Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi, Daniel Kang, Roy Ka-Wei Lee, Koustuv Saha, Christian Poellabauer, Christopher Lee, Sajeev Singh, Piyum Zonooz, Navin Kumar, Zeeshan Ahmed, Priyadarshini Kachroo
• Venue: arXiv: cs.AI
• Published: 2026-08-06
• Collected: 2026-08-07
• URL: http://arxiv.org/abs/2608.06366v1
• PDF: https://arxiv.org/pdf/2608.06366v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers have developed a system called nMAS for automating heart-failure feature engineering in electronic health records (EHRs). The system generates structured and aggregated features that improve the accuracy of heart failure phenotyping. The system is audited by a restricted large language model, and it demonstrated promising results in a single-institution cohort, but external validation is needed.

What the Document Says

• The research focuses on electronic health record (EHR) feature engineering as a significant challenge in clinical research and AI, accounting for 39-45% of data scientists' workload.
• Heart failure 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 partial automation with limited maintainability and evidence traceability.
• The authors developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering.
• nMAS was evaluated on 500 dummy patient records from nine EHR source tables.
• nMAS generated 132 structured and 70 rubric-scored aggregated features.
• The features were verified for structural integrity, rubric compliance, and provenance, and audited by a restricted LLM.
• Adding the aggregated features improved held-out AUROC (Area Under the Receiver Operating Characteristic Curve) from 0.895 to 0.963 for HFrEF (Heart Failure with Reduced Ejection Fraction) and 0.870 to 0.910 for HFpEF (Heart Failure with Preserved Ejection Fraction) phenotyping.
• An independent LLM-based rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points.
• The research demonstrates the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data.
• Evaluation was limited to a single-institution cohort, and external validation is needed.

Key Concepts Mentioned

• Electronic health records (EHRs)
• Heart failure
• Feature engineering
• Nimblemind Multi-Agent System (nMAS)
• Large language model (LLM)
• AUROC
• HFrEF
• HFpEF

Claims Made by the Document

• Existing rule-based and LLM-based approaches offer only partial automation with limited maintainability and evidence traceability.
• nMAS improves the accuracy of heart failure phenotyping when added aggregated features are considered.
• The developed nMAS system demonstrates the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data.

Evidence Used

• 69% of data scientists' workload is spent on EHR feature engineering
• nMAS generated and improved AUROC for HFrEF and HFpEF phenotyping
• An independent LLM-based rubric assessment scored the features at 81.5% of maximum points

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.