Background: Rule-based multi-agent system (MAS) architectures for healthcare coordination rely on hardcoded decision trees that cannot generalise to novel clinical scenarios or self-correct reasoning errors. These limitations are acute in surgical continuum care, where patients traverse presurgical risk stratification, intraoperative monitoring, postsurgical ICU, ward care, and remote rehabilitation over days to weeks—a complexity no fixed-policy agent architecture can address without prohibitive rule engineering. Objective: We present the first agentic large language model (LLM) framework for autonomous end-to-end surgical continuum monitoring, superseding the prior rule-based MAS Digital Twin. Six ReAct-driven tool-use agents replace fixed-policy agents with dynamic reasoning, multi-hop evidence retrieval, and Reflexion self-correction while maintaining mandatory confidence-gated Human-in-the-Loop (HITL) gating at every care-pathway-modifying decision. Methods: The framework is grounded in the ReAct paradigm and Reflexion self-evaluation, embedded within the DETER Digital Twin state engine S(t). Each agent is specified by a ReAct loop signature, a ten-function clinical tool registry, and confidence-gated HITL escalation logic. Inter-agent coordination replaces the rule-based Priority Queue Manager with an LLM-mediated Coordination Supervisor Agent reasoning over competing resource requests. Results: The framework delivers: (i) six formally specified ReAct-loop agents with explicit tool registries and authorisation boundaries; (ii) a confidence-gated HITL architecture that reduces alert fatigue while preserving safety for ambiguous clinical scenarios; (iii) an extended conflict resolution function P(p,t,context) incorporating surgical phase and DETER deterioration trajectory gradient; (iv) Reflexion self-correction with a formal N_max = 2 termination condition and Clinical Factuality Verification Layer; and (v) a multi-phase Digital Twin state engine extending S(t) to the full surgical continuum. Conclusions: The proposed framework represents a fundamental architectural departure from rule-based clinical AI—from hardcoded policies to dynamic reasoning, from static retrieval to multi-hop tool-use chains, and from fixed escalation thresholds to confidence-gated self-evaluation—providing a formally specified, clinically deployable foundation for next-generation autonomous surgical care coordination.

Background: Post-surgical cardiovascular monitoring places a heavy information burden on clinical teams, requiring rapid synthesis of patient history, intraoperative data, monitoring streams, and surgical outcomes evidence. Existing clinical decision support systems handle this integration poorly, and most offer little visibility into their reasoning. We present a Retrieval-Augmented Generation (RAG) architecture designed specifically for this domain, with a focus on evidence traceability and practical workflow integration. Methods: We developed a three-layer RAG architecture comprising: a retrieval layer to create 768-dimensional representations of clinical scenarios; an augmentation layer employing context-aware filtering and machine learning algorithms to integrate patient-specific data with retrieved evidence; and a generative layer using fine-tuned language models to synthesise actionable clinical recommendations. Results: An evaluation framework is proposed to assess the technical performance and clinical applicability of RAG architecture. The evaluation methodology encompasses technical validation of system components, assessment of clinical workflow integration potential, and analysis of interpretability features essential for healthcare deployment. Conclusions: We describe a RAG architecture for post-surgical cardiovascular monitoring in which every recommendation is linked to retrievable source documents, making the reasoning visible and challengeable. A structured evaluation framework is proposed to guide the system towards clinical validation.

Background: Post-surgical cardiovascular monitoring places a heavy information burden on clinical teams, requiring the rapid synthesis of patient history, intraoperative data, monitoring streams, and surgical outcome evidence. Existing clinical decision support systems handle this integration poorly, and most offer little visibility into their reasoning. We present a Retrieval-Augmented Generation (RAG) architecture designed specifically for this domain, with a focus on evidence traceability and practical workflow integration. Methods: We describe a three-layer RAG architecture comprising a retrieval layer that creates 768-dimensional representations of clinical scenarios; an augmentation layer using a stacking ensemble (Random Forest and XGBoost base learners with a logistic-regression meta-learner) to integrate patient-specific data with retrieved evidence and produce calibrated probability estimates; and a generative layer using a fine-tuned BERT classifier together with Gemini 2.5 Pro to synthesise actionable clinical recommendations. Components were prototyped on publicly available, de-identified data from MIMIC-III and the MIMIC-III-Ext-PPG benchmark to verify pipeline integrity. Proposed Evaluation Framework: This paper presents a system architecture rather than a clinically validated implementation. We outline a structured evaluation framework to assess the technical performance and clinical applicability of the RAG architecture, encompassing the technical validation of system components, expert assessment of clinical workflow integration potential, and analysis of interpretability features essential for healthcare deployment. Specific technical targets include retrieval precision >90% for relevant evidence, query response time 85% from expert review. Conclusions: We describe a RAG architecture for post-surgical cardiovascular monitoring in which every recommendation is linked to retrievable source documents, making the reasoning visible and challengeable. A structured evaluation framework is proposed to guide the system towards clinical validation.

MethodsSix autonomous agents — Dispatch, Pre-Hospital Triage, ED Triage (ERTRIAGE machine learning CDS), Monitoring, Resource Allocation, and Discharge/Admit — were formally specified with HL7 FHIR R4 interoperability, coordinated via a three-tier hierarchy and RAG-enhanced Decision Support System. ERTRIAGE is operationally active at NIMTS Hospital, Athens (>50% of the ED Triage Agent specification). Feasibility was evaluated by Discrete-Event Simulation against 228 retrospective NIMTS patient records (five replications, 95% CI).ResultsAll ACEP/RCEM targets were met: door-to-triage 2.58 ± 0.24 min, triage-to-clinic 8.12 ± 0.13 min (95% CI: 7.76–8.48 min), admission rate 15.7%, undertriage reduced from 6.0% to 3.3% (45% relative). The Resource Allocation Agent achieved 6% imaging and 8% biochemical order reduction (25% panel intensity reduction per order), saving €1,391 per cohort (~€2.2 M annually).ConclusionsThe formally specified MAS DT framework, with partial operational deployment at NIMTS Hospital, achieves clinically meaningful pre-hospital-to-ED coordination. Prospective clinical validation is the immediate next step.