面向可信度感知生物医学AI的定量证据挖掘
Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
- Fraunhofer Institute for Algorithms and Scientific Computing (SCAI)（弗劳恩霍夫算法与科学计算研究所（SCAI））
- Kairntech SAS（Kairntech公司）
- Bonn-Aachen International Center for Information Technology (b-it), University of Bonn（波恩大学波恩-亚琛国际信息技术中心（b-it））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对生物医学AI证据提取的缺陷，提出定量证据挖掘框架，将提取的主张作为可审计证据对象，以构建可信度感知AI。
AI中文摘要：
生物医学人工智能（AI）系统正日益从文献、临床试验和监管文件中提取、组织和复用科学主张。但仅自动提取无法使主张成为可靠证据：只有当主张可追溯至其来源、与支持它的定量细节关联，并在其生物医学背景和不确定性中解读时，才具有实用性。随着大语言模型（LLMs）和日益自主的系统推动证据合成、知识图谱（KG）构建和决策支持，这一点至关重要。许多文本挖掘和LLMs管道仍以关系为中心：它们捕获药物-TREATS-疾病等实体和关系，但会丢弃主张成立的剂量、效应量、人群、对照、不确定性及条件。此类关系看似可操作，却难以验证、比较或复用。在此视角下，我们主张转向定量证据挖掘——提取值、单位、被测实体与属性、背景、不确定性、来源和可信度，作为结构化证据单元，填充感知证据的KG，并可检查其来源基础、单位一致性、完整性和生物医学可信度。我们概述了一个面向可信度感知AI的框架，该框架将提取的主张视为可审计的证据对象而非最终答案，明确测量了什么、变化了多少、在何种场景下、具有何种不确定性以及来自哪个来源。核心风险不仅在于提取错误，还在于看似证据却缺乏信任所需结构的主张。
英文摘要：
Biomedical artificial intelligence is moving from literature retrieval toward evidence synthesis for knowledge graphs, clinical decision support, and computational models. Yet most information-extraction systems still represent findings as simple relations, discarding the quantitative and contextual detail needed for interpretation and reuse. A claim that one entity affects another is insufficient when the magnitude, unit, population, comparator, experimental conditions, uncertainty, and provenance are missing. We define quantitative evidence mining as a framework for transforming biomedical findings into structured, context-rich, and auditable evidence units. We define the core elements of an evidence unit: the claim; measured entity and property; value, unit, or scale; comparator; population; biological or clinical conditions; temporal context; uncertainty; provenance; validation results; and expert-review status. We propose an eight-stage reference architecture spanning corpus selection, entity recognition, quantity extraction, context linking, normalization, evidence-unit assembly, multidimensional plausibility assessment, and export and governance. A central principle is that plausibility should not be collapsed into a single truth label; statistical, biological, methodological, contextual, and provenance-based support should remain explicit. The framework links information extraction to evidence synthesis and computational reuse, with applications in clinical-trial analysis, biomarker research, pharmacovigilance, knowledge-graph construction, and mechanistic modelling. It is a research agenda rather than a validated end-to-end system. Progress will require annotated multimodal benchmarks, rigorous component- and workflow-level evaluation, prospective testing, transparent provenance, and sustained expert oversight.
