发表机构
Nimblemind; Singapore University of Technology and Design; University of Illinois Urbana-Champaign; Florida International University; University of California Los Angeles; Rutgers University Newark; Rutgers Institute for Health Health Care Policy and Aging Research; Robert Wood Johnson Medical School; Rutgers Health（宁敏德（音译）; 新加坡科技设计大学; 伊利诺伊大学厄巴纳-香槟分校; 佛罗里达国际大学; 加利福尼亚大学洛杉矶分校; 罗格斯大学纽瓦克分校; 罗格斯大学健康、医疗保健政策与老龄化研究所; 罗伯特·伍德·约翰逊医学院; 罗格斯医疗）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对心力衰竭EHR特征工程瓶颈，开发了nMAS管道，经500条虚拟记录验证，可提升HFrEF和HFpEF表型分析的AUROC，为自动化可审核特征工程提供了可行方案。
AI 中文摘要
电子健康记录（EHR）特征工程是临床研究与AI领域的主要瓶颈，占数据科学家工作量的39%-45%，在心力衰竭领域尤为突出：美国约有670万成年人受心力衰竭影响，需将碎片化的EHR数据与疾病特异性、基于指南的临床推理相结合。现有的基于规则及大语言模型（LLM）的方法仅能实现部分自动化，可维护性与证据可追溯性有限。我们开发了Nimblemind多智能体系统（nMAS）——一种用于自动化心力衰竭特征工程的、证据关联且基于评分标准的管道，并在来自9个EHR源表的500条虚拟患者记录上对其进行评估。nMAS生成了132个结构化特征及70个基于评分标准的聚合特征，这些特征经结构完整性、评分标准合规性及来源验证，并由受限LLM审核。添加聚合特征后，HFrEF表型分析的保留AUROC从0.895提升至0.963，HFpEF表型分析的保留AUROC从0.870提升至0.910；独立LLM对证据支持与方法学合理性的评分标准评估显示，这些特征获得了满分的81.5%。这些结果证明了针对复杂心血管EHR数据开展自动化、可审核的特征工程的可行性，但评估仅限于单机构队列，需进行外部验证。
英文摘要
Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering, and evaluated it on 500 dummy patient records from nine EHR source tables. nMAS generated 132 structured and 70 rubric-scored aggregated features, verified for structural integrity, rubric compliance, and provenance, and audited by a restricted LLM. Adding the aggregated features improved held-out AUROC from 0.895 to 0.963 for HFrEF and 0.870 to 0.910 for HFpEF phenotyping, and an independent LLM-based rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points. These results demonstrate the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data, though evaluation was limited to a single-institution cohort and external validation is needed.
