Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations

• URL: http://arxiv.org/abs/2603.29893v1
• Date: Mon, 09 Feb 2026 05:43:32 GMT
• Title: Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations
• Abstract summary: We present a production-validated framework grounded in real-time signals from 115M+ live patient-AI interactions.<n>These in-the-wild cues reveal failure modes that curated data misses and provide actionable training and evaluation signals for safety and reliability.<n>We drive measurable gains in safety, documentation, task completion, and equity in building the safest generative AI solution for autonomous patient-facing care.
• Score: 10.699629636647414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Healthcare conversational AI agents shouldn't be optimized only for clean benchmark accuracy in production-first regime; they must be optimized for the lived reality of patient conversations, where audio is imperfect, intent is indirect, language shifts mid-call, and compliance hinges on how guidance is delivered. We present a production-validated framework grounded in real-time signals from 115M+ live patient-AI interactions and clinician-led testing (7K+ licensed clinicians; 500K+ test calls). These in-the-wild cues -- paralinguistics, turn-taking dynamics, clarification triggers, escalation markers, multilingual continuity, and workflow confirmations -- reveal failure modes that curated data misses and provide actionable training and evaluation signals for safety and reliability. We further show why healthcare-grade safety cannot rely on a single LLM: long-horizon dialogue and limited attention demand redundancy via governed orchestration, independent checks, and verification. Many apparent "reasoning" errors originate upstream, motivating vertical integration across contextual ASR, clarification/repair, ambient speech handling, and latency-aware model/hardware choices. Treating interaction intelligence (tone, pacing, empathy, clarification, turn-taking) as first-class safety variables, we drive measurable gains in safety, documentation, task completion, and equity in building the safest generative AI solution for autonomous patient-facing care. Deployed across more than 10 million real patient calls, Polaris attains a clinical safety score of 99.9%, while significantly improving patient experience with average patient rating of 8.95 and reducing ASR errors by 50% over enterprise ASR. These results establish real-world interaction intelligence as a critical -- and previously underexplored -- determinant of safety and reliability in patient-facing clinical AI systems.

Related papers

• PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents [5.247635961504091]
  PatientAgentBench benchmarks patient-facing agentic healthcare.<n>It evaluates a foundation model wrapped in an agent with a sandbox of healthcare tools, conversing with a simulated patient.<n>We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps.
  arXiv  Detail & Related papers  (2026-07-28T09:24:04Z)
• MedCTA: A Benchmark for Clinical Tool Agents [47.47354499871572]
  We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks.<n>MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools.<n>We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use.
  arXiv  Detail & Related papers  (2026-06-10T06:26:52Z)
• RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation [46.82418087865201]
  RealICU is a hindsight-annotated benchmark for evaluating large language models under realistic ICU conditions.<n>We release two datasets: RealICU-Gold with 930-window annotations from 94 MIMIC-IV patients, and RealICU-Scale with 11,862 windows extended by Oracle.
  arXiv  Detail & Related papers  (2026-05-13T13:52:42Z)
• Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment [56.62016795093786]
  Cerebra is an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis.<n>It supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete.<n>Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation.
  arXiv  Detail & Related papers  (2026-03-23T05:46:45Z)
• A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic [21.374164324051012]
  Articulate Medical Intelligence Explorer (AMIE)<n>100 adult patients completed an AMIE text-chat interaction up to 5 days before their appointment.<n>Human safety supervisors monitored all patient-AMIE interactions in real time.
  arXiv  Detail & Related papers  (2026-03-09T14:43:40Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Continuous Patient Monitoring with AI: Real-Time Analysis of Video in Hospital Care Settings [0.0]
  This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings.<n>The platform provides real-time insights into patient behavior and interactions through video analysis.<n>The dataset, compiled in collaboration with 11 hospital partners, encompasses over 300 high-risk fall patients.
  arXiv  Detail & Related papers  (2024-12-17T18:23:33Z)
• RAISE -- Radiology AI Safety, an End-to-end lifecycle approach [5.829180249228172]
  The integration of AI into radiology introduces opportunities for improved clinical care provision and efficiency. The focus should be on ensuring models meet the highest standards of safety, effectiveness and efficacy. The roadmap presented herein aims to expedite the achievement of deployable, reliable, and safe AI in radiology.
  arXiv  Detail & Related papers  (2023-11-24T15:59:14Z)
• U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging [61.6346401960268]
  We propose a machine learning pipeline called U-PASS tailored for clinical applications that incorporates uncertainty estimation at every stage of the process. We apply our uncertainty-guided deep learning pipeline to the challenging problem of sleep staging and demonstrate that it systematically improves performance at every stage.
  arXiv  Detail & Related papers  (2023-06-07T08:27:36Z)
• Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching [49.78442796596806]
  We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM) Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
  arXiv  Detail & Related papers  (2023-03-24T03:14:00Z)

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.