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 developed an automated system called nMAS for heart-failure feature engineering in electronic health records (EHR). The system generates structured and aggregated features that were verified and audited, improving the accuracy of heart failure phenotyping. However, the evaluation was limited to a single institution, and external validation is needed.

What the Document Says

• The study introduces nMAS, an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering in EHR.
• nMAS generates 132 structured features and 70 aggregated features.
• The features were verified for structural integrity, rubric compliance, and provenance.
• An auditing was done by a restricted LLM.
• Adding the aggregated features improved held-out AUROC for HFrEF and HFpEF phenotyping.
• The independent evaluation of evidence support and methodological soundness scored the features at 81.5%.

Key Concepts Mentioned

• electronic health records (EHR)
• heart failure
• feature engineering
• nMAS
• structured features
• aggregated features
• AUROC

Claims Made by the Document

• nMAS can automate heart-failure feature engineering.
• Adding aggregated features improves the accuracy of heart failure phenotyping.

Evidence Used

• Improvement in held-out AUROC for HFrEF and HFpEF phenotyping after adding the aggregated features.

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.