail & Related papers  (2026-05-21T03:50:17Z)
• ABRA: Agent Benchmark for Radiology Applications [46.39696206872633]
  We introduce ABRA, a radiology-agent benchmark in which the agent operates a viewer and an Orthanc DICOM server.<n>ABRA contains 655 655 generated tasks across three difficulty tiers and eight types.<n>Each episode is scored along Planning, Execution, and Outcome (Blueth et al., 2025) by tasktype-specific automatic scorers.
  arXiv  Detail & Related papers  (2026-05-11T20:34:20Z)
• MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic [1.827510863075184]
  The Model Context Protocol (MCP) has become a widely adopted interface for agents to invoke external tools.<n> MCP is presented as an attack framework for MCP tool-call traffic that encodes each agent session as a graph.
  arXiv  Detail & Related papers  (2026-05-11T14:55:48Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• Analyzing Healthcare Interoperability Vulnerabilities: Formal Modeling and Graph-Theoretic Approach [0.6875312133832079]
  The research on detecting a race condition only targets the OS kernel.<n>The gap in the research in this area is addressed through the introduction of FHIR Resource Access Graph (FRAG)<n>Three clinically relevant race condition classes are formally specified: Simultaneous Write Conflict (SWC), TOCTOU Authorization Violation (TAV), and Cascading Update Race (CUR)<n>FRAG attains a 90.0% F1 score vs. 25.5% for the baseline, a 64.5 pp improvement.
  arXiv  Detail & Related papers  (2026-04-03T13:51:43Z)
• ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents [45.88028371034407]
  ElephantBroker is an open source cognitive runtime that unifies a Neo4j knowledge graph with a Qdrant vector store.<n>The system implements a complete cognitive loop (store, retrieve, score, compose, protect, learn) comprising a hybrid five source retrieval pipeline.
  arXiv  Detail & Related papers  (2026-03-26T07:03:12Z)
• U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT [44.3806898357896]
  We propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy.<n>U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge.
  arXiv  Detail & Related papers  (2025-09-24T14:19:33Z)
• How Well Can Modern LLMs Act as Agent Cores in Radiology Environments? [54.36730060680139]
  RadA-BenchPlat is an evaluation platform that benchmarks the performance of large language models (LLMs) in radiology environments.<n>The platform also defines ten categories of tools for agent-driven task solving and evaluates seven leading LLMs.
  arXiv  Detail & Related papers  (2024-12-12T18:20:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.