Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents

• URL: http://arxiv.org/abs/2609.09678v1
• Date: Wed, 09 Sep 2026 03:46:53 GMT
• Title: Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents
• Abstract summary: We present Cros, a risk-constrained stopping layer combining state-wise error ranking, policy design on disjoint development splits, and LTT-style exact tests of selective diagnostic error.<n>Its finite-sample guarantee requires the candidate family, testing rule, and any randomization to be frozen before calibration labels are accessed.
• Score: 8.33858460175655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical diagnosis agents must decide not only what test to request next, but also when to diagnose or defer. Existing agent benchmarks largely evaluate accuracy after fixed or unconstrained interaction, leaving autonomous stopping reliability implicit. We present Cros, a risk-constrained stopping layer combining state-wise error ranking, policy design on disjoint development splits, and LTT-style exact tests of selective diagnostic error and minimum autonomous coverage for complete sequential policies. Its finite-sample guarantee requires the candidate family, testing rule, and any randomization to be frozen before calibration labels are accessed. On a 1,834-episode MIMIC-derived abdominal-pain benchmark, the full ranker achieves exploratory state-error AUROC 0.853, compared with 0.715 for maximum class probability and 0.552 for the backbone's native stop score. On the previously viewed 367-episode evaluation split, analytically averaging over the frozen Cros weights yields 16.9% selective error at 78.8% coverage, cost 5.57, and 0.68 tests, versus 30.8% error at 100% coverage, cost 8.14, and 1.53 tests under native stopping. Forced continuation is non-monotone: error is 28.3% with HPI alone and 34.3% after full workup. However, the uniform-weight mixture ablation is cheaper on this viewed split despite missing the locked development margins, and Cros nominally satisfies the joint criterion in only 6 of 20 development resplits. Because evaluation labels were inspected during earlier development, these findings provide exploratory feasibility and audit evidence, not a confirmatory safety certificate.

Related papers

• Cross-dataset transportability of pediatric chest X-ray deep learning across three countries: discrimination, calibration, operating-point failure, and limited-label recovery [0.0]
  We evaluated a computational protocol that separately tests discrimination, probability calibration, fixed operatingpoint transport, and limited-label recoverability for pediatric pneumonia classification.<n>Cross-dataset shifts across countries affected ranking, probability alignment, and source-defined decision behavior differently.
  arXiv  Detail & Related papers  (2026-09-04T13:39:48Z)
• Passing Coarse Marginal Checks Can Be Cheap: Persona Mixtures and Imprecise Treatment-Response Estimates in an LLM Persona Panel [0.0]
  We study a fixed panel of sixteen lightweight persona-conditioned GPT-4.1 configurations in repeated strategic games.<n>Variation was strongly prompt-indexed, but its share depended on uncertainty assumptions.<n>Results concern one fixed model-prompt panel and do not establish human substitutability.
  arXiv  Detail & Related papers  (2026-08-02T04:10:11Z)
• Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair [36.56438114281786]
  We study the gap between finding a correct patch and retaining, verifying, and submitting it.<n>We derive an evidence-bound typed loop contract and instantiate its mechanically enforceable subset in a reference implementation.
  arXiv  Detail & Related papers  (2026-07-27T16:05:23Z)
• RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning [42.80742579670377]
  RareLens is a system that supports clinical decision-making across the entire rare disease trajectory.<n>Developed and evaluated on RareBench, a real-world dataset of 157,525 cases spanning all 33 Orphanet categories and more than 7,000 conditions.<n>It achieved an area under the curve of 0.917 for screening and top-1 accuracies of 65.5% and 89.8% for diagnosis and treatment.
  arXiv  Detail & Related papers  (2026-07-25T16:58:10Z)
• A Pathology Foundation Model for Gastric Cancer with Real-World Validation [47.19073124722865]
  We present GRACE, a Gastric-specific foundation model for Real-world Assessment and Clinical dEcision support.<n> GRACE was developed from multicenter gastric pathology datasets totaling 48,364 primarily HE-stained whole-slide images from 37,493 patients.<n>When calibrated to maintain non-inferior performance to senior pathologists, the AI-assisted workflow could triage 60.7% of atrophy and 82.7% of intestinal metaplasia cases.
  arXiv  Detail & Related papers  (2026-06-03T12:18:06Z)
• Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study [0.0]
  Machine learning models for chronic kidney disease often post strong discrimination scores on internal test sets.<n>We trained five classifiers on the UCI CKD dataset (400 patients, 62.5% CKD prevalence)<n>We evaluated each across calibration quality, conformal prediction coverage, and an eight-criterion deployment readiness framework.
  arXiv  Detail & Related papers  (2026-05-20T17:12:48Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• From Days to Minutes: An Autonomous AI Agent Achieves Reliable Clinical Triage in Remote Patient Monitoring [2.0918370570198763]
  Remote patient monitoring ( RPM) generates vast data, yet landmark trials (Tele-HF, BEAT-HF) failed because data volume overwhelmed clinical staff.<n>We developed Sentinel, an autonomous AI agent using Model Context Protocol (MCP) for contextual triage of RPM vitals.
  arXiv  Detail & Related papers  (2026-03-10T00:50:54Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology [48.732366302949515]
  Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety.<n>We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions.<n>We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration.
  arXiv  Detail & Related papers  (2026-03-02T00:50:39Z)
• An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastive Semantic Highlighting and LLM Judgment [0.0]
  Full-text screening is the major bottleneck of systematic reviews.<n>We present a scalable, auditable pipeline that reframes inclusion/exclusion as a fuzzy decision problem.
  arXiv  Detail & Related papers  (2025-08-17T17:41:50Z)
• Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations [44.71254888821376]
  We provide the first type-I-error and expected-rejection-time guarantees under general non-data generating processes. We show how to apply our results to inference on parameters defined by estimating equations, such as average treatment effects.
  arXiv  Detail & Related papers  (2022-12-29T18:37:08Z)

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.