Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture

• URL: http://arxiv.org/abs/2604.27045v1
• Date: Wed, 29 Apr 2026 17:59:28 GMT
• Title: Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture
• Abstract summary: General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement.<n>We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record.<n>We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions.
• Score: 71.46525715889656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critical challenge: reconciling two imperfect sources of truth. The patient's evolving self-report is current but prone to recall bias, while the Electronic Health Record (EHR) is medically validated but frequently stale. General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement, a pattern that risks safety failures when applied to clinical data. We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record (FHIR), governed by a dedicated Reconciliation Engine that evaluates every extracted memory against the patient's FHIR profile and classifies discrepancies by type, severity, and the specific FHIR resources involved. We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions, using a hybrid dataset that interleaves real provider-patient transcripts with synthetic, FHIR-grounded clinical scenarios. In isolated testing, the engine detects 84.4% of designed clinical discrepancies with 86.7% safety-critical recall. By coupling extraction and reconciliation evaluation on the same data, we directly quantify a 13.6% error cascade, tracing the degradation to clinical details lost during memory extraction from unstructured conversation rather than to downstream classification errors. These findings establish that validating patient-reported memories against clinical records is both feasible and necessary for safe deployment of longitudinal health agents.

Related papers

• CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR [15.66578453195388]
  CliniCARE-Bench is a benchmark for retrospective clinical audit.<n>25 clinician-validated scenarios instantiated as 750 patient-specific cases over real-patient-derived MIMIC-IV data.<n>System returns one of four verdicts: Yes, No, Indeterminate: Lack of Data, or Indeterminate: Medically Ambiguous.
  arXiv  Detail & Related papers  (2026-08-07T22:39:13Z)
• VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards [1.5504500166769226]
  We introduce VISTA Architect, a database-oriented AI architecture for integrating large language models with longitudinal electronic health records.<n>At ingestion, it transforms complex clinical documentation into a persistent, provenance-linked knowledge graph.<n>Across 1,180 patients, VISTA Architect achieved 96.4% accuracy on 15 tumor board-salient variables.
  arXiv  Detail & Related papers  (2026-06-21T22:09:12Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics [17.682803546212824]
  We propose a Longitudinal Intra-Patient Tracking (LIPT) scheme to capture the trajectory of relative symptomatic changes within individuals.<n>Central to this framework is a Sequential Personalised (PSE) which transforms longitudinal speech recordings into context-aware latent representations.<n> Experimental results from a cohort of 225 patients demonstrate that the LIPT paradigm significantly outperforms the classic cross-sectional approaches.
  arXiv  Detail & Related papers  (2026-02-23T10:19:17Z)
• Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation [97.36081721024728]
  We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations.<n>Our benchmark unifies three types of medical data for open-ended diagnostic generation.<n>We present MedConf, an evidence-grounded linguistic self-assessment framework.
  arXiv  Detail & Related papers  (2026-01-22T04:51:39Z)
• AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization [28.032865974227875]
  RetroSum is a framework that unifies a retrospective summarization mechanism with an evolving experience strategy.<n>It achieves performance gains of up to 29.16% over competitive baselines, while significantly decreasing total interaction errors by up to 92.3%.
  arXiv  Detail & Related papers  (2026-01-20T12:48:04Z)
• WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue [3.468314243424983]
  Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue.<n>Standard evaluations still rely heavily on Error Error Rate (WER)<n>This paper challenges that standard, investigating whether WER or other common metrics correlate with clinical impact of transcription errors.
  arXiv  Detail & Related papers  (2025-11-20T16:59:20Z)
• HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation [17.45722229030237]
  We propose Hierarchical Ontology and Network Refinement for Robust Medication Recommendation (HiRef)<n>We embed entities in hyperbolic space, which naturally captures tree-like relationships and enables knowledge transfer through shared ancestors.<n>Our model achieves strong performance on EHR benchmarks (MIMIC-III and MIMIC-IV) and maintains high accuracy under simulated unseen-code settings.
  arXiv  Detail & Related papers  (2025-08-14T07:55:03Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [50.56875995511431]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)
• COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching [70.08786840301435]
  We propose CrOss-Modal PseudO-SiamEse network (COMPOSE) to address these challenges for patient-trial matching. Experiment results show COMPOSE can reach 98.0% AUC on patient-criteria matching and 83.7% accuracy on patient-trial matching.
  arXiv  Detail & Related papers  (2020-06-15T21:01:33Z)

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.