arXiv cs.CL· Elyas Irankhah, Shahed Salehzehi, Parisa Hosseini·· 11 小时前AI 评分31
RAG-TRACE：AI 生成心电图报告的测量证据与诊断完整性追踪
RAG-TRACE: Tracing Measurement Evidence and Diagnostic Completeness in AI-Generated ECG Reports
AI 导读
研究提出 RAG-TRACE，用于评估 RAG 检索到的诊断标准在 AI 生成心电图报告中是否有患者级测量证据支持。基于 1,083 份 PTB-XL 记录与 47 张标准卡，关键词检索使 46.8% 的 GPT-4.1-mini 报告引入无法验证或测量不符的标准，确定性验证规则撤回了 647 次标准应用。
正文 · 原文
Abstract:Purpose: Retrieval-augmented generation (RAG) can introduce electrocardiogram (ECG) criteria that lack patient-specific measurement support. This study evaluates the reliability of retrieved diagnostic criteria in AI-generated ECG reports. Methods: We analyzed 1,083 human-validated PTB-XL patient records using a library of 47 criteria cards, including 33 without numeric verification rules. Language models generated structured reports with and without retrieval. Criterion applicability was evaluated using Marquette 12SL measurements, with independent assessment using Uni-G and comparison against expert-validated diagnostic labels. Results: Keyword retrieval introduced untestable or measurement-disconfirmed criteria in 46.8% of GPT-4.1-mini reports. A deterministic verification rule withdrew 647 criterion applications, including 639 without numeric checks, while preserving 268 of 269 applications independently supported by Uni-G. Restricting retrieval to 14 testable criteria reduced the initial unsupported-criterion rate to 13.8%. Under matched instructions and an identical output schema, retrieval increased unsupported-criterion reports from 17.4% to 31.1%, while hypertrophy recall remained unchanged at 62.6%. Conclusion: These findings identify a fundamental limitation of retrieval-based clinical report generation: retrieved criteria do not necessarily provide valid patient-specific evidence. Measurement-based verification can reduce unsupported criterion applications, but diagnostic validity requires independent assessment.
| Comments: | Code and study materials available at this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01409 [cs.CL] |
| (or arXiv:2611.01409v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01409 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elyas Irankhah [view email]
[v1]
Sun, 1 Nov 2026 01:42:38 UTC (1,010 KB)
来源：arXiv cs.CL · arxiv.org